{"_id":"@bigsteele/ai-audit","_rev":"7-1a323448eb1f4774bcb746b1444ee266","name":"@bigsteele/ai-audit","dist-tags":{"latest":"0.2.5"},"versions":{"0.1.0":{"name":"@bigsteele/ai-audit","version":"0.1.0","author":{"url":"Together Inc.","name":"Big Steele"},"license":"UNLICENSED","_id":"@bigsteele/ai-audit@0.1.0","maintainers":[{"name":"bigsteele","email":"info@togetheritsbuilt.com"}],"homepage":"https://bigsteele.com","bugs":{"url":"https://github.com/bigsteele/blank-canvas-project/issues"},"bin":{"ai-audit":"dist/cli.js"},"dist":{"shasum":"1aa20173b807fa64bfb2d84eeea589dc3050352a","tarball":"https://registry.npmjs.org/@bigsteele/ai-audit/-/ai-audit-0.1.0.tgz","fileCount":13,"integrity":"sha512-MyjcAGT+nGqW3qR4N6Or66WU6G5EUyp3+h9lAE8xfmW8raEjokkpUA4d8s8/7GEUGeK7iK2CeZPHMyTizkjihQ==","signatures":[{"sig":"MEUCIQCL/51rY+0EKHeN8yi1rar0+CO6OLlKBo929LG8XNcNlQIgehZQGNG5COdLdzWVneaQBV81faQVr3D5AcvQlG+Zahg=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":53824},"type":"module","engines":{"node":">=20"},"gitHead":"ff675a2d5544d0581c186aed1c6fba0260313cb1","scripts":{"test":"vitest run","build":"rm -rf dist && tsc -p tsconfig.json","typecheck":"tsc -p tsconfig.json --noEmit","prepublishOnly":"npm run build && npm test"},"_npmUser":{"name":"bigsteele","email":"info@togetheritsbuilt.com"},"repository":{"url":"git+https://github.com/bigsteele/blank-canvas-project.git","type":"git","directory":"packages/ai-audit"},"_npmVersion":"10.9.8","description":"Big Steele's AI audit: reads a codebase and reports what it automates, what its AI does, what its agents can do, and how much of the software an agent could run. One score, one grade, every finding cited to a file. Never reads env values; never includes s","directories":{},"_nodeVersion":"22.23.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.7.0","@types/node":"^22.10.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-audit_0.1.0_1788664021393_0.9510888053301281","host":"s3://npm-registry-packages-npm-production"}},"0.2.0":{"name":"@bigsteele/ai-audit","version":"0.2.0","author":{"url":"Together Inc.","name":"Big Steele"},"license":"UNLICENSED","_id":"@bigsteele/ai-audit@0.2.0","maintainers":[{"name":"bigsteele","email":"info@togetheritsbuilt.com"}],"homepage":"https://bigsteele.com","bugs":{"url":"https://github.com/bigsteele/blank-canvas-project/issues"},"bin":{"ai-audit":"dist/cli.js"},"dist":{"shasum":"a97f73290bccac883c347f575f40c8423327ef78","tarball":"https://registry.npmjs.org/@bigsteele/ai-audit/-/ai-audit-0.2.0.tgz","fileCount":14,"integrity":"sha512-Lw1NI3i5qqKFfh/mYDC1nVG6UU5D4+mCWFKjPAGeMNtC95Rkrxg2X5EubYYFosTRP7Cymdf/ps8+uGHNNDUWsw==","signatures":[{"sig":"MEQCIFcAxXbxXA/yoBgW3R8q78kxQ0ytjrsl9rvc7Ux1BhR6AiAs+QPzddEzg7GcUNKFq63JujkjLwcvN7v6CKZn6xJDMA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":69360},"type":"module","engines":{"node":">=20"},"gitHead":"1153f1c6e090b927e506fe142d98aee8ab959cb7","scripts":{"test":"vitest run","build":"rm -rf dist && tsc -p tsconfig.json","typecheck":"tsc -p tsconfig.json --noEmit","prepublishOnly":"npm run build && npm test"},"_npmUser":{"name":"bigsteele","email":"info@togetheritsbuilt.com"},"repository":{"url":"git+https://github.com/bigsteele/blank-canvas-project.git","type":"git","directory":"packages/ai-audit"},"_npmVersion":"10.9.8","description":"Big Steele's AI audit: reads a codebase and reports what it automates, what its AI does, what its agents can do, and how much of the software an agent could run. One score, one grade, every finding cited to a file. Never reads env values; never includes s","directories":{},"_nodeVersion":"22.23.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.7.0","@types/node":"^22.10.