{"_id":"agent-orchestrator-kit","_rev":"33-39d431fc8a5a2f078b14389c757a16b9","name":"agent-orchestrator-kit","dist-tags":{"latest":"0.18.0"},"versions":{"0.1.0":{"name":"agent-orchestrator-kit","version":"0.1.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js"},"dist":{"shasum":"ee2a9d6f1a9f66d6e7a9ef492e1801c9f67c74bc","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.0.tgz","fileCount":23,"integrity":"sha512-H042tv0vTbKdgV92iU5YeiWXQBZe5t2mhXb+FfxJAC+DVlk7cMjVpGYrdRfHqA1Ms7zpk1wpVUYzm8g/BnsUwA==","signatures":[{"sig":"MEYCIQCv23/TfiBAgaDgj/J/X/IsV3cCla9A/oH70mpBNLVLwgIhAPQo6g9bAF8pGbY7dKxuZOks/5wmIa0l9DKJC8X8XUCc","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":73024},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"574330ba7b71d157c1030e75a45ebf52c2ad1af5","scripts":{"link":"npm link","test":"node --test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.0","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.12.0","dependencies":{"prompts":"^2.4.2","commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.0_1781452517548_0.5937893540686332","host":"s3://npm-registry-packages-npm-production"}},"0.1.1":{"name":"agent-orchestrator-kit","version":"0.1.1","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.1","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js"},"dist":{"shasum":"55256145345f6a034a7178817e343af1fde08a08","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.1.tgz","fileCount":32,"integrity":"sha512-gAvLkWtoncS1zVHIN7dCFD1fT5Q4sh4dm96LS2U5gA1eG+GbqO+kTM2rPRRCpAi8GhwmciNQPaRGPsLoTCA1fQ==","signatures":[{"sig":"MEYCIQD+DOr8fBcPeCGOQl8q/VgN2Vv8EtEQJu/KmPe2beeEkAIhAIgH0cOK3r2pZBislc+Vws/D7kmEiW1Vq9HQ5h/Dnfwq","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":116031},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"69b1a031007efe1f8c4f16e5fe95b3d88b0dbde1","scripts":{"link":"npm link","test":"node --test test/*.test.js"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.0","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.12.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.1_1781452932891_0.694783529359273","host":"s3://npm-registry-packages-npm-production"}},"0.1.2":{"name":"agent-orchestrator-kit","version":"0.1.2","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.2","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"73a1d80d4abbe244933b77b570af5994967eba73","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.2.tgz","fileCount":32,"integrity":"sha512-sZmT+lH8WB3TDs/R/2qBSQf/soyHu3fmSqNzrrg1AMVZ2umaF7tk0wDLBz8mCaqvC49XAKF9TButPlfxLwDdyw==","signatures":[{"sig":"MEUCIF4PYpPdcZvCvQZLFZmpdfZqy4cATJvTHNBOZogSesdfAiEAwFwUJBdvIxQmFC2vx16uGjOwT8vcwj9LuKJlJIuzO4M=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":116315},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"e861e1e18f4bbd95d1ea422110a37f80a26307a8","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.0","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.12.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.2_1781453133320_0.7518816098892569","host":"s3://npm-registry-packages-npm-production"}},"0.1.3":{"name":"agent-orchestrator-kit","version":"0.1.3","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.3","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"9f5d7f3dad23320efa62a60aab50b6f249eda0fb","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.3.tgz","fileCount":39,"integrity":"sha512-1qS2H7GuJ8m7+HCw/z1fUUo+mEBjqnLPdLARLrsIeb4/Mf7UqG4SD2zFqmPkKPcoTskwHdgWloO2cwzeyJiuJA==","signatures":[{"sig":"MEUCIGniV5iZmemACayN4I9WcHdSUoVWP6gyLtSiDZdcufYKAiEAxKPvduMWhqP2s/oJeBk86drn36zF58Yt6x6WBpcm5/Q=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":137844},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"8f42dde0e656b7ba84c560f0b490eef281d891bb","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.0","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.12.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.3_1781521480853_0.1450222133651189","host":"s3://npm-registry-packages-npm-production"}},"0.1.4":{"name":"agent-orchestrator-kit","version":"0.1.4","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.4","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"5182342713b9c0eced70906f3744fa5928e0aa67","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.4.tgz","fileCount":39,"integrity":"sha512-x3/fj/acKKuuRi8gKuJVvEGpa5E4/CcMFgWW/+vGbafzM075jrpnIZTTdt/8l9XhMkBIXyVJQUjh/gF/mRqYDw==","signatures":[{"sig":"MEUCIQDzEU1ZoNdugth64Va5SqcDz3UK9YXIQCFyxzzWD7mHKgIgbIoZbKzVyRMrlYugyXDeADXSz8QjBvC+0kUGhTG5hEQ=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":138211},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"1afdfc333e85a7d9c726a629bbfa39fc34ffba41","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.4_1782589724289_0.6558456920125535","host":"s3://npm-registry-packages-npm-production"}},"0.1.5":{"name":"agent-orchestrator-kit","version":"0.1.5","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.5","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"c586234c95445cb9f1a752af3d459c9615091f69","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.5.tgz","fileCount":41,"integrity":"sha512-A75gzcLNTAfUKsMPPBmBjHbeBLaXgNhed0Zm9MBoQg/SDnKSzp3jGSCpjhiF0wUgEqB+DjXDEXT1138Cp7T2qw==","signatures":[{"sig":"MEUCIE2DWKnj2wiTaVWYjUc1HJoc87D/fm3P3zviN7i30JS5AiEAkdrSsCT79ZQEqmkG9Q+6mzTTt8dt/9p0uCYGRZPbVYQ=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":144849},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"ec61754bc9aca9831d92506368e855f6bf056c7f","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.5_1782592068851_0.2680212281293628","host":"s3://npm-registry-packages-npm-production"}},"0.1.6":{"name":"agent-orchestrator-kit","version":"0.1.6","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.6","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"8a828da493bdaa8e8331be09abda390a0d7e0e9f","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.6.tgz","fileCount":44,"integrity":"sha512-QTBXGvEwF0WAvqX9Gc5EVjMxxnIIwKwxWFgTWI9l8FOXpkgdhqwpl7SrpVeewTHZG3vBN10vgHP6L3KAapDAog==","signatures":[{"sig":"MEUCIQDGm0V6hHHwXdkpnt4Uv/zjFfM6bIpHS5/rkFcwQUzV2QIgfDPfr+u/wapokmJVZJ8EWT3/9BzoKu8SJ2OPgdKhXuM=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":163904},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"ea242b5cd38988c77f96ee8fa90606093f5c3686","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.6_1783006472510_0.968393365556453","host":"s3://npm-registry-packages-npm-production"}},"0.1.7":{"name":"agent-orchestrator-kit","version":"0.1.7","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.7","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"97f7c2866af13844c688dd5141ff10f48a7d190f","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.7.tgz","fileCount":46,"integrity":"sha512-m4m63Q9ZOc54SfHr/R0MCSjoRP3ZOa0Hsz+JHKBa5r4nTyTmEJMyuDMGTIXf46nQoOt8l1CsiCUcFktDl/XsJQ==","signatures":[{"sig":"MEUCIEWy0W1zbQORIsug1PygrXjPHydQlG8KnlKf/Q5rpO5pAiEAq1HCOaBOTG3ymAEWMlxkjwmw+reQ55wDc50jpJfsfYE=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":184783},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"edeedc127eab61c992ba5b7d36f636c393ecbf72","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.7_1783415998847_0.4847216271296191","host":"s3://npm-registry-packages-npm-production"}},"0.1.8":{"name":"agent-orchestrator-kit","version":"0.1.8","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.8","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"3182f0497559046f28749eb4cac42c74860fbe68","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.8.tgz","fileCount":46,"integrity":"sha512-CeUR9JG9x5ncC+OyNHrMEroffj6RZ2OgX93cKmUtgGJgFAqB+yDm9cLY4O6UCj1AlBGbSBWau7DkBvQKqxoIZQ==","signatures":[{"sig":"MEUCIHtr1dQRrZ2M2b9LGAR8JkzIxJgmamo92bzHbPZpMO4jAiEAuG5M1BWQEpxewGMl97x0nGh+FWtopkXfSBmW2I6g6oc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":187576},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"9343c5e754f3b87a8baa83983236c2aae25de9a1","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.8_1783417028340_0.9222581692944931","host":"s3://npm-registry-packages-npm-production"}},"0.1.9":{"name":"agent-orchestrator-kit","version":"0.1.9","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.9","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"71919ccc2a6a47200202a753ef4de344a0daa77c","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.9.tgz","fileCount":47,"integrity":"sha512-VZRgamvEE2GoZxQwcrD3ZH4uM48rE/u7X3wlbl7NVlLD2Fv41c/f0Zq28qBiVo69F5wh/1X19iszw4VGCh6sZQ==","signatures":[{"sig":"MEMCHwGjBUmT5LGqw/XmdCWYpFS78mLhSi+WsaSrrNSiPVACIDa0sRtvZKOKI1WbOpDjwrmX6unfKvJ/G9lhQDlamt6s","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":199327},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"85443d68a8d87e2c8c74d0e1ecddb9cbc5a7a1c2","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven pipeline with OpenSpec integration","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.9_1783841053625_0.46298324639193456","host":"s3://npm-registry-packages-npm-production"}},"0.1.10":{"name":"agent-orchestrator-kit","version":"0.1.10","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.10","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"435c1213be7b4615be4f2793a8160c7351dcf275","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.10.tgz","fileCount":53,"integrity":"sha512-Iezr0TnGRq+l4KVfAZ23mXYbyeap1VdqJf61WL/yLxCE6niHzqmbCk2walnmmtKhtHzI2fagS1qyCKUeZ1j99Q==","signatures":[{"sig":"MEUCIQCN1JS+OaRWdRcR8UUKhMJ/OVQxF9COj/Scq2etfDYaygIgcQhEIHws1JE9mOR4gfF4dRZGOlcKn2oHEUri8R47Nt0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":223906},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"b603926b1f36bb1a1b1d61bc26f7f0c1ece3071d","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline with cross-IDE custom subagents (openspec-guide, code-writer, code-reviewer, test-writer, setup-doctor, design-implementer)","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.10_1784104098306_0.6410091622443737","host":"s3://npm-registry-packages-npm-production"}},"0.1.11":{"name":"agent-orchestrator-kit","version":"0.1.11","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.11","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"2564f180423db3b4c3010a3765c6af12089158b2","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.11.tgz","fileCount":57,"integrity":"sha512-Iw9lMSkH8EB2qpVq/Q0cRlHLL8k2m7PuEJumSCX3K/w10cGiVlBUq9WVMV1qgtqqT1Xy7v68tpUZhAv33R8S6Q==","signatures":[{"sig":"MEUCIQD+M1/feMJdvkzp9ClU2mjYBORYizCJt+o0XzDI8hKkKwIgRftzIio5f7kScdY+CeQvROVAgzBq+lud8JHSNHZf3+I=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":245880},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"a2bace4b7fceba27e75794df5dbad62288fc7f6e","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, cross-IDE subagents, and optional local Figma PAT setup (figma-setup / figma-status / figma-fetch)","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.11_1784615159657_0.5521792943014787","host":"s3://npm-registry-packages-npm-production"}},"0.1.12":{"name":"agent-orchestrator-kit","version":"0.1.12","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.12","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"4f99b93e4c198676f6e44193f1ea6b48e582a1f4","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.12.tgz","fileCount":57,"integrity":"sha512-+bPiD4xEecK9jxLdk+EYE67Vgkvv/kjAHYrtG0/utaLcmcDgLG4ZIqDwgSV7RFt+kuIDRvyZsb9peK2FUabAeA==","signatures":[{"sig":"MEYCIQClHCsFQnURljWkFC/tXv1T8m2fAJsImtkRpBWKF8JvWQIhAIlS5cvoUHMSI+TTUZMYvrGiDq+hsaFl1ai7f/ekIRez","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":247551},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"26faa10e2d7f5eca0976512af8305f8d4e191dbc","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, cross-IDE subagents, and optional local Figma PAT setup (figma-setup / figma-status / figma-fetch)","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.12_1784616338030_0.8441868740692222","host":"s3://npm-registry-packages-npm-production"}},"0.1.13":{"name":"agent-orchestrator-kit","version":"0.1.13","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.13","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"93c2058a9a9b0ff06f942d0a85922cbbc1a31beb","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.13.tgz","fileCount":62,"integrity":"sha512-JFPHOG4bzThigX4eQYwxstJ5w2e00h35Ub4MEZ9gnPz0KgDFSbaRoso7odQ8z5llRIGFArQnFD85fMdVywj1oA==","signatures":[{"sig":"MEUCIQCgoDSogwcTWhhtGl9aTSNnA+Yx4Z0rYjCTf376YmxkhAIgTJHrrt13LZDmQ3LOWixjfKZ6Q1zs392jUxL+QL0KiGI=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":283970},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"650371b8521e398b3421c2fdebe18db26e04e074","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, session handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.13_1786609465069_0.425993380451521","host":"s3://npm-registry-packages-npm-production"}},"0.1.14":{"name":"agent-orchestrator-kit","version":"0.1.14","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.1.14","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"4846a803a9ffca6895b7c2ba5b01d2cc3a7b8b6c","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.1.14.tgz","fileCount":65,"integrity":"sha512-zU4DL6RjbEt9KhQE632do3bTsd50PYlqCPtRH/19lIA6CK+2PGjbULTx0Vxff5XpqGpxPmb2oAZKwmv3pMdypQ==","signatures":[{"sig":"MEUCIQDNcRmR0yMIix8cpGCjt6lkFqgvLvDyl8O20IODVhb1YAIgVQSrjs0Yp47gcWn3MXWayEo6VLJ1WNIaTSmPfSrMWx8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":327826},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"69e4e1278a6102f18b1fd3c1e9e9835cef19299c","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff CLI, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.1.14_1786655478449_0.012545674530967998","host":"s3://npm-registry-packages-npm-production"}},"0.2.0":{"name":"agent-orchestrator-kit","version":"0.2.