What is this?
Cool Workflow (cw) is a small command-line tool that turns your AI coding agent's chat answer β easy to lose, hard to check β 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 β 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 β never the engine.
It never calls a model API, never holds your keys, and never uploads your code.
Install
npm install -g cool-workflow
Or install with Homebrew
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.
You need: Node.js v18 or newer. No agent yet? Step 1 below still works β CW never runs a model itself.
Works with your agent
| Agent | Flag | Status |
|---|
| Claude Code | -claude | β
works |
| Codex CLI | -codex | β
works |
| Muse Code | -muse | β
works |
| OpenCode | -opencode | β
works |
| Gemini | -gemini | β
through opencode |
| DeepSeek | -deepseek | β
through opencode or an HTTP endpoint |
| Cursor | β | β¬ not yet |
| GitHub Copilot CLI | β | β¬ not yet |
| Aider | β | β¬ not yet |
| Qwen Code | β | β¬ not yet |
| Kimi | β | β¬ 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 Β· See it work β 30 seconds, no agent needed
2 Β· Ask a question about your code β one command
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.
A full review takes about 4 minutes on a real repo (14 workers; the Map and Assess stages run at the same time). One focused question? Add --fast: 6 workers in place of 14, the same cited answer for fewer agent calls.
3 Β· Open the report
The report opens in your browser by itself when the run ends. It starts with the answer, then the evidence behind it. Later, open it again with:
Want to see one first? A real run's Workbench and report, rebuilt on every push: coo1white.github.io/cool-workflow (the report is at /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 β it keeps the books. Your agent signs its findings (ed25519), and cw report verify-bundle checks β offline, with only the public key β 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 β not that nothing else was added, and not that none were left out. See the Trust Model.
Troubleshooting
| Problem | Fix |
|---|
| No agent found | cw doctor β 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 | Fix the cause, then cw --resume --run <id> takes it to the end; a worker that stopped gets fresh tries (inside the project, or add --repo <path>) |
... is not a git project | Run it inside the project, or pass --repo |
Learn more
CW dogfoods its own release: every cut runs release-cut against this repo.
License
BSD-2-Clause. Built by COOLWHITE LLC.