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-audit_0.2.0_1788666520980_0.39723055227593695","host":"s3://npm-registry-packages-npm-production"}},"0.2.1":{"name":"@bigsteele/ai-audit","version":"0.2.1","author":{"url":"Together Inc.","name":"Big Steele"},"license":"UNLICENSED","_id":"@bigsteele/ai-audit@0.2.1","maintainers":[{"name":"bigsteele","email":"info@togetheritsbuilt.com"}],"homepage":"https://bigsteele.com","bugs":{"url":"https://github.com/bigsteele/blank-canvas-project/issues"},"bin":{"ai-audit":"dist/cli.js"},"dist":{"shasum":"d87708a7b6258b9e100ab434a030cf8f36468695","tarball":"https://registry.npmjs.org/@bigsteele/ai-audit/-/ai-audit-0.2.1.tgz","fileCount":14,"integrity":"sha512-6n0AU1gPa0JyPDnMMZwszr+Oh5Yy0OWb9r1yeTnyBQX2qMO1fkc3jiVh3zfNOmeZMDhM2fS4H4+vi0QdiGKdRQ==","signatures":[{"sig":"MEUCIC+cEMGWG9u6HsjDEk2uaW9d/V5j5hhVBISP8oXhKYXIAiEA2T8PzqtOQ04j3JIU5R9M2ffnMPEa1FoDzQL23gJLHio=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":70312},"type":"module","engines":{"node":">=20"},"gitHead":"8611564caeb347018df876b2f880b5e773389310","scripts":{"test":"vitest run","build":"rm -rf dist && tsc -p tsconfig.json","typecheck":"tsc -p tsconfig.json --noEmit","prepublishOnly":"npm run build && npm test"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:38e3aa05-0c25-4f79-bd03-c687ff3baed5"}},"repository":{"url":"git+https://github.com/bigsteele/blank-canvas-project.git","type":"git","directory":"packages/ai-audit"},"_npmVersion":"12.0.2","description":"Big Steele's AI audit: reads a codebase and reports what it automates, what its AI does, what its agents can do, and how much of the software an agent could run. One score, one grade, every finding cited to a file. Never reads env values; never includes s","directories":{},"_nodeVersion":"22.23.2","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.7.0","@types/node":"^22.10.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-audit_0.2.1_1788715810478_0.095017791588617","host":"s3://npm-registry-packages-npm-production"}},"0.2.2":{"name":"@bigsteele/ai-audit","version":"0.2.2","author":{"url":"Together Inc.","name":"Big Steele"},"license":"UNLICENSED","_id":"@bigsteele/ai-audit@0.2.2","maintainers":[{"name":"bigsteele","email":"info@togetheritsbuilt.com"}],"homepage":"https://bigsteele.com","bugs":{"url":"https://github.com/bigsteele/blank-canvas-project/issues"},"bin":{"ai-audit":"dist/cli.js"},"dist":{"shasum":"1326444962131843d64ff0f8570d3e8d608cb0ba","tarball":"https://registry.npmjs.org/@bigsteele/ai-audit/-/ai-audit-0.2.2.tgz","fileCount":26,"integrity":"sha512-ZurepoAYD8m/4ZK/ixx3GWl6Y0e4kIVOvscMqgAhnn8Jp9GGH8JKVIiuJmRDJKGNoh3prMMB/6NXKJ0ca1f4Qw==","signatures":[{"sig":"MEYCIQCOVjevbKJ09gIBHcKGJ9zyH1/+xLXIRd3TINSTuUQsUgIhALB+I3rclHRK0HrXkn9D0MZ3kfS4aRiuftrrvC0M2vzv","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":78414},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","engines":{"node":">=20"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"},"./package.json":"./package.json"},"gitHead":"5387750c1903f49109b3a6e00a5054d2e7bd328b","scripts":{"test":"vitest run","build":"rm -rf dist && tsc -p tsconfig.json","typecheck":"tsc -p tsconfig.json --noEmit","prepublishOnly":"npm run build && npm test"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:38e3aa05-0c25-4f79-bd03-c687ff3baed5"}},"repository":{"url":"git+https://github.com/bigsteele/blank-canvas-project.git","type":"git","directory":"packages/ai-audit"},"_npmVersion":"12.0.2","description":"Big Steele's AI audit: reads a codebase and reports what it automates, what its AI does, what its agents can do, and how much of the software an agent could run. One score, one grade, every finding cited to a file. Never reads env values; never includes s","directories":{},"_nodeVersion":"22.23.2","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.7.0","@types/node":"^22.10.