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.2.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"280506e37904729fc8aa62f9d6d2121effcfb7b0","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.2.0.tgz","fileCount":65,"integrity":"sha512-4VT6pvushypyVc+0x7f9pBLvyVxeaoNMROI2+DCIYs5ItzjMJIP/oQI+hR5EIB0FMM0/nz7ZHdsR/nBIug8Hsw==","signatures":[{"sig":"MEQCIEEK/aZyyrcLYeavjdKoo5YpgEE+qWc0pD8sgVPLOeVdAiAsPsYWqO15KssrWiMcdjOuqS0M4T3J+pMm+IhKshNKLw==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":311592},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"7ec7510d6083731812f3d946e8b9df4119ac5bd6","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff CLI, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.2.0_1787038683282_0.48451908869096605","host":"s3://npm-registry-packages-npm-production"}},"0.3.0":{"name":"agent-orchestrator-kit","version":"0.3.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.3.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"06583931c68c85338a9ca364c4b5c4526cbc86cf","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.3.0.tgz","fileCount":65,"integrity":"sha512-qIYNkHE6SWIZ2sXXmHTan3dauWIPazbYOiq5UQI+4V/jUDIRd1rOKsadh2toaS6KoDW6x07DqpqSsGOSih4txg==","signatures":[{"sig":"MEYCIQDLyihy1VA5hhf9yURDeC91TgPSa5tDvAR/CI6BzNwaNgIhAPge/GLIUoX9J4/M9I0yiVsBcNFOr5WB7soPp3iG/YxK","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":323941},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"6900325742e2a4d29947b59e63d8776c7114ca7d","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff CLI, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.3.0_1787063282791_0.8510690559736329","host":"s3://npm-registry-packages-npm-production"}},"0.4.0":{"name":"agent-orchestrator-kit","version":"0.4.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.4.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"20e1f82282645a7c3edeafb617fd3202e3ab44c3","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.4.0.tgz","fileCount":72,"integrity":"sha512-VnUKXzQHOjoZkfx+rOJV9wTwTLVc426qlu5RNrqQp3gHgL9cQQgWGmfEktI8U97fH5i8mDg2v+Kl0rINBCISmA==","signatures":[{"sig":"MEQCIFcFgLCck4hU6FWRSNhe043gS9B043rBoJOrXF2bGY7KAiBM+vLVLIJJtLo/k+C8knEz0aYuVJ8P24aBHlHeBHvptA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":377818},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"1274897335b351baddc2a7e9372ea53789a547c4","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.4.0_1787906846343_0.5342490356056278","host":"s3://npm-registry-packages-npm-production"}},"0.5.0":{"name":"agent-orchestrator-kit","version":"0.5.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.5.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"9129d5b4869eec160b99c2be6660fba838d38d3f","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.5.0.tgz","fileCount":72,"integrity":"sha512-QGGpH0T6mI5veEq0/EtUfkOPN4/1gQyjlWVg9gQLlKh1r3zsp3QgMrTA/fZGIeMuu/7+ny4NokibXRgQtRdr7g==","signatures":[{"sig":"MEUCIG0kb3+4qEZt47tDZZ6MjLeFRwfnRYCcL8kBmZna34UAAiEAy9frmJc6N750ribO/SZEFQnXcRsW78hTMaMxGJQ7Xjs=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":394781},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"1429aa3457cb3df0823a4e6fd4df178777e2281c","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.5.0_1787988255913_0.09102975386349677","host":"s3://npm-registry-packages-npm-production"}},"0.6.0":{"name":"agent-orchestrator-kit","version":"0.6.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.6.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"ea032caad9549f24286f5c99c58589a1e2939724","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.6.0.tgz","fileCount":74,"integrity":"sha512-3d3PBqeNswa7WpC3j/1BZCY2bp26fV72KVMmw7l75Hhfu22xBymLcF/kM+6QkJXNfkjfWzo9xh5xLO8ng1MFsQ==","signatures":[{"sig":"MEUCIQCF2AaLwvaGuUkpuhVA6qSZfcp9W6PYq1OA+1FP3VKhvgIgS+yfWj2UW7eSF/fbxmA18QxOMW6GHheHeWfLiyk1vGY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":433773},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"70e1851d37a70ccb636e5d4a2826e004203af686","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.6.0_1788028216786_0.3280076652205297","host":"s3://npm-registry-packages-npm-production"}},"0.7.0":{"name":"agent-orchestrator-kit","version":"0.7.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.7.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"f807ffb21bbc18afac0892c646558a8046a9dd1d","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.7.0.tgz","fileCount":75,"integrity":"sha512-WCIg7bpUfNWOTil5zoJTU77xzEhgcAmAXGmSuSDlUHFg9QweEdoHFZCMKUvGPbg1qNsVLn8W3b6slugiAPI2NA==","signatures":[{"sig":"MEQCIArR0TzFtVO28uo6VGbgCdug/sMhzeCJbGP5Kg/9pXM+AiBjPmzbvo/AbEf8eUX8LmWbkBbuFb2bH6vSoNXuJIYWbQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":465899},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"c2659a430427cf4df58a65050b82af5a52278a12","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.7.0_1788073628806_0.4550479119314179","host":"s3://npm-registry-packages-npm-production"}},"0.8.0":{"name":"agent-orchestrator-kit","version":"0.8.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.8.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"e26bfe680d46fda8770855a39a234b742e6c32c1","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.8.0.tgz","fileCount":76,"integrity":"sha512-EIUlf1jGHJF89aNIGVb2kbriXLpU7igH4snrXGRH6eA0Mmu9TXtghOB+oXzcF8M/glX4o4Y97x1TyvvLinoHiw==","signatures":[{"sig":"MEQCIFMCNMQAFF9Bf4cySaxw/6yPuhNR55pXBUNIrb8zo/4DAiAbKbagzkuRc3LfenMAIXHGQNTsBaNgrHo/zil4/BRQ6A==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":479910},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"b861b7055cf6b00e9a9b1dc48e48adc8385a3ad5","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.8.0_1788153500725_0.756431990696194","host":"s3://npm-registry-packages-npm-production"}},"0.9.0":{"name":"agent-orchestrator-kit","version":"0.9.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.9.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"306a8862249024d817b95d05e14074be2d4ecc78","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.9.0.tgz","fileCount":79,"integrity":"sha512-TY/ktPP3emuFPNCRGmG/BDynsqRgEJqA1DKbcToc6GjJkbn2Qv5DOFGadLOg2NXjuY3IXJs+A5XYDd5r5ADdxQ==","signatures":[{"sig":"MEUCIBC9NU42UlxkMrKsfgMVbriQLd3UwGhkEvt/+7nW2OuCAiEAyX1MyAUWC39ksjyUtYXXY5i/kZhWFJHon/zs8a9jkUM=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":500501},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"78848b3c253fa2ba6a5eddbbe5e7b9662a6af229","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.9.0_1788167940703_0.20403180074399385","host":"s3://npm-registry-packages-npm-production"}},"0.10.0":{"name":"agent-orchestrator-kit","version":"0.10.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.10.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"ccc755c52c15beebbdf543298a4a44e7ad1ff65f","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.10.0.tgz","fileCount":79,"integrity":"sha512-cI6DAkjHG2BgXIEut1KTeUiRitx/zNL4SpLsHQiDBT+sMFtb64MuGH+1H6kKtKdS6Z+Or+DTwRVUFBrYVB8AqQ==","signatures":[{"sig":"MEUCIBBZbM8NDrEGNtEe1087QN9wRnEOKwlndIYlL+oNzQhtAiEA76NhEcpcRMSGmpR3kyfMmjI1+rZ8UXt3coRTdlYQPSQ=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":503306},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"3a887f7eaefd617f8880b2cc1200453b91b523d7","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.10.0_1788178463785_0.8232113718709013","host":"s3://npm-registry-packages-npm-production"}},"0.11.0":{"name":"agent-orchestrator-kit","version":"0.11.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.11.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"cac86a800677d5d97e6fdc5fa6b09506cb23b32e","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.11.0.tgz","fileCount":79,"integrity":"sha512-2FHDox7ks/rZeAaLJ1cuXUSxdyUa66Fqu/FzKBbJdhc8jDMzp3Exw5h3ZP9Ql97P36yI+xBv0IhY9xoJ/uSPmQ==","signatures":[{"sig":"MEYCIQCVLqknmzBjLXzQxerimuK3NddXzxlPaP5EYQLeYzFpBAIhAMCiK0j6fHgnSO5pX58OjQ9wYowjXp0Beduih2MzrggS","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":532933},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"9e42ff27f46c13900ea2a7159790805720b97017","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.11.0_1788332836750_0.8649710842769738","host":"s3://npm-registry-packages-npm-production"}},"0.12.0":{"name":"agent-orchestrator-kit","version":"0.12.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.12.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"108b9378d137285d5e7d9c984ccd37e0b8321915","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.12.0.tgz","fileCount":79,"integrity":"sha512-dcZXchkr7wgWt8JCnv99LiUy5fdNVadj4y1q2pyw2b1IybM2Hgkmmey/knEoUorpW9PhX/rC3a+5NXQ+Jat33g==","signatures":[{"sig":"MEYCIQDVoyODCiVu3b+wlztikr0799utGXSll2B96kuvvTYgQAIhAJZTurI6i8QMGMP8JQIoqU+wCDU34lyQtnRG/cHvi8x0","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":543511},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"b12a75792a42f274d3d2d0ee239ed7328b05de8b","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.12.0_1788379823150_0.07766821468325436","host":"s3://npm-registry-packages-npm-production"}},"0.13.0":{"name":"agent-orchestrator-kit","version":"0.13.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.13.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"22505d31e7b0d29baf9ba5eb43a6e4efd243c9c5","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.13.0.tgz","fileCount":79,"integrity":"sha512-v0kUDSOOAcCfpVEPcjPGGZJjbgmG69lp17TBHe84tDUkuffzRy5t/IGAo/xkw183KIX1u4IA/jw2vLSpl9aw/A==","signatures":[{"sig":"MEUCID7GUsxMmmtk/QLLDlxBCx8Q9fxIVUFy2VmFCQjqT6JCAiEAtTBqKUGk3LjHp+iUsaO5NoVSN7+WGTSslok+3x1CJd8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":552469},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"eee2150e11577aff933c82bd45ccf7411186fa47","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.13.0_1788536137514_0.8991443056722541","host":"s3://npm-registry-packages-npm-production"}},"0.14.0":{"name":"agent-orchestrator-kit","version":"0.14.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.14.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"e1dfe41cd9d3d69541f86b3f32c5f19d57ce6967","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.14.0.tgz","fileCount":80,"integrity":"sha512-IZskZkRfusGCEqhUMum0pw32f9sCe6icacVFrRSWLU8t/b2cNYeV0chhEMoYG99g1wxwKJpRvQnCyRwlkxIUiA==","signatures":[{"sig":"MEYCIQCpwcE0p8YRmQGw/9yT++pheg18YgRblnJTH6Rc/GnjKQIhAO219LSXcyJ/KhvQazdUHcEiUEnjWxlPFYcqFFTDrnLL","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":576577},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"bbdb11fb96a3c394f5ea54ec417aa4ca51e582ca","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.14.0_1788812676858_0.1315181432237713","host":"s3://npm-registry-packages-npm-production"}},"0.14.1":{"name":"agent-orchestrator-kit","version":"0.14.1","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.14.1","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"f550da3dec1fbd139f65ff38c1337fe30fc22808","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.14.1.tgz","fileCount":79,"integrity":"sha512-wSKLBJixVk7/082VGxOguNvbcwbyMW3WqIIpScsQNnJVXJeVnKOnbnXy1SaNUX4id0LQx04fm1iEI2YfJqcfnA==","signatures":[{"sig":"MEQCIDyMVjddZBCMzmZuxDchkENeHOfWw4+rVjqBf92xhC+HAiAJjv8RU52hP+VRNsJf/yjJXBYX8LiX3TpH7hmXQINgfg==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":585278},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"5048a8f34413b1745463206f9f2ff81e6fe4d570","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.14.1_1788832183097_0.9639543922931308","host":"s3://npm-registry-packages-npm-production"}},"0.15.0":{"name":"agent-orchestrator-kit","version":"0.15.