使用单个AGENTS.md统一Claude Code、Cursor与Codex配置

your-repo/
├── AGENTS.md            # 规范源：命令、目录结构、规范、完成定义
├── CLAUDE.md            # "@AGENTS.md" + Claude专属注释
├── .claude/
│   ├── settings.json    # 权限与钩子
│   ├── agents/          # 子代理
│   └── skills/          # 按需加载的过程
├── .cursor/
│   ├── rules/           # .mdc规则，核心规则指向AGENTS.md
│   └── cli.json         # `agent` CLI的权限
├── .cursorignore
└── .codex/
    ├── config.toml      # 沙箱与审批默认值
    └── agents/          # 自定义代理

# CLAUDE.md
@AGENTS.md

# AGENTS.md

## Project snapshot
- What it is: <one sentence>
- Main language / runtime: <TypeScript 5, Node 22>
- Package manager: <pnpm>. Do not use any other package manager.
- Layout:
  - `apps/web/`: frontend
  - `apps/api/`: HTTP API (handlers in `apps/api/src/handlers/`)
  - `packages/db/`: schema + migrations

## Commands
- Install: `<pnpm install>`
- Unit tests (fast, run often): `<pnpm test>`
- Single test file: `<pnpm test -- path/to/file.test.ts>`
- Lint + types: `<pnpm lint && pnpm typecheck>`
- Build: `<pnpm build>`

## Conventions
- Named exports, no default exports.
- Errors: return `{ code, message }` objects from services; never throw raw strings.
- New code needs tests next to it (`*.test.ts`).

## Working agreement
1. Restate the task in one or two lines and list the files you expect to touch before editing.
2. Make the smallest change that solves the task. No drive-by refactors.
3. If requirements are ambiguous, stop and ask. Do not guess on behaviour.
4. Never commit secrets, tokens, or `.env*` files.
5. Do not run `git push`, `git reset --hard`, `git clean -fd`, force-pushes,
   or destructive DB commands unless explicitly asked.

## Definition of done
- [ ] Lint + types pass
- [ ] Tests pass (and a new test covers the change)
- [ ] Diff is limited to files related to the task
- [ ] Short summary: what changed, why, how it was verified, open risks

## Code Review Rules
- Flag any handler that reads request input without validation.
- Flag SQL built with string concatenation.

<!-- Keep this file under ~200 lines. HTML comments are stripped before Claude sees them. -->

@AGENTS.md

## Claude Code specifics
- Use plan mode before touching more than 3 files.
- For searches that would flood the context, delegate to a subagent
  and ask for a summary with file paths.
- Before calling a task done, run the checks in "Definition of done"
  and paste the command output summary.

## Things that went wrong before
- Do not "fix" failing tests by loosening assertions or adding `.skip`.

---
description: "Core working agreement for every Agent chat in this repo"
alwaysApply: true
---

- Follow `AGENTS.md` at the repo root for commands, layout and definition of done.
- Before editing, list the files you plan to change. Keep the diff limited to the task.
- Never read, print, or edit `.env*`, `*.pem`, `*.key` or credential files.
- Finish every task with: what changed, how you verified it (exact commands), open risks.

approval_policy = "on-request"
sandbox_mode = "workspace-write"
web_search = "cached"

[agents]
max_concurrent_threads_per_session = 4