io.github.coo1white/cool-workflow
Signed, cited, replayable workflows for Claude, Codex, Gemini, DeepSeek, and other agents.
Open source Open in the app JSON README (API)
About
Signed, cited, replayable workflows for Claude, Codex, Gemini, DeepSeek, and other agents.
Details
- Kind
- MCP servers
- Topic
- AI, RAG & memory
- Publisher
- coo1white
- Origin
- official
- Category
- ferramentas
- Transport
- local
- Version
- 0.1.97
- Stars
- 2
- Last push
- 2026-09-08T04:18:41Z
- Repository state
- ativo
- Language
- JavaScript
- License
- BSD-2-Clause
- Added
- 2026-08-29 03:02:38
- Updated
- 2026-08-29 03:02:38
- Origin id
io.github.coo1white/cool-workflow
README
<div align="center"> <img src="plugins/cool-workflow/project/docs/assets/cw-hero.png" alt="Cool Workflow hero image: the CW name over a line reading ask, plan, dispatch, verify, report — the stages of a saved, cited run." width="100%"> ### Get a saved report from your AI agent, with every claim tied to a line of code — not a chat answer you lose. [](https://github.com/coo1white/cool-workflow/actions/workflows/ci.yml) [](https://www.npmjs.com/package/cool-workflow) [](https://www.npmjs.com/package/cool-workflow) [](https://www.npmjs.com/package/cool-workflow) [](https://github.com/coo1white/cool-workflow/tags) [](LICENSE) </div> ## What is this? Cool 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: - **It plans the work.** Your question becomes a set of small tasks. - **Your agent does the work.** CW never runs a model itself — your own agent reads and thinks. - **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. > **The model is fuel. CW is the black-box recorder, the dashboard, and the gearbox — never the engine.** > It never calls a model API, never holds your keys, and never uploads your code. ## Install ```bash npm install -g cool-workflow ``` <details> <summary>Or install with <b>Homebrew</b></summary> ```bash brew tap coo1white/cool-workflow https://github.com/coo1white/cool-workflow brew install coo1white/cool-workflow/cool-workflow cw version ``` Upgrade later with `brew update && brew upgrade cool-workflow`. </details> **You need:** Node.js v18 or newer. No agent yet? Step 1 below still works — **CW never runs a model itself.** ## Works with your agent | Agent | Flag | Status | |---|---|---| | Claude Code | `-claude` | ✅ works | | Codex CLI | `-codex` | ✅ works | | Muse Code | `-muse` | ✅ works | | OpenCode | `-opencode` | ✅ works | | Gemini | `-gemini` | ✅ through opencode | | DeepSeek | `-deepseek` | ✅ through opencode or an HTTP endpoint | | Cursor | — | ⬜ not yet | | GitHub Copilot CLI | — | ⬜ not yet | | Aider | — | ⬜ not yet | | Qwen Code | — | ⬜ not yet | | Kimi | — | ⬜ not yet | Not sure what you have? `cw doctor` checks your setup and `cw fix` prints the commands that put it right. ## Quick Start ### 1 · See it work — 30 seconds, no agent needed ```bash cw demo tamper # → builds a real signed ledger, forges it three ways, catches all three offline # → VERDICT: tamper-evidence holds ✓ ``` ### 2 · Ask a question about your code — one command ```bash cw -q "How does auth work end-to-end here?" ``` CW 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`. ### 3 · Open the report The report opens in your browser by itself when the run ends. Later, open it again with: ```bash cw report --open ``` Want 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)). These three steps are the core path. Everything else is kept working, not grown. ## Can You Trust the Report? CW 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)**. ## Troubleshooting | Problem | Fix | |---|---| | No agent found | `cw doctor` — shows which agents are on your machine | | `status: blocked` | Set `CW_AGENT_COMMAND=builtin:claude` or pass `-claude` | | `claude: command not found` | Install Claude Code and run again | | Where is my report? | `<repo>/.cw/runs/<id>/report.md`, or run `cw report --open` | | `Missing required input: question` | Add `-q "<question>"` | | Run stopped before the end | `cw --resume --run <id>` takes it to the end (inside the project, or add `--repo <path>`) | | `... is not a git project` | Run it inside the project, or pass `--repo` | ## Learn more - **[User Guide](https://github.com/coo1white/cool-workflow/wiki/User-Guide)** — your first ten minutes - **[Why Cool Workflow](https://github.com/coo1white/cool-workflow/wiki/Mental-Model)** - **[How it works](https://github.com/coo1white/cool-workflow/wiki/Architecture)** - **[What you can run](https://github.com/coo1white/cool-workflow/wiki/Workflow-Apps)** - **[From your editor](https://github.com/coo1white/cool-workflow/wiki/MCP-And-Manifests#from-your-editor)** - **[Trust & Audit](https://github.com/coo1white/cool-workflow/wiki/Trust-And-Audit)** - **[Repo Map](https://github.com/coo1white/cool-workflow/wiki/Repo-Map)** - **[Wiki home](https://github.com/coo1white/cool-workflow/wiki)** CW dogfoods its own release: every cut runs `release-cut` against this repo. ## License BSD-2-Clause. Built by COOLWHITE LLC.