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.15.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"f9b1a488393f89ad762e09478f828dd61563cb80","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.15.0.tgz","fileCount":79,"integrity":"sha512-7zmbYK+6aY9kJl8K3458SzI2YQRIVBtE8vNFoncG8W3lEhROTOAzrhwZ7suwWOr6IrawhSXfGa+MDz8EpuSWrQ==","signatures":[{"sig":"MEUCIQDGdzgBT/lSErU90ipZ3605TzSJhNUlbGV2XM8jg5/90wIgCgzMrsVa8SC9Jggqs0FLMWcVm5rSbQf7LRF4PujGWlM=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":590260},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"44a20e5e6bdc17cfd1e8eabbfb779cd0e69782e7","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.15.0_1788851944322_0.6627764321086203","host":"s3://npm-registry-packages-npm-production"}},"0.16.0":{"name":"agent-orchestrator-kit","version":"0.16.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.16.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"73f39fe1e2312d326a2621bda443b6acaa3c8367","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.16.0.tgz","fileCount":80,"integrity":"sha512-JWdeoBdewj/Q8hMVjQsZ5Xp99/IkeD5/mpjr1u2tGL2f/z0EvEWS5iaf7s0fMlLiXRRbTvKK8Dj4ZMw1AXzMWA==","signatures":[{"sig":"MEUCIHomCOaQNC9jPUp619n5dqH4aop32rBrC+op1yGVnwrBAiEA0kfQvC6IhZmsHgShpOLoMHoK27Dem70Sn+Sl8hA52cQ=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEYCIQCYfzy0v1d8LFhgyBkb3vXamVpw3psDj6DT+bXcn5ywkQIhAOGfq5RbgxMrt7lkHKrBN1Ige1E4Ja3OP5niyJC2+Hzl","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":603026},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"99f57bbd77f904bd4247b2ee46564cc8483d247e","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.16.0_1790345206219_0.4028238701375586","host":"s3://npm-registry-packages-npm-production"}},"0.17.0":{"name":"agent-orchestrator-kit","version":"0.17.0","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","_id":"agent-orchestrator-kit@0.17.0","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"dist":{"shasum":"27faac30a1a1492e385fb68c35f69d282481e93b","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.17.0.tgz","fileCount":80,"integrity":"sha512-7uKnDi+xSirIvSejlmAVMFkte9tsXbToYZqzmwZjscMu/GdF8uWjjL/jnOoOwJPaUNs1+uEo/wbUS6bttLQB/Q==","signatures":[{"sig":"MEUCIAsGAEfSL4b7IVh2+BzF2X/v+chGIehqe149TfGPCNJqAiEA6+D+5POYxFnA6A1ySxevSNAwqukh5goU4NjtAWCJTZ4=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIDSVNPjWunUlgIRVNziG4PYwyFRDyetPuI8+p8QO6qoLAiEA8wOmrICu+dz0erpKNTHEHqVZ0JXN+1s0cGYQtnT/XP4=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":643836},"type":"module","engines":{"node":">=18.0.0"},"gitHead":"ece045dc7c542afc5600e024637db020d597488d","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"tmp":"tmp/agent-orchestrator-kit_0.17.0_1790921838200_0.31365079100657245","host":"s3://npm-registry-packages-npm-production"}},"0.18.0":{"_id":"agent-orchestrator-kit@0.18.0","bin":{"agent-orchestrator":"bin/agent-orchestrator.js","agent-orchestrator-kit":"bin/agent-orchestrator.js"},"bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"dist":{"shasum":"fd8a95ac1f55f2ed1eee2b6c4660c32724e7d79e","tarball":"https://registry.npmjs.org/agent-orchestrator-kit/-/agent-orchestrator-kit-0.18.0.tgz","fileCount":80,"integrity":"sha512-98P24UuBl0owMgGJD+38KlLkvjFE6sfUOm6SfNpVh9M9yv47MWIfU0zsqTd9qwX7W3JJV1DyEAoD6HvJof5+xA==","signatures":[{"sig":"MEYCIQDVpxIm01Fx9R++qYvidh44aT1evTAM0LRmtdSDpDYPrAIhANvdYfuULXLMtMfSmYBT9ZO4GpFROTA7DmkfTYwa6XeS","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEQCIFFamMgANQpWmRgRQVbDW2LTzMPHFeEdfC6rmMicgaF3AiB3JzRJdAMu2UeBt4Dky2O2JYSxSqh1iW2Mcdz5Uf7oBg=="}],"unpackedSize":662788},"name":"agent-orchestrator-kit","type":"module","author":{"name":"Maksim Shevyakov","email":"makshc2"},"engines":{"node":">=18.0.0"},"gitHead":"dd19ddc7a834050cafc7a5141f5cb0b16b5aebf8","license":"MIT","scripts":{"link":"npm link","test":"node --test test/*.test.js","prepack":"chmod +x bin/agent-orchestrator.js","release:tag":"git tag v$(node -p \"require('./package.json').version\")","release:check":"npm test && npm pack --dry-run","prepublishOnly":"npm test"},"version":"0.18.0","_npmUser":{"name":"makshc2","email":"makshc2@gmail.com"},"homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"_npmVersion":"10.9.4","description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","directories":{},"maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"_nodeVersion":"22.22.0","dependencies":{"commander":"^12.0.0","picocolors":"^1.0.0"},"_hasShrinkwrap":false,"devDependencies":{"@fission-ai/openspec":"^1.4.1"},"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/agent-orchestrator-kit_0.18.0_1791014746471_0.7220154229535867"}}},"time":{"created":"2026-06-14T15:55:17.428Z","modified":"2026-10-03T08:05:46.736Z","0.1.0":"2026-06-14T15:55:17.671Z","0.1.1":"2026-06-14T16:02:13.029Z","0.1.2":"2026-06-14T16:05:33.490Z","0.1.3":"2026-06-15T11:04:41.026Z","0.1.4":"2026-06-27T19:48:44.418Z","0.1.5":"2026-06-27T20:27:49.001Z","0.1.6":"2026-07-02T15:34:32.646Z","0.1.7":"2026-07-07T09:19:59.007Z","0.1.8":"2026-07-07T09:37:08.499Z","0.1.9":"2026-07-12T07:24:13.770Z","0.1.10":"2026-07-15T08:28:18.446Z","0.1.11":"2026-07-21T06:25:59.824Z","0.1.12":"2026-07-21T06:45:38.171Z","0.1.13":"2026-08-13T08:24:25.233Z","0.1.14":"2026-08-13T21:11:18.614Z","0.2.0":"2026-08-18T07:38:03.432Z","0.3.0":"2026-08-18T14:28:02.984Z","0.4.0":"2026-08-28T08:47:26.509Z","0.5.0":"2026-08-29T07:24:16.040Z","0.6.0":"2026-08-29T18:30:16.924Z","0.7.0":"2026-08-30T07:07:08.958Z","0.8.0":"2026-08-31T05:18:20.858Z","0.9.0":"2026-08-31T09:19:00.859Z","0.10.0":"2026-08-31T12:14:24.009Z","0.11.0":"2026-09-02T07:07:16.914Z","0.12.0":"2026-09-02T20:10:23.372Z","0.13.0":"2026-09-04T15:35:37.670Z","0.14.0":"2026-09-07T20:24:37.150Z","0.14.1":"2026-09-08T01:49:43.255Z","0.15.0":"2026-09-08T07:19:04.496Z","0.16.0":"2026-09-25T14:06:46.325Z","0.17.0":"2026-10-02T06:17:18.309Z","0.18.0":"2026-10-03T08:05:46.588Z"},"bugs":{"url":"https://github.com/makshc2/agent-orchestrator-kit/issues"},"author":{"name":"Maksim Shevyakov","email":"makshc2"},"license":"MIT","homepage":"https://github.com/makshc2/agent-orchestrator-kit#readme","keywords":["ai-agent","cursor","claude-code","amp-code","openspec","sdd","agent-orchestration","subagents","custom-subagents","design-to-code","figma","figma-mcp","developer-tools"],"repository":{"url":"git+https://github.com/makshc2/agent-orchestrator-kit.git","type":"git"},"description":"Universal AI agent orchestration kit for Cursor, Claude Code, and Amp Code — spec-driven OpenSpec pipeline, conductor subagents, durable session handoff, factory gates and MCP setup, cloud-agent handoff, and optional local Figma PAT setup","maintainers":[{"name":"makshc2","email":"makshc2@gmail.com"}],"readme":"# agent-orchestrator-kit\n\nUniversal AI agent orchestration kit for **Cursor**, **Claude Code**, and **Amp Code** — spec-driven OpenSpec pipeline with **cross-IDE custom subagents**.\n\n[![npm version](https://img.shields.io/npm/v/agent-orchestrator-kit)](https://www.npmjs.com/package/agent-orchestrator-kit)\n[![license](https://img.shields.io/npm/l/agent-orchestrator-kit)](LICENSE)\n\n## What It Is\n\nA portable kit that installs a **role-separated AI pipeline** into any project:\n\n```\nexplore → [design] → propose → review → apply → verify → archive\n```\n\nEach role runs in a **separate agent session**. The parent `/opsx:*` session is a conductor: it restores state, spawns the routed specialist, verifies its report, and does not perform specialist work itself. OpenSpec files remain the requirements/tasks source of truth; Memory MCP and `openspec/changes/<name>/handoff.md` index phase state and the next command.\n\n**Figma PAT setup** — local `.agents/figma.local.env` + MCP launcher (token never in chat / committed MCP JSON). See [Figma token](#figma-token-optional).\n\n**Custom subagents** ship with the kit and work in all three IDEs:\n\n| Subagent | Role |\n|----------|------|\n| `openspec-guide` | Pipeline navigator — status, gates, next `/opsx:*` command |\n| `code-writer` | Scoped task implementation against stack conventions |\n| `code-reviewer` | Spec-compliance + convention review of the resulting code |\n| `test-writer` | Automated tests for recently changed code |\n| `setup-doctor` | Orchestrator / MCP / sync diagnosis and repair |\n| `design-implementer` | Pixel-accurate Figma / screenshot → production UI |\n| `codebase-explorer` | Read-only repository investigation for explore |\n| `design-intake` | Design source → durable brief + assets |\n| `spec-architect` | Proposal, design, delta specs, and tasks |\n| `spec-reviewer` | Pre-apply artifact gate + `review.md` |\n| `spec-archiver` | Delta merge and completed-change archive |\n| `session-handoff` | Restore/persist Memory + `handoff.md` + expanded next-thread prompt |\n\nDelegation is **differentiated per phase** (lean model): thinking-heavy phases spawn a mandatory specialist, apply is parent-driven, archive is a deterministic CLI:\n\n| Phase / signal | Delegation |\n|----------------|------------|\n| Status / gates / next command | `openspec-guide` |\n| Session start restore / session exit persist | parent-driven CLI (`handoff --restore` / `handoff <name>`); `session-handoff` is a fallback only |\n| Kit / MCP / sync repair | `setup-doctor` |\n| Explore repository research | `codebase-explorer` (mandatory) |\n| Design / propose / spec review | `design-intake` / `spec-architect` / `spec-reviewer` (mandatory) |\n| Apply | parent implements from `tasks.md` + `apply-notes.md`; `code-writer` / `test-writer` optional for ≥ 2 independent tasks or explicit request; `design-implementer` for design-brief/Figma tasks |\n| Pre-PR code review | `code-reviewer` |\n| Archive | `npx agent-orchestrator-kit archive <name>` (CLI — no subagent; `spec-archiver` is a fallback when the CLI is unavailable) |\n\n- **Cursor** → `.cursor/agents/` (native subagents)\n- **Claude Code** → `.claude/agents/` (native subagents)\n- **Amp Code** → auto-generated `subagent-*` skill wrappers in `.agents/skills/`; each wrapper requires the parent to spawn an isolated subagent, never execute it in the main thread\n\nWorks with:\n- [Cursor](https://cursor.sh) — via `.cursor/rules/` + `.cursor/skills/` + `.cursor/agents/`\n- [Claude Code](https://code.claude.com) — via `CLAUDE.md` + `.claude/skills/` + `.claude/agents/`\n- [Amp Code](https://ampcode.com) — via `AGENTS.md` + `.agents/skills/` (native, including `subagent-*` wrappers)\n\n## Why\n\nWithout role separation, AI agents tend to mix thinking with implementation, skip spec review, and accumulate context debt across one long chat. This kit enforces the discipline at the filesystem level: each role has explicit allowed files, a checklist, and a handoff gate before the next role starts.\n\nThe `AGENTS.md` / `CLAUDE.md` files tell each IDE exactly what the roles are, so you don't repeat yourself every session.\n\n## Quickstart\n\n**🆕 New project:**\n\n```bash\nnpm i -D @fission-ai/openspec && npx openspec init\nnpx agent-orchestrator-kit@latest init --profile generic          # default: GitHub Actions CI\n./scripts/sync-local-agent-skills.sh\n```\n\nGitLab-hosted project with the opt-in AI Spec Verifier (needs the Amp CLI, `AMP_API_KEY`, and a GitLab token in CI):\n\n```bash\nnpx agent-orchestrator-kit@latest init --profile generic --ci gitlab --spec-verify\n```\n\nSee [Installation](#installation) for profile/CI options.