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-audit_0.2.2_1788716020124_0.8609422371839552","host":"s3://npm-registry-packages-npm-production"}},"0.2.3":{"name":"@bigsteele/ai-audit","version":"0.2.3","author":{"url":"Together Inc.","name":"Big Steele"},"license":"UNLICENSED","_id":"@bigsteele/ai-audit@0.2.3","maintainers":[{"name":"bigsteele","email":"info@togetheritsbuilt.com"}],"homepage":"https://bigsteele.com","bugs":{"url":"https://github.com/bigsteele/blank-canvas-project/issues"},"bin":{"ai-audit":"dist/cli.js"},"dist":{"shasum":"13b411b5f46ede244353001179e86aabfc032105","tarball":"https://registry.npmjs.org/@bigsteele/ai-audit/-/ai-audit-0.2.3.tgz","fileCount":26,"integrity":"sha512-VF2y9qw5mJFYKGlNNAhVoGEJNMu0bahX0lrvPXMOe4Mw2nC3agR2uWjYS7NAukpVeqg5wusYv0UA7KPKSNTFQw==","signatures":[{"sig":"MEYCIQDjZZg35zfnIFjtkEavnn5Dgm37xrugWs0RJG9hZpYO2gIhAIXugygq6U9ZQFslWC6pNLx8cqDKF2masN7IIT6j4QX0","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":81863},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","engines":{"node":">=20"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"},"./package.json":"./package.json"},"gitHead":"0784bf02da05547c3c6dc39f94f3d99a576751b4","scripts":{"test":"vitest run","build":"rm -rf dist && tsc -p tsconfig.json","typecheck":"tsc -p tsconfig.json --noEmit","prepublishOnly":"npm run build && npm test"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:38e3aa05-0c25-4f79-bd03-c687ff3baed5"}},"repository":{"url":"git+https://github.com/bigsteele/blank-canvas-project.git","type":"git","directory":"packages/ai-audit"},"_npmVersion":"12.0.2","description":"Big Steele's AI audit: reads a codebase and reports what it automates, what its AI does, what its agents can do, and how much of the software an agent could run. One score, one grade, every finding cited to a file. Never reads env values; never includes s","directories":{},"_nodeVersion":"22.23.2","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.7.0","@types/node":"^22.10.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-audit_0.2.3_1788742889133_0.45460170969789804","host":"s3://npm-registry-packages-npm-production"}},"0.2.4":{"name":"@bigsteele/ai-audit","version":"0.2.4","author":{"url":"Together Inc.","name":"Big Steele"},"license":"UNLICENSED","_id":"@bigsteele/ai-audit@0.2.4","maintainers":[{"name":"bigsteele","email":"info@togetheritsbuilt.com"}],"homepage":"https://bigsteele.com","bugs":{"url":"https://github.com/bigsteele/blank-canvas-project/issues"},"bin":{"ai-audit":"dist/cli.js"},"dist":{"shasum":"8c6387003f8e041742c49d0bf89fa2a04b74ec37","tarball":"https://registry.npmjs.org/@bigsteele/ai-audit/-/ai-audit-0.2.4.tgz","fileCount":26,"integrity":"sha512-mfSUGDl1yyOyRmySipQ08wAOIKIn/9pomKGGAJFj9Dn5E5C/QQqlkRPOAqqE2ukLOfOTvLfrawsOqEj0KWFnhw==","signatures":[{"sig":"MEYCIQDg7xj/qvdnw+TAHecDaKfTsPVXMnflYafdhtvxiD/1iAIhAMnKqLyzDPEpUSD6PH34ZS/GWdtcjuukebz91Me3wMQA","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":82005},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","engines":{"node":">=20"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"},"./package.json":"./package.json"},"gitHead":"f793e3eed990d285ba1f41be651a9884d2ebab31","scripts":{"test":"vitest run","build":"rm -rf dist && tsc -p tsconfig.json","typecheck":"tsc -p tsconfig.json --noEmit","prepublishOnly":"npm run build && npm test"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:38e3aa05-0c25-4f79-bd03-c687ff3baed5"}},"repository":{"url":"git+https://github.com/bigsteele/blank-canvas-project.git","type":"git","directory":"packages/ai-audit"},"_npmVersion":"12.0.2","description":"Big Steele's AI audit: reads a codebase and reports what it automates, what its AI does, what its agents can do, and how much of the software an agent could run. One score, one grade, every finding cited to a file. Never reads env values; never includes s","directories":{},"_nodeVersion":"22.23.2","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.7.0","@types/node":"^22.10.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-audit_0.2.4_1788744342958_0.3991988822477526","host":"s3://npm-registry-packages-npm-production"}},"0.2.5":{"name":"@bigsteele/ai-audit","version":"0.2.5","description":"Big Steele's AI audit: reads a codebase and reports what it automates, what its AI does, what its agents can do, and how much of the software an agent could run. One score, one grade, every finding cited to a file. Never reads env values; never includes s","type":"module","license":"UNLICENSED","author":{"name":"Big Steele","url":"Together Inc."