{ "markdown": "
\n\n\"Cool\n\n### Get a saved report from your AI agent, with every claim tied to a line of code — not a chat answer you lose.\n\n[![CI](https://img.shields.io/github/actions/workflow/status/coo1white/cool-workflow/ci.yml?branch=main&style=flat-square&label=CI&color=EC6516)](https://github.com/coo1white/cool-workflow/actions/workflows/ci.yml) [![npm](https://img.shields.io/npm/v/cool-workflow?style=flat-square&label=npm&color=cb3837)](https://www.npmjs.com/package/cool-workflow) [![downloads](https://img.shields.io/npm/dm/cool-workflow?style=flat-square&label=downloads&color=EC6516)](https://www.npmjs.com/package/cool-workflow) [![provenance](https://img.shields.io/badge/npm-provenance-3178C6?style=flat-square)](https://www.npmjs.com/package/cool-workflow) [![release](https://img.shields.io/github/v/tag/coo1white/cool-workflow?style=flat-square&label=release&color=brightgreen&sort=semver)](https://github.com/coo1white/cool-workflow/tags) [![license](https://img.shields.io/badge/license-BSD--2--Clause-blue?style=flat-square)](LICENSE)\n\n
\n\n## What is this?\n\nCool Workflow (`cw`) is a small command-line tool that turns your AI coding agent's chat answer — easy to lose, hard to check — into a saved report. Point it at a repo, or any folder of docs, and:\n\n- **It plans the work.** Your question becomes a set of small tasks.\n- **Your agent does the work.** CW never runs a model itself — your own agent reads and thinks.\n- **It writes a checked report.** Every claim points to a real place in your code, like `file.ts:42`. A result with no evidence stops instead of passing through.\n\n> **The model is fuel. CW is the black-box recorder, the dashboard, and the gearbox — never the engine.**\n> It never calls a model API, never holds your keys, and never uploads your code.\n\n## Install\n\n```bash\nnpm install -g cool-workflow\n```\n\n
\nOr install with Homebrew\n\n```bash\nbrew tap coo1white/cool-workflow https://github.com/coo1white/cool-workflow\nbrew install coo1white/cool-workflow/cool-workflow\ncw version\n```\n\nUpgrade later with `brew update && brew upgrade cool-workflow`.\n
\n\n**You need:** Node.js v18 or newer. No agent yet? Step 1 below still works — **CW never runs a model itself.**\n\n## Works with your agent\n\n| Agent | Flag | Status |\n|---|---|---|\n| Claude Code | `-claude` | ✅ works |\n| Codex CLI | `-codex` | ✅ works |\n| Muse Code | `-muse` | ✅ works |\n| OpenCode | `-opencode` | ✅ works |\n| Gemini | `-gemini` | ✅ through opencode |\n| DeepSeek | `-deepseek` | ✅ through opencode or an HTTP endpoint |\n| Cursor | — | ⬜ not yet |\n| GitHub Copilot CLI | — | ⬜ not yet |\n| Aider | — | ⬜ not yet |\n| Qwen Code | — | ⬜ not yet |\n| Kimi | — | ⬜ not yet |\n\nNot sure what you have? `cw doctor` checks your setup and `cw fix` prints the commands that put it right.\n\n## Quick Start\n\n### 1 · See it work — 30 seconds, no agent needed\n\n```bash\ncw demo tamper\n# → builds a real signed ledger, forges it three ways, catches all three offline\n# → VERDICT: tamper-evidence holds ✓\n```\n\n### 2 · Ask a question about your code — one command\n\n```bash\ncw -q \"How does auth work end-to-end here?\"\n```\n\nCW uses the current repo and the first agent it finds on your `PATH`. Want a specific agent? Add a flag from the table above, such as `-claude`.\n\n### 3 · Open the report\n\nThe report opens in your browser by itself when the run ends. Later, open it again with:\n\n```bash\ncw report --open\n```\n\nWant to see one first? A real run's Workbench and report, rebuilt on every push: **[coo1white.github.io/cool-workflow](https://coo1white.github.io/cool-workflow/)** (the report is at [/report.html](https://coo1white.github.io/cool-workflow/report.html)).\n\nThese three steps are the core path. Everything else is kept working, not grown.\n\n## Can You Trust the Report?\n\nCW does not run the model — it keeps the books. Your agent signs its findings (**ed25519**), and `cw report verify-bundle` checks — offline, with only the public key — that every signed finding is in the report unaltered. CW holds no private key: the agent signs, CW only verifies. This proves the signed findings reached you unaltered — not that nothing else was added, and not that none were left out. See the **[Trust Model](plugins/cool-workflow/docs/trust-model.md)**.\n\n## Troubleshooting\n\n| Problem | Fix |\n|---|---|\n| No agent found | `cw doctor` — shows which agents are on your machine |\n| `status: blocked` | Set `CW_AGENT_COMMAND=builtin:claude` or pass `-claude` |\n| `claude: command not found` | Install Claude Code and run again |\n| Where is my report? | `/.cw/runs//report.md`, or run `cw report --open` |\n| `Missing required input: question` | Add `-q \"\"` |\n| Run stopped before the end | `cw --resume --run ` takes it to the end (inside the project, or add `--repo `) |\n| `... is not a git project` | Run it inside the project, or pass `--repo` |\n\n## Learn more\n\n- **[User Guide](https://github.com/coo1white/cool-workflow/wiki/User-Guide)** — your first ten minutes\n- **[Why Cool Workflow](https://github.com/coo1white/cool-workflow/wiki/Mental-Model)**\n- **[How it works](https://github.com/coo1white/cool-workflow/wiki/Architecture)**\n- **[What you can run](https://github.com/coo1white/cool-workflow/wiki/Workflow-Apps)**\n- **[From your editor](https://github.com/coo1white/cool-workflow/wiki/MCP-And-Manifests#from-your-editor)**\n- **[Trust & Audit](https://github.com/coo1white/cool-workflow/wiki/Trust-And-Audit)**\n- **[Repo Map](https://github.com/coo1white/cool-workflow/wiki/Repo-Map)**\n- **[Wiki home](https://github.com/coo1white/cool-workflow/wiki)**\n\nCW dogfoods its own release: every cut runs `release-cut` against this repo.\n\n## License\n\nBSD-2-Clause. Built by COOLWHITE LLC.\n", "bytes": 5969, "sha": "e5a91cf82bdc6647baa6d90e6643f9fd0d9e9c6588ffc32d860f932a83eb5a47", "repo_slug": "coo1white/cool-workflow", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_coo1white_cool_workflow_871ff5b7/readme" }