\n\n**🔄 Already have the kit installed? Upgrade to latest (v0.18.0 makes the `/opsx:propose` conductor thin — it no longer researches the repo before or after the `spec-architect` spawn — and adds two deterministic checks: `gate-check --review` warns when a change's artifacts outgrow the size budget, and `gate-check --review-md` checks `review.md` against the `/opsx:review` schema; `spec-architect` and `spec-reviewer` also get reading rules):**\n\n```bash\nnpx agent-orchestrator-kit@latest update\nnpx agent-orchestrator-kit@latest sync         # or: ./scripts/sync-local-agent-skills.sh\nnpx agent-orchestrator-kit@latest mcp-setup    # optional — GitHub/GitLab from origin + browser\nnpx agent-orchestrator-kit@latest figma-setup  # optional — local Figma token\nnpx agent-orchestrator-kit@latest hooks-setup  # optional — pre-commit review gate\nnpx agent-orchestrator-kit@latest status\n```\n\nThis refreshes kit-managed files, installs `.agents/subagents/`, generates Amp `subagent-*` skill wrappers, and syncs agents into `.cursor/agents/` + `.claude/agents/`. See [Changelog](#changelog) for the full list.\n\n## Installation\n\n### Prerequisites\n\n- Node.js ≥ 18\n- [OpenSpec](https://github.com/fission-ai/openspec) installed in the project:\n\n```bash\nnpm i -D @fission-ai/openspec\nnpx openspec init\n```\n\n> **Important:** `agent-orchestrator-kit init` does **not** install OpenSpec automatically. Install OpenSpec first (or ensure it exists in the repo), then run kit init.\n\n### Install the kit\n\n```bash\nnpx agent-orchestrator-kit init\n```\n\nWith a stack profile:\n\n```bash\nnpx agent-orchestrator-kit init --profile vue3\nnpx agent-orchestrator-kit init --profile node\nnpx agent-orchestrator-kit init --profile generic\nnpx agent-orchestrator-kit init --profile mvp    # demos / spikes — no review gate\n```\n\nWith options:\n\n```bash\nnpx agent-orchestrator-kit init \\\n  --profile vue3 \\\n  --name \"My Project\" \\\n  --lang uk\n```\n\nFor GitLab-hosted projects (verify via `prebuild` hook — no GitHub Actions):\n\n```bash\nnpx agent-orchestrator-kit init --ci gitlab\n```\n\nThis installs `.gitlab/agent-verify.yml`, injects `verify:openspec` and PM-aware `prebuild` into `package.json`. When DevOps runs `npm run build` (or yarn/pnpm build), npm lifecycle runs `prebuild` first → `npx openspec validate --all --strict` executes automatically.\n\nOptional dev-controlled CI before DevOps setup: copy `templates/.gitlab-ci.starter.yml.example` from the kit to `.gitlab-ci.yml` and adjust stages as needed.\n\nSkip CI files entirely:\n\n```bash\nnpx agent-orchestrator-kit init --ci none\n```\n\nDefault remains GitHub Actions (`--ci github`).\n\n### Sync to local IDEs\n\nAfter init (and after every update):\n\n```bash\n./scripts/sync-local-agent-skills.sh\n```\n\nThis copies `.agents/` to your local IDE directories (not committed to git).\n\n## What Gets Installed\n\n```\nyour-project/\n├── AGENTS.md\n├── CLAUDE.md\n├── .github/workflows/agent-verify.yml   # CI (default --ci github)\n├── .github/workflows/spec-verify.yml    # AI Spec Verifier (--ci github --spec-verify, opt-in)\n├── .gitlab/agent-verify.yml             # CI fragment (--ci gitlab)\n├── .gitlab/spec-verify.yml              # AI Spec Verifier (--ci gitlab --spec-verify, opt-in)\n├── openspec/config.yaml.example         # only when openspec/config.yaml does not exist yet\n├── .agents/\n│   ├── orchestrator.yaml\n│   ├── mcp.json.example                 # Cursor / Claude Code MCP template (.mcp.json)\n│   ├── amp.settings.json.example        # Amp MCP template (.amp/settings.json)\n│   ├── figma.local.env.example          # + github/gitlab.local.env.example (token templates)\n│   ├── commands/                        # /opsx:* role commands\n│   ├── rules/                           # auto-applied orchestration rules\n│   ├── subagents/                       # 12 stage/custom subagents (Cursor/Claude/Amp)\n│   └── skills/\n│       ├── agent-orchestration/         # Pipeline orchestration\n│       ├── openspec-howto/\n│       ├── openspec-explore/\n│       ├── openspec-propose/\n│       ├── openspec-apply-change/\n│       ├── openspec-archive-change/\n│       ├── openspec-sync-specs/\n│       └── spec-workflow-openspec/\n├── scripts/sync-local-agent-skills.sh\n├── scripts/{memory,figma,github,gitlab,browser}-mcp-launcher.cjs   # stdio MCP launchers (always)\n├── scripts/cursor-spend-hook.cjs + cursor-spend-collect.cjs        # Cursor spend capture (always)\n├── scripts/pre-commit-gate-check.sh     # installed unconnected; wire with hooks-setup / --hooks\n├── scripts/post-pr-verdict-github.sh    # always copied; used only by the GitHub Spec Verifier\n├── scripts/verify-specs.sh + post-mr-verdict.sh   # (--spec-verify, opt-in)\n├── .mcp.json                            # seeded from mcp.json.example if missing (memory + figma; mcp-setup adds VCS/browser); no secrets, committing is fine\n├── .amp/settings.json                   # local only — seeded from amp.settings.json.example the same way\n└── .cursor/hooks.json + .cursor/memory.json       # local only — spend hook entries + Memory MCP store\n```\n\n### Included in kit\n\n| Category | Contents |\n|----------|----------|\n| Orchestration | Role-separated pipeline (explore → design → propose → review → apply → verify → archive), `AGENTS.md`, `orchestrator.yaml`, review command |\n| OpenSpec skills | All 7 skills for `/opsx:*` workflow |\n| IDE sync | Cursor + Claude Code sync script (`--delete` semantics — removes stale skills/subagents/commands) |\n| Subagents | 12 exclusive routes: guide/setup/session-handoff, explore/design/propose/review/archive stage agents, and apply implementation/test/code-review agents — native in Cursor + Claude Code, isolated Amp `subagent-*` wrappers |\n| CLI gates | `npx agent-orchestrator-kit status` / `gate-check` / `archive` / `handoff` / `metrics` / `memory-setup` — deterministic review-gate, archive, session-handoff, and change metrics (always via `npx`; see `cli-via-npm.mdc`) |\n| CI | `agent-verify.yml` — GitHub (default) or GitLab fragment + `prebuild` hook, both run `gate-check` |\n| AI Spec Verifier | `spec-verify.yml` + verifier scripts — GitLab or GitHub, opt-in (`--spec-verify`) |\n| MCP templates | `.agents/mcp.json.example` (Cursor / Claude Code `.mcp.json`) and `.agents/amp.settings.json.example` (Amp) — five stdio launchers: `memory`, `figma`, `github`, `gitlab`, `browser` |\n\n### Not included (install separately)\n\n| What | How |\n|------|-----|\n| OpenSpec CLI | `npm i -D @fission-ai/openspec && npx openspec init` |\n| Stack skills (Vue, JS, Vite) | `npx frontend-agent-skills install` for vue3 profile |\n| Project conventions | Create `.agents/project-conventions/SKILL.md` manually |\n| Domain specs | Live in `openspec/specs/` per project |\n\nGit-committed: `.agents/` + `AGENTS.md` + `CLAUDE.md` + `scripts/` + `.github/`\nLocal only (not committed): `.cursor/` `.claude/` `.amp/`\n\n## IDE Integration\n\n### Amp Code (primary — zero config)\n\nAmp reads `.agents/skills/` and `AGENTS.md` **natively** — no sync needed.\n\n**CLI note:** Amp shells often lack global `openspec` / `agent-orchestrator-kit` on PATH (exit 127). Agents must use `npx …` / `npm run …` — see always-apply rule `.agents/rules/cli-via-npm.mdc`.\n\n1. Install the kit → `AGENTS.md` is created automatically.\n2. Amp picks up skills from `.agents/skills/` on session start.\n3. Copy Amp MCP config (on first sync):\n\n```bash\ncp .agents/amp.settings.json.example .amp/settings.json\n```\n\nOr run `./scripts/sync-local-agent-skills.sh` — it creates `.amp/settings.json` automatically.\n\n**Subagents in Amp:** the kit exposes every `.agents/subagents/<name>.md` as an auto-generated `subagent-<name>` skill. The conductor MUST run the wrapper as an isolated subagent with fresh context and MUST NOT execute its body in the main thread. Edit only the source file and re-run `sync` to regenerate wrappers.\n\n4. Use commands directly:\n\n```\n/opsx:explore\n/opsx:propose add-feature-name\n/opsx:review add-feature-name\n/opsx:apply add-feature-name\n/opsx:archive\n/opsx:sync add-feature-name      # agent-driven merge of the change's delta specs into openspec/specs/ without archiving\n```\n\n**Model hints per role** (Amp modes):\n\n| Role | Recommended Amp mode |\n|------|---------------------|\n| explore | `rush` |\n| propose | `smart` or `deep` |\n| review | `smart` |\n| apply (complex) | `smart` or `deep` |\n| apply (simple task) | `rush` |\n\nSwitch modes in Amp CLI: `Ctrl+O` → `mode`.\n\n### Claude Code\n\n1. Run sync: `./scripts/sync-local-agent-skills.sh`\n2. This creates:\n   - `.claude/CLAUDE.md` — project context\n   - `.claude/skills/` — all skills from `.agents/skills/` (excluding Amp `subagent-*` wrappers)\n   - `.claude/agents/` — custom subagents from `.agents/subagents/` (native Claude Code subagents)\n   - `.claude/commands/opsx/` — `/opsx:*` commands from `.agents/commands/`\n3. Skills are auto-loaded by Claude Code from `.claude/skills/`. The `.agents/rules/*.mdc` files are synced only to Cursor (`.cursor/rules/`); Claude Code reaches them through the references in `CLAUDE.md` / `AGENTS.md`.\n4. Invoke `/opsx:*` or the orchestration skill. The conductor delegates using the mandatory phase/signal routing table rather than relying on description-only selection.\n\n**CLAUDE.md tiers used:**\n- Project level: `.claude/CLAUDE.md` (synced from `CLAUDE.md`)\n- Personal (optional): `~/.claude/CLAUDE.md` for preferences\n\n**Claude Code subagent config** (optional, in skill frontmatter):\n\n```yaml\n---\nname: openspec-explore\ncontext: fork\nagent: Explore\nallowed-tools: Read, Bash\n---\n```\n\nYou can add `context: fork` to explore/review skills for isolated subagent sessions.\n\n### Cursor\n\n1. Run sync: `./scripts/sync-local-agent-skills.sh`\n2. Creates:\n   - `.cursor/skills/` — all skills\n   - `.cursor/rules/` — `.mdc` rule files\n   - `.cursor/agents/` — all 12 custom/stage subagents\n   - `.mcp.json` — from `mcp.json.example` (if not present)\n3. Rules are applied automatically per `alwaysApply: true`.\n4. `/opsx:*` sessions use the mandatory conductor routing table to spawn subagents. Add project-specific subagents in `.agents/subagents/`, add an exclusive route, and re-run sync.\n\n**Memory + optional Figma MCP for Cursor** (`.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"memory\": {\n      \"command\": \"node\",\n      \"args\": [\"scripts/memory-mcp-launcher.cjs\"]\n    },\n    \"figma\": {\n      \"command\": \"node\",\n      \"args\": [\"scripts/figma-mcp-launcher.cjs\"]\n    }\n  }\n}\n```\n\nToken lives in `.agents/figma.local.env` — see [Figma token](#figma-token-optional).\n\n## The Pipeline in Detail\n\n### Role 1: Explorer — `/opsx:explore`\n\n**Mode:** read-only. Cannot edit any files.\n**Model:** fast/cheap.\n**Purpose:** Understand the problem. Surface options. Choose a direction.\n\nThe conductor spawns `codebase-explorer` for repository investigation and stays read-only.\n\n**Exit criteria (before starting Architect):**\n- Problem stated in 3–5 sentences\n- 2–3 solution options + recommendation\n- kebab-case change name chosen\n- Non-goals listed\n\n```\n/opsx:explore How should we handle bulk camera export?\n```\n\n---\n\n### Role 2: Architect — `/opsx:propose <name>`\n\n**Mode:** writes `openspec/changes/<name>/` only. Cannot touch `src/`.\n**Model:** strong reasoning.\n**Purpose:** Create all change artifacts: proposal, design, tasks, delta specs.\n\nThe conductor spawns `spec-architect`; it does not write artifacts in the parent session. It is a thin conductor: it does not research the repo itself, passes the decision brief by path, and after the report only runs the exit gate below without re-reading the artifacts.\n\n**Exit gate:**\n```bash\nnpx openspec validate <name> --strict --type change  # must be ✓\nnpx agent-orchestrator-kit gate-check --review <name>  # Tier 1 pre-gate: exit 0 before /opsx:review\n```\n\n```\n/opsx:propose add-bulk-camera-export\n```\n\n---\n\n### Role 3: Spec Reviewer — `/opsx:review <name>`\n\n**Mode:** read-only. No code edits.\n**Model:** medium or strong.\n**Purpose:** Review artifacts. Output **Approve ✓** or **Request Changes ✗**.