Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
Signed, cited, replayable workflows for Claude, Codex, Gemini, DeepSeek, and other agents.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"cool-workflow": {
"command": "npx",
"args": [
"-y",
"cool-workflow"
]
}
}
}ターミナルでこれを実行します
claude mcp add cool-workflow -- npx -y cool-workflowプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"cool-workflow": {
"command": "npx",
"args": [
"-y",
"cool-workflow"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"cool-workflow": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"cool-workflow"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月6日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント coo1white で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.1.97)がレジストリに届いたのは4 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, Reelsaw
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Drive a self-hosted Reelsaw: turn long videos into vertical clips, edit, re-render and export them.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
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:
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.
You need two things, and one more for real runs:
wsl --install in PowerShell, then open "Ubuntu" from the Start menu) and type every command below in that Ubuntu window.node -v. If it is missing or older, get it from nodejs.org (take the LTS one).npm install -g cool-workflow
cw version
cw version prints the version number when the install worked.
Install trouble?
| What you see | What to do |
|---|---|
EACCES: permission denied | Do not use sudo. Put Node in your home folder with nvm, then run the install again. |
cw: command not found | Close the terminal and open a new one. If it is still not found, npm prefix -g gives the folder; its bin folder needs to be on your PATH. |
Unsupported engine or a Node error | Your Node is older than v22.13: update it (node -v to check). |
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 v22.13 or newer. No agent yet? Step 1 below still works — CW never runs a model itself.
Runs on: Linux, macOS and Windows through WSL. Native Windows is not yet supported: CI runs it to measure what still fails, and that work is going on.
| Agent | Flag | Status | Get it |
|---|---|---|---|
| Claude Code | -claude | ✅ works | install |
| Codex CLI | -codex | ✅ works | install |
| Muse Code | -muse | ✅ works | — |
| OpenCode | -opencode | ✅ works | install |
| Gemini | -gemini | ✅ through opencode | install OpenCode |
| DeepSeek | -deepseek | ✅ through opencode or an HTTP endpoint | install OpenCode |
| GitHub Copilot CLI | -copilot | 🧪 beta | install |
| Antigravity | -antigravity | 🧪 beta | install |
| Grok | -grok | ✅ works (add -grok) | install |
| Cursor | — | ⬜ not yet | |
| Aider | — | ⬜ not yet | |
| Qwen Code | — | ⬜ not yet | |
| Kimi | — | ⬜ not yet |
🧪 beta: CW has a wrapper and an offline test for it, but no real login has passed cw doctor --conformance yet, and cw never picks it by itself: add its flag.
Log in to your agent once on its own (run it, for one claude, and follow its steps) before you use it with CW: CW uses your agent as it is set up, and never asks for your keys.
Not sure what you have? cw doctor checks your setup and cw fix prints the commands that put it right.
cw demo tamper
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.
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:
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).
An agent that says "all tests pass" has only said it. Run the tests through CW and keep a receipt:
cw check -- npm test
CW runs your command (never a model) and saves what happened: the commit, the exit code, a digest of the output. A result that cites receipt:rc-… is checked again before it counts: a failed run, a missing receipt, or code that changed since the run is turned down, with the one command to fix it. cw check list shows your receipts.
These steps are the core path. Everything else is kept working, not grown.
| Word | What it means |
|---|---|
| agent | The AI coding tool on your machine (Claude Code, Codex, …) that does the reading and thinking. CW gives it small tasks. |
| run | One question, from start to report. Each run has an id, and its files are kept in .cw/runs/ / in your project. |
| report | The answer, with the evidence for each claim (file.ts:42). Kept as report.md, and opened in your browser. |
| evidence | A pointer to a real line of code. A claim without it is not let through. |
| receipt | A record, from cw check, that a command (for one, your tests) truly ran and how it ended. |
| resume | Going on with a run that stopped: cw --resume --run . |
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).
| 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? | /.cw/runs/ /report.md, or run cw report --open |
Missing required input: question | Add -q " " |
| Run stopped before the end | Fix the cause, then cw --resume --run takes it to the end; a worker that stopped gets fresh tries (inside the project, or add --repo ) |
... is not a git project | Run it inside the project, or pass --repo |
Run was made for | The run belongs to another folder (a copied or moved repo): pass --repo , or move it with cw run export and cw run import |
CW dogfoods its own release: every cut runs release-cut against this repo.
BSD-2-Clause. Built by COOLWHITE LLC.