![\"Strikethroo:](\"docs/assets/strikethroo-hero.png\")
\n\n \n
\n Spec-driven development optimized for time-to-merge, not time-to-first-draft.
\n You review the plan, where a correction costs a sentence — not the diff, where it costs a review cycle.\n
\n ![\"npm](\"https://img.shields.io/npm/v/strikethroo?style=flat-square&label=npm&color=BE376F&labelColor=2b2230\")
![\"tests\"](\"https://img.shields.io/github/actions/workflow/status/e0ipso/strikethroo/test.yml?style=flat-square&label=tests&color=BE376F&labelColor=2b2230\")
![\"node](\"https://img.shields.io/node/v/strikethroo?style=flat-square&color=BE376F&labelColor=2b2230\")
![\"MIT](\"https://img.shields.io/badge/license-MIT-BE376F?style=flat-square&labelColor=2b2230\"){kind=icon}
\n Why Strikethroo · \n Workflow · \n Customization · \n Visualizations · \n FAQ\n
\n\n## Why Strikethroo?\n\nMost spec-driven tools optimize the input: better spec in, better code out, human catches the rest at the end. Strikethroo assumes the agent is an unreliable narrator of its own work -- including a second agent asked to review the first -- and that the scarce resource is your attention, not tokens.\n\n\n\n![\"\"](\"docs/assets/icons/focus.svg\"){kind=icon} \n\n### You review the plan, not the diff\n\nCorrecting a plan costs a sentence. Correcting the same misunderstanding in a diff costs a review cycle, a rework cycle, and a re-review. An explicit approval gate puts your careful read where it is worth the most, and one question is asked at a time so it never gets skim-answered.\n\n | \n\n\n![\"\"](\"docs/assets/icons/shield-check.svg\"){kind=icon} \n\n### Guarantees are compiled, not requested\n\nA rule in Markdown is a request; a rule in TypeScript is a guarantee. Hooks and templates are yours to edit. The certification rule -- an uncertified review is never reported as a clean one -- is compiled and cannot be loosened by editing a hook.\n\n | \n
\n\n![\"\"](\"docs/assets/icons/git-fork.svg\"){kind=icon} \n\n### Nobody marks their own homework\n\nThe optional review gate runs on a *different* harness than the one that wrote the code -- the current harness is structurally excluded from the candidate set, not merely deprioritized. The reviewer detects and never fixes; findings are reported for you to act on.\n\n | \n\n\n![\"\"](\"docs/assets/icons/sliders-horizontal.svg\"){kind=icon} \n\n### Bends to your conventions\n\nPlain-Markdown hooks fire at eleven points across the workflow; inject your test commands, standards, and domain rules so every plan, task, and run inherits them. No plugins, no code.\n\n | \n
![\"\"](\"docs/assets/icons/waypoints.svg\"){kind=icon}
Hooks\n\nFire at eleven points across the workflow (before planning, after each phase, on errors, and more). Drop in your test commands, coding standards, and domain rules; every plan, task, and execution run inherits them.\n\n### ![\"\"](\"docs/assets/icons/file-text.svg\"){kind=icon}
Templates\n\nDefine the shape of plans and tasks -- add your own sections and checklists.\n\n### ![\"\"](\"docs/assets/icons/book-open.svg\"){kind=icon}
Project context\n\nOne file of domain knowledge every step reads.\n\nHooks, templates, and a project-context file are all plain Markdown -- nothing to compile, no plugin API to learn. See the [Customization Guide](https://strikethroo.canpicasoft.com/customization.html) for examples.\n\n## Quick Start\n\n```bash\n# 1. Bootstrap the shared workspace\nnpx strikethroo init --harnesses claude\n\n# 2. Install the workflow skills\nnpx skills add e0ipso/strikethroo\n```\n\nOn re-init, `--harnesses` is optional — Strikethroo reuses the saved selection in `.ai/strikethroo/.init-metadata.json`. Workspaces initialized before that field existed must pass `--harnesses` once.\n\n**Already set up?** Refresh the workspace and update installed workflow skills in one step:\n\n```bash\nnpx strikethroo@latest update\n```\n\nExit 0 requires both the workspace refresh and the skills installer to succeed. If the installer fails after a successful refresh, the refreshed workspace is kept; re-run `update` or the installer command it reports. Start a fresh agent session after updating — a running session may still follow previous skill instructions. Old skill copies cannot show update notices until you run `update` once.\n\nRequires Node.js 22+ and an assistant that supports the Agent Skills format.\n\n## Profiles: a tailored setup in one step\n\nA strikethroo profile packages a complete workspace configuration -- hooks, templates, project context -- so `init --profile