\n\nReview is **two-tiered**. Tier 1 is deterministic: `npx agent-orchestrator-kit gate-check --review <name>` runs strict OpenSpec validation, the task-contract lint, and structural checks (Non-goals / Acceptance criteria in `proposal.md`, non-empty delta-spec sections); it also warns when the artifacts outgrow the size budget. If Tier 1 fails, the verdict is REQUEST CHANGES without spawning anyone. Only on a Tier 1 pass does the conductor spawn `spec-reviewer` (not `code-reviewer`) for Tier 2 judgment and verify its `review.md` with `gate-check --review-md <name>`. On APPROVE the reviewer also writes `apply-notes.md` (≤ 20 lines of constraints and pitfalls for the implementer).\n\nTier 2 checks (judgment only — no duplication of Tier 1):\n- Consistency proposal ↔ design ↔ tasks\n- No scope creep vs Non-goals\n- No conflicts with existing domain specs\n- Tasks self-sufficient for a blind implementer (Files / Do / Done-when)\n\n```\n/opsx:review add-bulk-camera-export\n```\n\n**Only after explicit APPROVE can apply start.**\n\n---\n\n### Role 4: Implementer — `/opsx:apply <name>`\n\n**Mode:** conductor; routed specialists write `src/` and tests. Only the conductor marks `tasks.md [x]` after a verified `Status: done` report.\n**Model:** strong. Use fast for simple mechanical tasks.\n**Purpose:** Implement tasks. One session = 1–3 tasks (not all 15 at once).\n\n**Exit gate:**\n```bash\nnpm run build   # must pass\nnpm run lint    # must pass\n```\n\n```\n/opsx:apply add-bulk-camera-export\n```\n\n---\n\n### Role 5: Verifier — CI (automatic)\n\n**GitHub (default `--ci github`):** installed at `.github/workflows/agent-verify.yml`:\n\n```yaml\n- run: npx openspec validate --all --strict\n- run: npm run lint --if-present\n- run: npm run build --if-present\n- run: npm test --if-present\n```\n\n**GitLab (`--ci gitlab`):** verify runs through the package manager build lifecycle — no GitHub Actions:\n\n```json\n\"verify:openspec\": \"npx openspec validate --all --strict\",\n\"prebuild\": \"npm run verify:openspec\"\n```\n\nWhen CI or a developer runs `npm run build`, npm executes `prebuild` first. DevOps pipelines that already call `npm run build` get OpenSpec validate with zero config changes.\n\nOptional: include `.gitlab/agent-verify.yml` in `.gitlab-ci.yml` for full lint/build/test verify before DevOps owns the root CI file. See kit `templates/.gitlab-ci.starter.yml.example`.\n\nBlocks merge if any gate fails.\n\nBoth consumer CI templates (`templates/.github/workflows/agent-verify.yml` and `templates/.gitlab/agent-verify.yml`, installed as `agent-verify.yml`) also run `npx agent-orchestrator-kit gate-check` — see [Deterministic gates](#deterministic-gates-status--gate-check) below. It never fails the pipeline for projects without `.agents/orchestrator.yaml`. (The kit's own repository CI runs only `openspec validate` + `npm test`.)\n\n#### AI Spec Verifier (GitLab or GitHub, opt-in)\n\n```bash\nnpx agent-orchestrator-kit init --ci gitlab --spec-verify\nnpx agent-orchestrator-kit init --ci github --spec-verify\n```\n\nInstalls an AI verification layer on top of the deterministic gates: on every merge/pull request that changes `src/`, an Amp agent reads `openspec/specs/`, checks the changed code against every relevant requirement, posts a **PASS / BLOCKED** comment to the MR/PR, and **fails the pipeline on BLOCKED** — specs become an enforceable merge contract, not just documentation.\n\nInstalled files (GitLab):\n\n| File | Purpose |\n|------|---------|\n| `.gitlab/spec-verify.yml` | CI fragment — hidden `.spec-verify-base` + blocking `spec-verify` job (MR + `src/**/*` only) |\n| `scripts/verify-specs.sh` | Collects changed files + specs, builds prompt (project context from `openspec/config.yaml`), calls `amp -x`, writes `artifacts/verdict.json` |\n| `scripts/post-mr-verdict.sh` | Posts the verdict as an MR comment via GitLab API |\n\nInstalled files (GitHub):\n\n| File | Purpose |\n|------|---------|\n| `.github/workflows/spec-verify.yml` | Workflow triggered on `pull_request` for `src/**` — same verdict evaluation, `permissions: pull-requests: write` |\n| `scripts/verify-specs.sh` | Same script as GitLab — stack-agnostic, reused as-is |\n| `scripts/post-pr-verdict-github.sh` | Posts the verdict as a PR comment via `gh pr comment` |\n\nThe flag also adds `spec-verify-blocking` to `roles.verifier.gates` in `.agents/orchestrator.yaml`.\n\nSetup after install (GitLab):\n\n1. Include the fragment from `.gitlab-ci.yml`:\n\n```yaml\ninclude:\n  - local: '.gitlab/spec-verify.yml'\n```\n\n2. Add CI/CD variables (Settings → CI/CD → Variables, masked): `AMP_API_KEY`, `GITLAB_VERIFIER_TOKEN` (project access token with `api` scope).\n\nSetup after install (GitHub): the workflow runs automatically on `pull_request` — just add the repo secret `AMP_API_KEY` (Settings → Secrets and variables → Actions). `GITHUB_TOKEN` is provided by Actions automatically.\n\nVerdict schema (`artifacts/verdict.json`): `pass`, `score` (0–100), `summary`, `findings[]` with `severity` (`error` fails the job), `spec`, `requirement`, `message`, `file`. The script degrades gracefully — no `src/` changes, no specs, missing `amp` CLI, or missing `AMP_API_KEY` produce a skipped passing verdict and never block the pipeline. Secrets are never logged; `.env`/key/token files are excluded from prompts.\n\n**Warning-only rollout (Phase 1):** uncomment `allow_failure: true` (GitLab) or `continue-on-error: true` (GitHub) to keep the pipeline green while the team builds trust in verdicts, then remove it to enforce blocking (Phase 2).\n\n`update` refreshes the spec-verify files only in projects that already installed them — the feature stays opt-in.\n\n---\n\n### Deterministic gates: `status` / `gate-check`\n\nOrchestration hard rules (review approval, one active change) used to rely entirely on the agent remembering to check them in chat. Two CLI commands make them checkable and CI-enforceable:\n\n```bash\nnpx agent-orchestrator-kit status\n```\n\nPrints an `archive_after_merge: <true|false>` policy line under the title (when `.agents/orchestrator.yaml` exists), then every active OpenSpec change with task progress (`N/M tasks`), review verdict (`APPROVE` / `REQUEST CHANGES` / `none`), design brief (`brief: yes/no`), a `ready to archive` flag once all tasks are `[x]`, and an **MCP health** section (launcher / env / live config — never prints token values). VCS tools that do not match `git remote origin` show as `skipped (no origin match)`.\n\n```bash\nnpx agent-orchestrator-kit gate-check [change-name] [--src-glob src/] [--base HEAD~1] [--staged]\n```\n\nFails (non-zero exit) when `pipeline.require_spec_review: true`, the diff against `--base` (or **staged** files with `--staged`) touches `--src-glob`, and the active change has no `review.md` with `Verdict: APPROVE`. When `pipeline.require_design_brief: true` and `src/` changed, it also requires `design-brief.md` (or a `Design: none` line in `proposal.md` for non-UI changes). It degrades gracefully to exit 0 (with a message, not silently) when: `.agents/orchestrator.yaml` is missing, neither review nor design brief is required, the diff can't be computed (e.g. shallow clone), or nothing under `--src-glob` changed. It also warns (never fails) when active changes exceed `pipeline.max_active_changes`. Both consumer `agent-verify.yml` templates (GitHub and GitLab, installed by `init --ci`) call `gate-check` automatically. Pre-commit uses `--staged` so it checks the index, not `HEAD~1`.\n\n```bash\nnpx agent-orchestrator-kit gate-check --tasks <change-name>\n```\n\nLints the task contract in `tasks.md`: every task needs `Files:` / `Do:` / `Done-when:`, no vague phrasing (`as needed`, `if necessary`, …), and every `Files:` path must exist unless prefixed `new file:`. Behavior follows `pipeline.task_contract` in `orchestrator.yaml`: `warn` (default) exits 0 with warnings, `strict` exits 1 on violations, `off` skips the lint.\n\n```bash\nnpx agent-orchestrator-kit gate-check --review <change-name> [--json]\n```\n\nDeterministic Tier 1 of the review phase: strict OpenSpec validation, the task-contract lint, `Non-goals` / `Acceptance criteria` sections in `proposal.md`, non-empty ADDED/MODIFIED/REMOVED sections in delta specs, and the same heading checks `archive --sync` enforces (a MODIFIED/REMOVED title must exist in the main spec, an ADDED title must not). Human-readable stdout, or `--json` for a `{pass, errors[]}` report.\n\nIt also measures `proposal.md`, `design.md`, `tasks.md` and the delta specs in bytes and reports `artifact budget: …` when `tasks.md` is over 60 000 B or their total is over 150 000 B, with the advice to split the change into slices. `pipeline.artifact_budget` sets the mode: `warn` (default) prints a warning and keeps the exit code, `strict` makes it an error (exit 1), `off` skips the measurement.\n\n```bash\nnpx agent-orchestrator-kit gate-check --review-md <change-name> [--json]\n```\n\nChecks `review.md` against the `/opsx:review` schema after Tier 2: exactly one `Verdict:` line (APPROVE or REQUEST CHANGES), a `Previous findings` heading, on REQUEST CHANGES non-empty `Checklist`, `Findings` (Blocker / Major / Minor) and `Required Before Apply`, on APPROVE an `apply-notes.md` of at most 20 lines. A Tier 1 record (`**Source:** gate-check`, no Checklist) only has to be REQUEST CHANGES. Exit 1 with the error list, or `--json` for a `{pass, errors[]}` report. `/opsx:review` runs it after the `spec-reviewer` report instead of checking the headings by hand.\n\n### Pre-commit review gate (optional)\n\n`gate-check` already exists; it is **not** wired to `git commit` unless you opt in. The kit never writes `.git/hooks/` directly.\n\n```bash\nnpx agent-orchestrator-kit hooks-setup\n# or: npx agent-orchestrator-kit init --hooks\n```\n\n- If `.husky/` exists, a marked line `sh scripts/pre-commit-gate-check.sh` is appended to `.husky/pre-commit` (idempotent; existing content is kept). `core.hooksPath` is not changed.\n- Otherwise the kit writes committed `.githooks/pre-commit` and runs `git config core.hooksPath .githooks`. If `core.hooksPath` is already set to something else, the command refuses and prints a manual line to add.\n- Lefthook: add `sh scripts/pre-commit-gate-check.sh` to your pre-commit job yourself (no auto-write).\n- `init` without `--hooks` still installs `scripts/pre-commit-gate-check.sh` as a managed file, unconnected.\n- Disable: remove the marked line from `.husky/pre-commit`, or `git config --unset core.hooksPath`.\n- MVP (`require_spec_review: false`): the hook is a no-op (exit 0).\n- Keep `agent-orchestrator-kit` in the project's **devDependencies** so `npx agent-orchestrator-kit` on every commit does not cold-fetch from the registry.\n\nRun `hooks-setup` on each machine (`git config` is local), same as `figma-setup`.\n\n### Optional MCP: GitHub, GitLab, browser\n\nSame pattern as Figma: stdio launcher + gitignored env + committed `.example`. Tokens never go in chat or committed MCP JSON.\n\n```bash\nnpx agent-orchestrator-kit mcp-setup\n```\n\nDetection uses `git remote get-url origin` (https and ssh). `--ci` is ignored.\n\n| Origin hostname | Installed VCS MCP |\n|-----------------|-------------------|\n| `github.com` | GitHub only |\n| `gitlab.com` or hostname contains `gitlab` (self-hosted) | GitLab only; `GITLAB_API_URL=https://<hostname>/api/v4` |\n| missing / unrecognized | no VCS MCP (`status` shows skipped) |\n\nBrowser MCP (`@playwright/mcp`) is always added unless you pass `--no-browser`. Override detection with `--vcs github` or `--vcs gitlab`.\n\n```bash\nnpx agent-orchestrator-kit mcp-setup --vcs gitlab --no-browser\n```\n\nThen put tokens **only** in the gitignored files (never in chat):\n\n| Path | Git |\n|------|-----|\n| `.agents/github.local.env` | ignored |\n| `.agents/gitlab.local.env` | ignored |\n| `.agents/*.local.env.example` | committed |\n| `scripts/*-mcp-launcher.cjs` | committed |\n\nCursor, Claude Code, and Amp all spawn the same launchers. Committed examples list all five servers (`memory`, `figma`, `github`, `gitlab`, `browser`); live `.mcp.json` / `.amp/settings.json` receive only the detected VCS plus browser.\n\n`npx agent-orchestrator-kit status` prints MCP health (`ok` / `not configured` / `skipped`) without token values.\n\n---\n\n### Design intake: `/opsx:design`\n\nOptional phase between explore and propose (or before apply) that captures design into a durable artifact so implement sessions do not depend on live Figma MCP:\n\n```\n/opsx:design add-login-form\n```\n\nWrites only:\n- `openspec/changes/<name>/design-brief.md` — Source, Structure, Tokens, Reference images, Constraints, Confidence notes\n- `openspec/changes/<name>/assets/` — reference PNGs\n\nSource fallback: Figma MCP (one pass) → exported images → screenshots → photos. Raster sources must mark inferred values with confidence notes.