},"homepage":"https://bigsteele.com","repository":{"type":"git","url":"git+https://github.com/bigsteele/blank-canvas-project.git","directory":"packages/ai-audit"},"bin":{"ai-audit":"dist/cli.js"},"main":"dist/index.js","types":"dist/index.d.ts","exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"},"./package.json":"./package.json"},"engines":{"node":">=20"},"scripts":{"build":"rm -rf dist && tsc -p tsconfig.json","typecheck":"tsc -p tsconfig.json --noEmit","test":"vitest run","prepublishOnly":"npm run build && npm test"},"devDependencies":{"@types/node":"^22.10.0","typescript":"^5.7.0","vitest":"^3.0.0"},"publishConfig":{"access":"public"},"_id":"@bigsteele/ai-audit@0.2.5","gitHead":"8831bbdd7c01343198591e3edb21a3d26f136b8c","bugs":{"url":"https://github.com/bigsteele/blank-canvas-project/issues"},"_nodeVersion":"22.23.0","_npmVersion":"10.9.8","dist":{"integrity":"sha512-TYwCR1Xy6eUe46aqXGcaJ/BuhqhkGyBRN2mwMbSMs4PUHILBmVOZzSQ2wPieIhAfPs45Oq5v+koUrG1lB8hRnw==","shasum":"f61b1fff1a3089ab8368246e5dadf42f17ab239b","tarball":"https://registry.npmjs.org/@bigsteele/ai-audit/-/ai-audit-0.2.5.tgz","fileCount":26,"unpackedSize":82019,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQD4Grx+r1R7q5K0WhdtkYLhQhj7XouWAJ0iHKr9n08L4wIhALA8fpGC8CvsjTGA9NMw54NdxGw3xBNWVDWakMjldktI"}]},"_npmUser":{"name":"bigsteele","email":"info@togetheritsbuilt.com"},"directories":{},"maintainers":[{"name":"bigsteele","email":"info@togetheritsbuilt.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/ai-audit_0.2.5_1789390573260_0.12184258080550547"},"_hasShrinkwrap":false}},"time":{"created":"2026-09-06T03:07:01.181Z","modified":"2026-09-14T12:56:13.567Z","0.1.0":"2026-09-06T03:07:01.552Z","0.2.0":"2026-09-06T03:48:41.098Z","0.2.1":"2026-09-06T17:30:10.607Z","0.2.2":"2026-09-06T17:33:40.259Z","0.2.3":"2026-09-07T01:01:29.295Z","0.2.4":"2026-09-07T01:25:43.124Z","0.2.5":"2026-09-14T12:56:13.407Z"},"bugs":{"url":"https://github.com/bigsteele/blank-canvas-project/issues"},"author":{"name":"Big Steele","url":"Together Inc."},"license":"UNLICENSED","homepage":"https://bigsteele.com","repository":{"type":"git","url":"git+https://github.com/bigsteele/blank-canvas-project.git","directory":"packages/ai-audit"},"description":"Big Steele's AI audit: reads a codebase and reports what it automates, what its AI does, what its agents can do, and how much of the software an agent could run. One score, one grade, every finding cited to a file. Never reads env values; never includes s","maintainers":[{"name":"bigsteele","email":"info@togetheritsbuilt.com"}],"readme":"# @bigsteele/ai-audit\n\nBig Steele's AI audit. Point it at a codebase and it reports, file by file, what the\nsoftware automates, what its AI does, what its agents can do, and how much of the\nsoftware an AI agent could run. One score out of 100, a letter grade, and a level:\n\n| Level | Name | Means |\n|---|---|---|\n| 0 | Manual | operated by people through screens |\n| 1 | Automated | programs can call it; work runs on schedules and webhooks; no model in the loop |\n| 2 | AI-assisted | models answer or draft inside the product; people do the doing |\n| 3 | Agentic | agents act through tools or an MCP server; a person owns the operation |\n| 4 | Autonomous | an AI agent could run the whole software: operations reachable by machine, failures visible |\n\n100 and A+ means an AI agent could run the whole thing.\n\n```\nnpx @bigsteele/ai-audit --repo .\n```\n\nWrites `ai-audit-<app>.md` (the report) and `ai-audit-<app>.json` (the same facts for a\nprogram) into the repository, named for the app from its manifest (or its folder, when the\nmanifest carries a scaffold name), so two audits never overwrite each other. Add `--out <dir>` to write elsewhere, `--stdout` to print the report instead,\n`--gate <score>` to set the pass mark (default 25 and level 1 or above).\n\nExit code 0 when the gate passes, 2 when it does not. The two output files land in the\nrepository unless `--out` says otherwise; add `ai-audit-*.md` and `ai-audit-*.json` to\n`.gitignore` if you do not want them committed.