\n\n**Opt-in gate** (default off — existing projects unchanged):\n\n```yaml\npipeline:\n  require_design_brief: true   # gate-check fails without brief when src/ changed\n```\n\nNon-UI changes: add this line to `proposal.md`:\n\n```\nDesign: none\n```\n\n**Existing projects after `update`:** the command file `opsx-design.md` is installed automatically. Your `orchestrator.yaml` is never overwritten — add the role and flag manually if you want the gate:\n\n```yaml\npipeline:\n  require_design_brief: false   # set true to enforce\nroles:\n  design_intake:\n    command: /opsx:design\n    mode: brief-only\n    model_hint: strong\n```\n\n---\n\n### Archive — terminal first, `/opsx:archive` as fallback\n\nAfter the PR is merged and CI is green, archive from a terminal — no chat needed:\n\n```bash\nnpx agent-orchestrator-kit archive add-bulk-camera-export --sync\n```\n\nAfter a green apply (the Implementer closes, every task in `tasks.md` is `[x]`, `## Blocked` is `none`), `handoff <name>` prints exactly this line instead of a next-session prompt; run it once the PR is merged. `/opsx:archive <name>` stays as a fallback for when a terminal or CI was not available.\n\nArchive is a **deterministic CLI**, not an agent workflow:\n\n```bash\nnpx agent-orchestrator-kit archive <name> [--sync | --no-sync --force] [--if-ready] [--collect]\n```\n\nIt first runs **Gate 0** and refuses a folder that already looks archived (`archivedAt` set in the change `metrics.json`, or `Next command: none` in `handoff.md`; for a re-opened copy clear the marker and re-run), then checks the gates (APPROVE in `review.md` when required, all tasks `[x]`, target folder free), merges delta specs into `openspec/specs/` (`--sync`: ADDED append, MODIFIED replace, REMOVED delete), moves the change to `openspec/changes/archive/YYYY-MM-DD-<name>`, and runs `npx openspec validate --all --strict` with a full rollback on failure (main specs restored, new spec files deleted, move reverted). With delta specs present you must decide: `--sync` merges, `--no-sync --force` archives without merging, and no flag refuses with exit 1. It finishes by writing the final `handoff.md` (`next_command: none`), updating memory, appending an Archiver session, and printing the same human metrics summary as `metrics <name>`. Archive collects the locked client (Cursor hook / Amp threads / Claude JSONL) in `[pending.startedAt, now]` plus leftover of the previous session — the same leftover-then-collect flow as persist. `--collect` still runs every adapter. Unique `## Metrics` in the change `handoff.md` still counts as Archiver self-report; leftover apply numbers that match the previous session are ignored. `/opsx:archive` is the chat fallback: a thin wrapper that calls this CLI, shows its output, and on a refusal prints it and stops; the `spec-archiver` subagent remains only as a fallback when the CLI is unavailable.\n\n**`--if-ready`** is the CI mode of the same command. It prints one `skip: <reason>` line, exits 0 and changes nothing when `pipeline.archive_after_merge` is `false`, the change already looks archived (Gate 0), or it is not ready — the same blockers `status` prints (`tasks incomplete`, `no review.md`, …; a missing `tasks.md` counts as not ready). Otherwise it archives like a normal run, and real failures (an existing target folder, a delta-spec sync conflict, a failed validation) still exit 1. Without `--if-ready` a manual archive ignores `archive_after_merge`.\n\n#### CI archive (opt-in)\n\nA terminal stays the default. The CI templates (`agent-verify.yml`: GitHub job `archive`, GitLab job `agent-archive`) also contain an archive job that is off until you opt in:\n\n1. Set the repository variable (GitLab: CI/CD variable) `AOK_ARCHIVE_ON_MERGE=true`. Without it the job is skipped.\n2. Add the secret (GitLab: masked CI/CD variable) `AOK_ARCHIVE_TOKEN` — a token whose user may push to the protected default branch (a branch-protection bypass). On GitHub the job falls back to the workflow token, which can push only to an unprotected branch.\n3. Keep `pipeline.archive_after_merge: true` in `.agents/orchestrator.yaml` (the `mvp` profile sets `false`).\n\nOn a push to the default branch the job waits for `verify`, runs `archive <name> --sync --if-ready` for every `openspec/changes/<name>/`, and pushes one `chore(openspec): archive merged change [skip ci]` commit with the moved change and its finalized `metrics.json`; `[skip ci]` keeps that push from starting another run.\n\nKnown caveats: a Cursor `sessionEnd` hook can append leftover usage to a *local* `metrics.json` after the last persist, which then conflicts with the CI commit (keep the archived copy when you resolve it); two merges in quick succession can make the first push fail as non-fast-forward (the next push to the default branch archives again, or archive from a terminal); the job runs the published `npx agent-orchestrator-kit`, so it needs a kit version that has `--if-ready`.\n\n## Configuration\n\nEdit `.agents/orchestrator.yaml` after init:\n\n```yaml\nproject:\n  name: \"My Project\"\n  agent_language: uk      # response language for agents\n\npipeline:\n  require_spec_review: true\n  require_design_brief: false   # opt-in: require design-brief.md when src/ changed\n  max_active_changes: 1\n  archive_after_merge: true     # policy flag: `status` shows it; `archive --if-ready` and the opt-in CI job honour it; a manual archive ignores it\n  task_contract: warn           # tasks.md lint mode for gate-check: warn | strict | off\n  artifact_budget: warn         # change size budget for gate-check --review: warn | strict | off (a missing key means warn)\n  src_glob: \"src/\"              # paths gate-check treats as product code (default for --src-glob)\n\nverifier:\n  lint_command: \"npm run lint\"\n  build_command: \"npm run build\"\n  test_command: \"npm test\"   # optional\n```\n\n## Update\n\nWhen a new version of the kit is released:\n\n```bash\nnpx agent-orchestrator-kit update\n./scripts/sync-local-agent-skills.sh\n```\n\n`update` only touches kit-managed files (commands, rules, skills). It never overwrites:\n- `orchestrator.yaml`\n- `openspec/config.yaml`\n- `openspec/specs/`\n- `openspec/changes/`\n- Any project-conventions skills\n\n**Existing `openspec/config.yaml`:** `update` never touches it, and `init` skips `openspec/config.yaml.example` when `openspec/config.yaml` already exists (for example after `npx openspec init`). Add the proposal rule by hand, under `rules.proposal`, so `openspec instructions proposal` tells the architect about the Tier 1 headings:\n\n```yaml\nrules:\n  proposal:\n    - \"Always include the exact level-2 headings '## Non-goals' and '## Acceptance criteria' (gate-check --review Tier 1 rejects the proposal without them).\"\n```\n\nDouble-quote every rule: an unquoted item that contains `: ` makes OpenSpec drop the whole list for that artifact, and an unquoted ` #` silently cuts the rule short (YAML reads the rest as a comment). A fresh `init --profile node` or `init --profile generic` installs `openspec/config.yaml.example` with these rules from `templates/openspec-config.yaml.example`; `init --force` overwrites an existing `openspec/config.yaml`.\n\n### Upgrading from older versions\n\nNo re-`init` is needed — `update` + sync is the whole upgrade path:\n\n```bash\nnpx agent-orchestrator-kit@latest update\nnpx agent-orchestrator-kit@latest sync   # or: ./scripts/sync-local-agent-skills.sh\nnpx agent-orchestrator-kit@latest status\n```\n\n- CI files are refreshed only where they already exist: `update` rewrites `.github/workflows/agent-verify.yml` / `.gitlab/agent-verify.yml` and the opt-in `spec-verify.yml` + verifier scripts when the project has them, and never creates a workflow for a provider you did not choose.\n- Adding the AI Spec Verifier to a project that never had it is a separate opt-in — run it once, then add the `AMP_API_KEY` secret:\n  ```bash\n  npx agent-orchestrator-kit@latest init --ci github --spec-verify   # or --ci gitlab\n  ```\n- `update` never edits your CI root file. If `gate-check` does not seem to run on GitLab, check that `.gitlab-ci.yml` still `include`s `.gitlab/agent-verify.yml` (GitHub Actions picks up `.github/workflows/*.yml` automatically).\n\n## Profiles\n\n| Profile | Stack | Extra (separate install) |\n|---------|-------|--------------------------|\n| `generic` | Any | Orchestration + OpenSpec skills only. `init` still writes the detected JS package-manager commands (`npm`/`yarn`/`pnpm` `lint` / `build` / `test`) into `verifier.*` of `orchestrator.yaml` — non-Node projects edit those three commands after init |\n| `vue3` | Vue 3 + Vite + JS | + `npx frontend-agent-skills install` |\n| `node` | Node.js | + `npx frontend-agent-skills install --category javascript` |\n| `mvp` | Vue 3 demo/spike | + frontend-agent-skills; use `/opsx:quick`, no review gate |\n\nFor `vue3`, after kit init also run:\n\n```bash\n# Amp (primary — installs directly to .agents/skills/)\nnpx frontend-agent-skills install --agent amp --yes\n\n# Cursor + Claude Code users — sync local IDE dirs\n./scripts/sync-local-agent-skills.sh\n```\n\nOr install for all IDEs at once:\n\n```bash\nnpx frontend-agent-skills install --agent all --yes\n```\n\n> **Migrating from `vue-cursor-skills`?** Renamed to `frontend-agent-skills` v2 — same package, old CLI alias still works.\n\n## Figma token (optional)\n\nPersonal Access Token for design intake (`/opsx:design`) and the optional Framelink `figma-developer-mcp` server. **Never paste the token into AI chat.**\n\n### Setup (each developer, once)\n\n```bash\nnpx agent-orchestrator-kit figma-setup\n# open .agents/figma.local.env in the IDE and set:\n# FIGMA_ACCESS_TOKEN=figd_...\nnpx agent-orchestrator-kit figma-status\n```\n\nThen restart Cursor / Claude Code / Amp.\n\n| Path | Purpose | Git |\n|------|---------|-----|\n| `.agents/figma.local.env` | Your token (`FIGMA_ACCESS_TOKEN`) | **ignored** |\n| `.agents/figma.local.env.example` | Template | committed |\n| `scripts/figma-mcp-launcher.cjs` | Starts MCP with token from the env file | committed |\n| `.mcp.json` → `figma` | Points at the launcher (no secret inline) | committed OK |\n\nCreate a token: Figma → Settings → Security → Personal access tokens (file content read as needed).\n\n### CLI\n\n```bash\nnpx agent-orchestrator-kit figma-setup\nnpx agent-orchestrator-kit figma-status\nnpx agent-orchestrator-kit figma-fetch --url \"https://www.figma.com/design/FILE_KEY/Name?node-id=1-2\" \\\n  --out openspec/changes/<name>/assets/figma-nodes.json\n# large frames: limit tree depth\nnpx agent-orchestrator-kit figma-fetch --file FILE_KEY --nodes 1:2 --depth 2 --out figma-nodes.json\n```\n\n`figma-fetch` uses the Figma REST API (`X-Figma-Token`) and writes JSON for design-brief capture. Live Figma is for design-intake only — apply uses `design-brief.md`.\n\n### Upgrade existing projects\n\n```bash\nnpx agent-orchestrator-kit@latest update\nnpx agent-orchestrator-kit figma-setup\n./scripts/sync-local-agent-skills.sh\n```\n\n## Memory MCP — Shared State Between Sessions\n\nEach role starts a fresh session. OpenSpec artifacts remain the source of truth; Memory MCP and `openspec/changes/<name>/handoff.md` are the phase index used to resume without re-explanation.\n\n**Standard entities to save:**\n\n```\nChange:add-bulk-export     status: spec-approved, tasks: 0/7, last_role: reviewer, review: APPROVE\nDecision:export-format     chosen: xlsx, reason: matches existing reports\nHandoff:add-bulk-export    next_role: implementer, next_command: /opsx:apply add-bulk-export,\n                           session_count: 2, summary: ..., blocked: none\n```\n\nSession boundaries are **parent-driven** (no routine subagent): every `/opsx:*` session restores via `npx agent-orchestrator-kit handoff --restore` (the CLI briefing already reads memory.json and `handoff.md`), falling back to reading `handoff.md` directly if the CLI fails. At exit the parent itself writes `handoff.md`, runs `npx agent-orchestrator-kit handoff <name>` (upserts `.cursor/memory.json` with an absolute path), and pastes the CLI stdout prompt. The `session-handoff` subagent is spawned only when the CLI path fails; Memory MCP is an optional mirror. The prompt is self-contained — Amp often skips Memory MCP, so the next thread must be able to work from the pasted text alone. Never configure Memory with a relative `MEMORY_FILE_PATH`; use `scripts/memory-mcp-launcher.cjs` (`npx agent-orchestrator-kit memory-setup`). The next phase always starts in a new chat. The canonical Session Start / Exit protocol lives in one place — `.agents/rules/session-handoff.mdc` — and the `/opsx:*` commands reference it instead of duplicating it.\n\n### Change decisions (`decisions.md`)\n\nSession decisions accumulate in git-tracked, append-only `openspec/changes/<name>/decisions.md`. That file is the canon visible in a PR/MR; Memory `Decision:*` is a **file → Memory** mirror only.\n\n```bash\nnpx agent-orchestrator-kit handoff add-bulk-export\n# appends dated bullets from handoff.md ## Decisions (skips duplicates; same topic + new text → new row)\nnpx agent-orchestrator-kit handoff add-bulk-export --restore\n# prints decisions from the git file (or `decisions: none` if the file does not exist)\n```\n\n`Decisions: none` does not create the file. Re-running persist with the same handoff does not duplicate rows. A later revision of the same topic is a new line; the old line stays. `update` does not migrate historical Memory entities into the file.\n\n### Cloud agent handoff (Phase 3)\n\nEvery persist writes a `## Runtime` section to `openspec/changes/<name>/handoff.md`:\n\n```\n## Runtime\n- runtime: local|cloud\n- agent_id: <id|none>\n```\n\nDetection is a fixed chain (no TTY / `CURSOR_AGENT` magic): `--runtime` → env `AOK_RUNTIME` → `CLOUD_ENV_MARKERS` (starts with `CURSOR_BACKGROUND_AGENT`) → existing `## Runtime` in the file → `local`. `agent_id` uses `--agent-id` → `AOK_AGENT_ID` → existing value → `none`. Invalid `--runtime` (not `local` or `cloud`) exits non-zero. Legacy files without Runtime stay valid; the next persist appends the section.\n\nConfigure a cloud agent once:\n\n```\nAOK_RUNTIME=cloud\nAOK_AGENT_ID=<vm-or-run-id>\n```\n\n`--cloud-check` is a **separate** branch of `handoff`, never part of persist (persist has just rewritten `handoff.md`, so the tree is always dirty at that point). It verifies (1) `git status --porcelain -- openspec/changes/<name>/` is empty and (2) the current branch has an upstream with no unpushed commits. Verdict: `cloud` + any failure = non-zero; `local` + the same failure = warning + exit 0; clean = exit 0. The CLI never runs `git commit` or `git push`.\n\nCloud Session Exit order:\n\n```bash\nnpx agent-orchestrator-kit handoff <name> --runtime cloud\ngit add openspec/changes/<name>/\ngit commit\ngit push\nnpx agent-orchestrator-kit handoff <name> --cloud-check   # require exit 0\n```\n\nPersist with `runtime: cloud` prints those four steps on stderr; stdout stays the pure `/opsx:` next-thread prompt. Local persist is unchanged.\n\n### Change metrics\n\nEvery change accumulates git-tracked `openspec/changes/<name>/metrics.json` — the data source for planning the next feature: how long each phase took, how many sessions it needed, what it cost.\n\nSchema v2 stores compact `sourceIds`, `sourceTotals`, and `byModel` per session instead of `sessions[].sources`. This is **BREAKING** for readers of the old event arrays. v1 files are normalized in memory without rewriting; run `npx agent-orchestrator-kit metrics <name> --migrate` for a schema-only rewrite that preserves existing numeric fields and aggregates.\n\n- **`## Metrics` self-report** — Session Exit fills `handoff.md` with `platform`, `model`, `input_tokens`, `output_tokens`, `cost_usd`, `amp_credits`, `spend_source` (`unknown` when missing). Persist reads that section; `metrics.json` is the source of truth for what landed. CLI flags do not rewrite the section.\n- **`session.model`** — source product id wins when any collected source has a model; `--model` / `## Metrics: model` / `AOK_MODEL` apply only when sources have no model. Never a Closed role.\n- **Session start** — `handoff --restore` writes a `pending` marker (`startedAt`, expected role).\n- **Session end** — `handoff <name>` closes the pending session. Its collect lower bound is `--started-at` or `pending.startedAt` minus 120 seconds; without either it is the previous `endedAt`, or `createdAt` for the first session, with no open-ended scan. Amp usage totals and fresh Cost are authoritative; Claude JSONL is deduplicated by `message.id`, includes subagents, and accepts cwd descendants. Claude uses a versioned Anthropic list-price estimate with cache split; Amp without Cost uses the same model table or the $3/$15 fallback. Estimates never enter billed `costUsd`.\n- **Archive** — successful `archive <name>` always creates or finalizes `metrics.json`, sets `archivedAt`, appends an Archiver session, collects the locked client (Cursor hook / Amp export+usage / Claude JSONL) in `[pending.startedAt, now]` plus leftover of the previous session, and prints the same human summary as `metrics <name>`. `--collect` still runs all three adapters. Leftover apply `## Metrics` that repeats the previous session is ignored so those tokens are not counted twice.\n- **`sessionEnd` leftover** — `scripts/cursor-spend-collect.cjs` also reads the newest `openspec/changes/archive/*-<name>/metrics.json` when the active change folder is gone, so a late hook after archive still attaches. `stop` / `afterAgentResponse` run the same leftover after a successful jsonl append. When `last.threadId` is non-empty, leftover keeps only rows whose `conversationId` matches that id (empty/`null` threadId stays time-only). In a multi-root window leftover walks every candidate that has `openspec/changes`, reading that root’s jsonl. Aggregates write `costUsdEstimated` with 4 decimal places. Each `phases.<phase>` stores `startedAt` / `endedAt` / `leadTimeMs` from that phase’s sessions; `durationMs` stays the work-time sum and does not clone `totals.leadTimeMs`.\n- **Leftover without `--collect`** — Scopes to `last.platform` and Amp thread identity from `threadId` or `sourceIds`. Sessions without a thread id are capped at `endedAt + 120s`; identified sessions may continue to the next pending boundary. Fresh Amp usage totals, Models, and Cost replace cached values.\n- **Cursor `conversationId`** — restore writes `CURSOR_CONVERSATION_ID` into `pending.threadId`; Cursor collect and sessionEnd leftover skip rows whose `conversationId` does not match when a filter id is present (`last.threadId` on leftover).\n- **Canonical role** — `session.role` and `pending.role` store the first known token (`Explorer`, `Architect`, `Spec Reviewer`, `Implementer`, `Archiver`, `Design Intake`); Closed role in `handoff.md` MAY keep a sentence after `—`.\n- **Platform** — `--platform` → `## Metrics: platform` → `AOK_PLATFORM` → **pending client from `--restore`** → host env (Amp / Cursor / Claude Code) → collected sources (`cursor|claude|amp` only). Invalid `--platform` fails before persist/move.\n- **Locked client** — `--restore` records `pending.platform` and Amp `pending.threadId` before phase work. Persist follows that client’s flow even if persist runs in another shell (no `AMP_*` / `CURSOR_*`). Amp: `amp threads export` plus `amp threads usage --details` (`AOK_AMP_BIN`) and local `threads/*.json`. Export supplies `model` / tokens / `agentMode`; usage supplies billed `$`. If Amp runs tools over a pipe (`/dev/null`), thread id comes from `amp threads list`, not stale `session.json` `lastThreadId`. When env and Amp parent do not win, restore locks a fresh `session.json` `lastThreadId` as `amp-session-last`. Cursor: spend hook file. Claude: `~/.claude/projects`. `--collect` still runs all three adapters.\n- **Cursor spend hook (optional)** — Cursor never writes token usage to disk, so the kit can install `scripts/cursor-spend-hook.cjs` plus `.cursor/hooks.json` entries (`stop` / `subagentStop` / `afterAgentResponse`) in `init` / `update` / `sync` / `mcp-setup`: the hook appends each turn's tokens to gitignored `.agents/spend/cursor-usage.jsonl`. After a successful `stop` / `afterAgentResponse` append the hook runs leftover (fail-open, no stdout). Hook and collect resolve the consumer in a multi-root window (not the first cwd with `.agents` or `openspec`). Persist auto-reads that file when the locked client is Cursor. Persist and restore do not self-heal the hook. `sessionEnd` still runs `scripts/cursor-spend-collect.cjs`. Restart Cursor once after the first install. `status` shows a `Spend capture` section. Claude JSONL remains a fallback. Amp web/CLI spend is taken from `amp threads export` (tokens, model, `agentMode`) and `amp threads usage` (billed USD).\n\nAggregates are recomputed on every write: per-phase totals (`startedAt`, `endedAt`, `leadTimeMs` from that phase’s sessions, `durationMs` = sum of session work time — not `totals.leadTimeMs` and not `endedAt − startedAt`, tokens, `costUsd`, `costUsdEstimated`, `costUsdTotal` to 4 decimals, `sessions`, `roles`, `models`) plus overall `totals` (`sessions`, `cloudSessions`, `durationMs` = sum of session work time, `leadTimeMs` = wall clock from first session start to last session end), `spend` (USD only), and separate **by platform** / **by model** tables. Numbers are null-honest: a metric nobody reported stays `null`, never a fake `0`. No single total that adds Amp credits to USD. `costUsdTotal` is the one USD figure per change, phase, platform, model, and session: each session contributes its billed `costUsd` when present, otherwise its `costUsdEstimated`, so a change that ran on Amp (billed) plus Cursor and Claude (estimated) sums all three platforms instead of showing only the billed part. Amp credits never enter it. The human `cost:` line prints it as `$21.08 ($14.48 billed + ~$6.60 est.)`.\n\nFill `## Metrics` in `handoff.md` **before** persist (unknown is fine; do not invent `0`):\n\n```markdown\n## Metrics\n- platform: cursor\n- model: cursor-grok-4.6\n- input_tokens: 128000\n- output_tokens: 9400\n- cost_usd: unknown\n- amp_credits: unknown\n- spend_source: self-report\n```\n\n```bash\nnpx agent-orchestrator-kit handoff add-thing\nnpx agent-orchestrator-kit handoff add-thing --collect   # optional: Claude JSONL / Amp threads / Cursor hook\nnpx agent-orchestrator-kit metrics add-thing             # human summary: phases, tokens, cost, roles / models\nnpx agent-orchestrator-kit metrics add-thing --json      # raw metrics.json (works for archived changes too)\nnpx agent-orchestrator-kit metrics add-thing --summary-json # compact dashboard contract\nnpx agent-orchestrator-kit metrics add-thing --migrate   # rewrite v1 → v2 without numeric recompute\nnpx agent-orchestrator-kit archive add-thing --sync      # finalize + the same tables as metrics\n```\n\n#### For dashboards\n\nUse only `phases.<phase>.startedAt`, `endedAt`, and `durationMs` for phase boundaries and duration. Use `totals.leadTimeMs` only for the whole change. Git log MUST NOT be used for phase boundaries; the kit does not provide per-phase commit counts. `metrics <name> --summary-json` returns only aggregate `totals`, `phases`, and spend maps, without sessions or commits. For the headline cost use `spend.costUsdTotal` (and `phases.<phase>.costUsdTotal`, `spendByPlatform.<platform>.costUsdTotal`, `spendByModel[].costUsdTotal`): `costUsd` alone is only the billed part and `costUsdEstimated` alone is only the estimated part, so picking one of them drops every platform that reported the other.\n\nRecording is on by default and never a persist/archive/`gate-check` gate; opt out per persist with `--no-metrics`. Persist and archive collect the locked client without `--collect`; `--collect` runs every adapter. Flags (`--model`, `--platform`, `--input-tokens`, …) override session totals in `metrics.json` and do not rewrite the `## Metrics` section.