\n\n## What it reads, and what it never does\n\nIt reads the files in the tree, skipping `node_modules`, build output, dot-directories\n(planning trees, editor folders), a nested repository of its own, a copy of the repository\ninside itself, and every `.env*` file. It never opens an env file, never runs anything, and never writes source text or a\nvalue into the report: findings are file paths and counts. If any output string looks\nlike a credential, nothing is written and the exit code is 1, because that means a secret\nis committed in the repository and that is the thing to fix first.\n\n## What the software is for decides what counts\n\nA flat rubric punishes a platform for not being a voice product. So the repository may\ndeclare a **profile**, which weights the four groups, and **waive** named criteria with a\nreason. Both print in the report; a reader sees exactly what was set aside and why.\n\n| Profile | Surfaces | AI | Agents | Autonomy | Set aside by default |\n|---|---|---|---|---|---|\n| `product` (default) | 25 | 25 | 25 | 25 | nothing |\n| `platform` | 35 | 15 | 20 | 30 | voice/vision, retrieval |\n| `agent` | 15 | 25 | 35 | 25 | nothing |\n| `internal` | 30 | 20 | 20 | 30 | voice/vision |\n\nDeclare it with `--profile platform`, or in `ai-audit.config.json` at the repository root:\n\n```json\n{ \"profile\": \"platform\", \"waive\": { \"webhooks\": \"nothing upstream sends this system events\" } }\n```\n\nA waiver needs a reason of at least a sentence. The criteria that make the grade a grade\ncannot be waived and always count: API handlers, a model provider, server-side AI, tools,\na loop, reach, observability, reliability, guardrails. A refused waiver is printed as\nrefused, so nobody thinks it applied. The level floors never move: a level 3 still needs\ntools and a loop or an MCP server, whatever the profile.\n\n## The rubric\n\nFour groups of 25 points, each point earned by a cited fact:\n\n- **Automated surfaces.** API handlers, an OpenAPI or GraphQL description (a generated\n  capability inventory or typed contract schemas earn half), inbound webhooks, schedules,\n  queues.\n- **AI systems.** A model provider on the server, prompts as code, structured output,\n  retrieval over your own data, voice or vision.\n- **Agents.** Tools a model may call, a loop that lets it act until done, an MCP server,\n  orchestration or MCP client use, memory between runs.\n- **Autonomy and operability.** Reach (machine surfaces against human pages), surfaces\n  that write, observability, retries and idempotency, evals, guardrails and a human gate,\n  documentation written for agents.\n\nThe report ends with \"what raises the grade\": every unearned point with what earning it\ntakes, largest first. Documentation is a multiplier there, not a line item: undocumented\nhandlers count at a quarter toward Reach, so the description item carries the Reach it\nwould unlock (\"+2 direct, +3.5 through Reach\") and is ranked by the sum.\n\n## What it is not\n\nIt measures how ready the architecture is for agents, not whether the product works today.\nIt is not a security review, not a health check, and it runs nothing; a broken deploy\nscores the same as a working one. The report says so in its footer.\n\n## No terminal? (Lovable, Bolt, v0, Replit)\n\n`docs/LOVABLE-PROMPT.md` has two prompts to paste into Lovable's chat. Route A makes\nLovable's agent apply this same rubric to the project it can see and write\n`docs/ai-audit.md` itself, with no GitHub and nothing installed; route B, for projects\nconnected to GitHub, makes Lovable create a workflow that runs the real tool there. The\ntool's grade is the official one; route A is the same rubric read by an agent.\n\n## For the class\n\nThe entry rule is level 1 or above: an automated platform. Run the audit, attach\n`ai-audit.md`. The grade tells you where you stand between a manual tool and a business an\nagent could run.\n\nEvery report ends with the next step: upload it at **bigsteele.com/scan** and get a written read of the three changes that move the grade most, in order. No call required to get it.\n\nBig Steele · bigsteele.com\n","readmeFilename":"README.md"}