\n\n### Skill inventory\n\n`.agents/orchestrator.yaml` carries a machine-readable `skills:` section (`kit` / `stack` / `external`) instead of hardcoded skill names in the CLI:\n\n```yaml\nskills:\n  kit:\n    - agent-orchestration\n    - openspec-howto\n    # ... remaining kit skills\n  stack: []                 # vue3: vue-core, vue-pinia, vue-axios, vue-router\n  external: \"\"              # vue3/node: frontend-agent-skills\n```\n\n`npx agent-orchestrator-kit status` prints **Skill health** after MCP health (`ok` / `missing` / `stale`) for kit + stack skills and Amp `subagent-*` wrappers. The section is warn-only: missing or stale skills never change the exit code. Repair with the existing commands — `sync` (stale IDE copies), `update` (missing kit files), or a manual stack install:\n\n```bash\nnpx frontend-agent-skills install --agent all --yes\n```\n\nThe CLI never auto-installs external skill packages. `.agents/orchestrator.yaml` is outside kit-managed paths, so `update` does **not** refresh `skills.kit` — after a kit skill is added or removed, edit that list by hand (or re-init with `--force`).\n\n## Amp Code — Deep Integration Notes\n\nAmp is the **primary target** of this kit. It reads `.agents/skills/` and `AGENTS.md` without any sync step — your team commits `.agents/` and everyone gets the same orchestration behavior automatically.\n\n**Amp-specific features used:**\n\n| Feature | How the kit uses it |\n|---------|-------------------|\n| `AGENTS.md` at the repo root | Roles, hard rules, and routing pointers (`.agents/rules/`) read on every session |\n| `.agents/skills/` | All orchestration + domain skills |\n| `.amp/settings.json` (`amp.mcpServers`) | Memory MCP via `scripts/memory-mcp-launcher.cjs`; seeded from `.agents/amp.settings.json.example` by `init` / `sync` |\n| Subagents | Conductor routing + isolated `subagent-*` wrappers |\n| Amp modes (rush/smart/deep) | Per-role model hints in AGENTS.md |\n\n**Amp generated wrapper** (`.agents/skills/subagent-codebase-explorer/SKILL.md`):\n\n```yaml\n---\nname: subagent-codebase-explorer\ndescription: Read-only repository research specialist...\n---\n\nCRITICAL (Amp / Cursor / Claude): Parent MUST spawn this skill as an isolated subagent with fresh context.\nDo not execute it in the main thread. If spawn is unavailable, STOP and report blocked.\n```\n\nThe conductor invokes the wrapper in isolation and consumes only its structured report.\n\n**Team workflow with Amp:**\n\n1. Commit `.agents/` to git.\n2. Team members clone — skills available immediately.\n3. No `sync-local-agent-skills.sh` needed for Amp users.\n4. Cursor/Claude Code users run sync once after clone.\n\n## CLI Reference\n\n```bash\nnpx agent-orchestrator-kit init [options]\n  --profile <name>   Stack profile: generic | vue3 | node | mvp\n  --lang <code>      Agent language: en | uk | ...\n  --name <name>      Project name (default: directory name)\n  --ci <provider>    CI provider: gitlab | github | none (default: github)\n  --spec-verify      Install AI Spec Verifier blocking gate (GitLab or GitHub)\n  --hooks            Opt-in: install pre-commit gate-check hook (husky-first)\n  --force            Overwrite existing files\n\nnpx agent-orchestrator-kit update\n  Updates kit-managed files, preserves project overlay\n\nnpx agent-orchestrator-kit sync [options]\n  --target <ide>     cursor | claude | amp | all (default: all)\n  Copies .agents/ to local IDE directories, removing skills/rules no longer\n  present in .agents/. Also seeds local files it never overwrites: creates an\n  empty .cursor/memory.json, seeds .mcp.json / .amp/settings.json from the\n  .example files and upserts the memory server entry, writes the spend-hook\n  entries into .cursor/hooks.json, merges .gitignore, and copies CLAUDE.md to\n  .claude/CLAUDE.md. Existing user content in those files is kept.\n\nnpx agent-orchestrator-kit status\n  Show the archive_after_merge policy line, progress, review verdict, archive-readiness, MCP health, and Skill health\n  (warn-only; missing/stale skills do not fail the command)\n\nnpx agent-orchestrator-kit gate-check [change-name] [options]\n  --src-glob <glob>  Source path filter used to detect code changes; a comma- or\n                     space-separated list is passed to git as separate pathspecs\n                     (default: pipeline.src_glob from orchestrator.yaml, else src/)\n  --base <ref>       Git ref to diff against (default: HEAD~1)\n  --staged           Check staged files (git diff --cached) instead of --base\n  --tasks <name>     Lint task contracts (Files / Do / Done-when)\n  --review <name>    Deterministic Tier 1 review (optional --json)\n  --review-md <name> Check review.md against the /opsx:review schema (optional --json)\n  Exit non-zero when require_spec_review is true, src/ changed, and the\n  active change has no review.md with Verdict: APPROVE. Graceful no-op\n  otherwise (missing config, review not required, no relevant diff).\n\nnpx agent-orchestrator-kit hooks-setup\n  Opt-in pre-commit gate (husky-first, else core.hooksPath=.githooks)\n\nnpx agent-orchestrator-kit mcp-setup [--vcs github|gitlab] [--no-browser]\n  Install GitHub/GitLab (from origin) and browser MCP launchers\n\nnpx agent-orchestrator-kit figma-setup\n  Create local .agents/figma.local.env from the example, refresh the launcher,\n  and add the figma MCP entry to .mcp.json / .amp/settings.json (never prints the token)\n\nnpx agent-orchestrator-kit figma-status\n  Report whether a local Figma token is configured (never prints the token)\n\nnpx agent-orchestrator-kit figma-fetch [options]\n  --url <url>        Figma design URL (file key + optional node-id)\n  --file <key>       Figma file key\n  --nodes <ids>      Comma-separated node ids (1:2 or 1-2)\n  --depth <n>        Limit node tree depth (use for large frames; omit = full tree)\n  --out <path>       Output JSON path (default: figma-nodes.json)\n  Fetch Figma file/nodes JSON via the REST API using the local token\n\nnpx agent-orchestrator-kit memory-setup\n  Install the memory MCP launcher and rewrite Cursor/Amp configs to use an\n  absolute MEMORY_FILE_PATH\n\nnpx agent-orchestrator-kit archive <name> [--sync | --no-sync --force] [options]\n  --model <name>     LLM product id recorded on the Archiver session\n  --platform <id>    cursor | claude | amp\n  --input-tokens <n> / --output-tokens <n> / --total-tokens <n>\n                     Token spend for the Archiver session (total defaults to in+out)\n  --cost-usd <usd>   Cost of the Archiver session in USD\n  --collect          Collect all spend adapters (default: locked client only)\n  --if-ready         CI mode: print \"skip: <reason>\" and exit 0 (nothing changed) when\n                     archive_after_merge is false, the change already looks archived\n                     (Gate 0) or is not ready; real failures still exit 1\n  Refuse an already archived folder (Gate 0), gate-check a completed change, optionally merge delta specs, move to\n  openspec/changes/archive/YYYY-MM-DD-<name>, validate, write final handoff,\n  and print the change-wide metrics summary.\n\nnpx agent-orchestrator-kit handoff [change-name] [options]\n  --restore          Print the restore briefing instead of persisting\n                     (also records the session start into metrics.json)\n  --closed-role <role>      Closed role for persist\n  --next-command <command>  Next /opsx:* command\n  --next-role <role>        Next role or subagent name\n  --summary <text>   Persisted summary (also fills Done when Done is empty)\n  --done <text>      Done section\n  --decisions <text> Decisions section\n  --blocked <text>   Blocked section\n  --attach <text>    Attach section\n  --spawn <text>     Subagents to spawn\n  --constraints <text>      Constraints section\n  --status <status>  Change status observation\n  --tasks <progress> Task progress n/m\n  --review <verdict> Review verdict\n  --session-count <n>       Handoff session_count\n  --runtime <value>  local | cloud (invalid values exit non-zero)\n  --agent-id <id>    Cloud agent identifier (default: none)\n  --cloud-check      Verify change artifacts are committed and pushed\n                     (cloud: non-zero on failure; local: warning, exit 0)\n  --started-at <iso> Session start override when --restore was not run\n  --model <name>     LLM product id (metrics.json); never a Closed role\n  --platform <id>    cursor | claude | amp\n  --input-tokens <n> / --output-tokens <n> / --total-tokens <n>\n                     Token spend for this session (total defaults to in+out)\n  --cost-usd <usd>   Session cost in USD\n  --collect          Also run local spend adapters (off by default)\n  --no-metrics       Skip recording this session into metrics.json\n  After a green apply (Implementer, every task [x], Blocked none) stdout is the\n  single archive command line instead of a next-session prompt.\n\nnpx agent-orchestrator-kit metrics [change-name] [options]\n  --json             Print raw metrics.json\n  --summary-json     Print compact aggregate JSON for dashboards\n  --migrate          Rewrite metrics.json using the current schema without\n                     recomputing numbers (v1 → v2)\n  --collect          Backfill the last session from local spend adapters\n                     without adding a new session\n  Show recorded session metrics for a change (active or archived):\n  time per phase, sessions, tokens, cost, roles, models, lead time.\n```\n\n## Directory Reference\n\n```\n.agents/                 # Committed — source of truth for all IDEs\n  commands/              # /opsx:* command definitions\n  rules/                 # Auto-applied rules for Cursor\n  subagents/             # Custom subagents (source of truth, all IDEs)\n  skills/                # Skills for Cursor, Claude Code, Amp\n                         #   subagent-*/ — auto-generated Amp wrappers (do not edit)\n  orchestrator.yaml      # Project pipeline config\n\n.cursor/                 # Local only — Cursor IDE runtime\n  skills/                # Synced from .agents/skills/\n  rules/                 # Synced from .agents/rules/\n  agents/                # Synced from .agents/subagents/\n  commands/              # Synced from .agents/commands/ (flat — /opsx-apply)\n  memory.json            # Memory MCP data\n\n.claude/                 # Local only — Claude Code runtime\n  skills/                # Synced from .agents/skills/\n  agents/                # Synced from .agents/subagents/\n  commands/opsx/         # Synced from .agents/commands/ (namespaced — /opsx:apply)\n  CLAUDE.md              # Synced from root CLAUDE.md\n\n.amp/                    # Local only — Amp config\n  settings.json          # MCP servers (manual or via amp mcp add)\n\nAGENTS.md                # Committed — read natively by Amp; CLAUDE.md is the Claude Code entry point\nCLAUDE.md                # Committed — synced to .claude/CLAUDE.md\nopenspec/                # Committed — spec-driven workflow\n  config.yaml            # Project context for AI\n  specs/                 # Source of truth after archive\n  changes/               # Active work; <name>/handoff.md + metrics.json index session state\n```\n\n## Roadmap\n\nThe kit moves toward an Agentic Factory in four phases. **One phase = one OpenSpec change**; the next phase does not start until the previous change is archived.\n1. `add-factory-gates-and-mcp` — local review gate on commit and Figma-style MCP launchers (GitHub / GitLab / browser). Implemented: `hooks-setup`, `mcp-setup`, `gate-check --staged`, MCP health in `status`.\n2. `add-factory-memory-and-skills` — git-canonical decisions with Memory MCP as a mirror, plus a machine skill inventory. Implemented: append-only `decisions.md`, Skill health in `status`.\n3. `add-cloud-agent-handoff` — session artifacts exist only on git-tracked paths. Implemented: `## Runtime` in `handoff.md`, `--runtime` / `--agent-id` / `--cloud-check`, cloud Session Exit.\n4. Phase 4 (`add-factory-control-plane`) is an opt-in platform decision, not the next sprint.\nPhase bounds and non-goals: [`openspec/specs/agentic-factory-roadmap/spec.md`](openspec/specs/agentic-factory-roadmap/spec.md).\n\n## Changelog\n\n### 0.18.0\n- **Thin `/opsx:propose` conductor**: the parent does not research the repo. It reads the decision brief (by path), `status` and `handoff --restore`, spawns `spec-architect` within 5 tool calls, and after the report makes at most 3 tool calls without re-reading the artifacts on a green gate.\n- **Artifact size budget in `gate-check --review`**: a warning when `tasks.md` is over 60 000 B or `proposal.md` + `design.md` + `tasks.md` + delta specs are over 150 000 B, with the advice to split the change into slices. `pipeline.artifact_budget: warn | strict | off` sets the mode (def","readmeFilename":"README.md"}