How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
grabCLAUDE.mdgrab/cursor-talk-to-figma-mcp/CLAUDE.md
built MCP server bun setup # Full setup (install + write .cursor/mcp.json + .mcp.json) ``` There is no test suite or linter configured. ## Architecture ### MCP Server (`src/talk_to_figma_mcp/server.ts`) The main server implementing the MCP protocol
OsmanticCLAUDE.mdOsmantic/ODS/CLAUDE.md
nvidia.json`, etc.), GPU database, LiteLLM config, hardware classes - **`extensions/services/dashboard-api/`** — Python FastAPI backend (with `routers/`, `tests/`) - **`extensions/services/dashboard/`** — React + Vite + Tailwind frontend (`src/`) - **`scripts/`** — operational scripts (health checks, model management, compose stack
deanpetersCLAUDE.mddeanpeters/Product-Manager-Skills/CLAUDE.md
questions: product + trigger → seven **transition questions** (scored) → pressure source (demand / supply-cost / capability) → extension test. Recommends extend, replace, retire, harvest, or **"nothing yet"**. [`product-lifecycle-plays`](skills/product-lifecycle-plays/SKILL.md) (Component) — PLC strategy
BlockRunAICLAUDE.mdBlockRunAI/ClawRouter/CLAUDE.md
install dependencies npm run build # compile with tsup npm run dev # watch mode npm test # run vitest npm run typecheck # type checking npm run lint # eslint npm run format # prettier
airweave-aiCLAUDE.mdairweave-ai/airweave/CLAUDE.md
Install dependencies poetry run uvicorn airweave.main:app --host 0.0.0.0 --port 8001 --reload # Dev server # Tests poetry run pytest tests/unit # Unit tests only poetry run pytest tests/integration # Integration tests poetry
op7418CLAUDE.mdop7418/CodePilot/CLAUDE.md
改动必须验证，但默认不要强制 CDP：** - 修改组件、样式、布局后，必须实际验证效果；优先选择最小、最稳定的验证方式，避免长时间占用浏览器自动化进程 - 默认顺序：代码审查 / targeted test → `npm run test` → `npm run test:smoke` 或 Playwright E2E → Browser Use 轻量截图与 console 检查 → Chrome
SentryCLAUDE.mdgetsentry/XcodeBuildMCP/CLAUDE.md
trace changed or reused helper contracts, including error and sentinel returns, through callers, consumers, tests, and operational configuration. - Verify standard quality commands include every changed path and exercise exact entry
czlonkowskiCLAUDE.mdczlonkowski/n8n-skills/CLAUDE.md
router skill (loaded by SessionStart hook) ├── hooks/ # Enforcement layer: hooks.json + SessionStart/PreToolUse/PostToolUse scripts ├── evaluations/ # Test scenarios for each skill ├── docs/ # Documentation ├── dist/ # Build output (gitignored — zips ship as GitHub Release assets
builderz-labsCLAUDE.mdbuilderz-labs/mission-control/CLAUDE.md
docker # full guided setup ``` Production hardening: `docker compose -f docker-compose.yml -f docker-compose.hardened.yml up -d` ## Tests ```bash pnpm test # unit tests (vitest) pnpm test:e2e # end-to-end (playwright) pnpm typecheck
jacob-bdCLAUDE.mdjacob-bd/gemini-notebook-mcp-cli/CLAUDE.md
notebook.google.com) via both a Model Context Protocol server and a comprehensive command-line interface. Tested with personal/free tier accounts. May work with Google Workspace accounts but has not been tested
Q00CLAUDE.mdQ00/ouroboros/CLAUDE.md
required to merge — reproduce them locally first: ```bash uv run ruff format src/ tests/ && uv run ruff check src/ tests/ --fix uv run mypy src/ouroboros uv run pytest ``` (`Ruff Lint
UfoMiaoCLAUDE.mdUfoMiao/zcf/CLAUDE.md
code quality. The architecture emphasizes robust error handling, user-friendly interfaces, and extensive testing coverage with advanced tool integration including CCR proxy, Cometix status line, and CCusage analytics. Version
UfoMiaoCLAUDE.mdUfoMiao/zcf/templates/CLAUDE.md
string, 'en': string } description: { 'zh-CN': string, 'en': string } template: string personality: string } ``` ## Testing and Quality ### Template Validation - **File**: `tests/templates/chinese-templates.test.ts` - **Coverage**: Template completeness and format validation - **Validation**: Markdown syntax
UfoMiaoCLAUDE.mdUfoMiao/zcf/tests/CLAUDE.md
Tests Module **Last Updated**: Mon Oct 27 19:39:26 CST 2025 [Root](../CLAUDE.md) > **tests** ## Module Responsibilities Test suite module providing comprehensive test coverage for the ZCF project, including unit
ChrisWilesCLAUDE.mdChrisWiles/claude-code-showcase/CLAUDE.md
configure Claude Code for your project. ## Quick Facts - **Stack**: React, TypeScript, Node.js - **Test Command**: `npm test` - **Lint Command**: `npm run lint` - **Build Command**: `npm run build` ## Key Directories - `src/components/` - React
ZSeven-WCLAUDE.mdZSeven-W/openpencil/CLAUDE.md
server (Rust):** `bash scripts/start-web-rust.sh` - **Build (Rust):** `cargo build --workspace --release` - **Run all tests (Rust):** `cargo test --workspace`; single crate: `cargo test -p ` - **Type check:** `cargo check --workspace`; wasm: `cargo check
ZSeven-WCLAUDE.mdZSeven-W/openpencil/crates/CLAUDE.md
plumbing, `jian-core` event types + taffy layout, `jian-scene` canonical render scene — `LayoutScene` + hit-test + path geometry, consumed by OP and any jian app); `vendor/casement` is the winit fork; `vendor/agent
ZSeven-WCLAUDE.mdZSeven-W/openpencil/packages/CLAUDE.md
ships its own wasm under `wasm/`. - Build: `tsup` (`bun run build` inside the package). Tests: `vitest`. ## op-web-sdk-react (`op-web-sdk-react/`) React 19 adapter
fengshao1227CLAUDE.mdfengshao1227/ccg-workflow/CLAUDE.md
v3.6.2) - ✨ **CCG 落地 DeepSeek Harness**：`dsh-ccg/` 进仓库并**随主包一起发**（`files` 加 7 条白名单，不含 test/）。七个角色委派工具各跑各的模型；一个角色挂多模型即成**模型群**（同一简报、独立作答、**答案在对话流里并排渲染**，不投票不平均）；`ccg_team` 把角色雇成**常驻队友**（跨轮次存活、独占文件、撞车直接拒绝、每次雇人先走
fengshao1227CLAUDE.mdfengshao1227/ccg-workflow/codeagent-wrapper/CLAUDE.md
并发调度 `executeConcurrentWithContext()`；拓扑排序 `topologicalSort()`；进程终止 `terminateCommand()` / `killProcessTree()`；并行输出报告 `generateFinalOutputWithMode()` | | `utils.go` | `resolveTimeout()`；输出提取辅助函数（coverage / files / tests / key output） | ### 日志层 | 文件 | 职责 | |------|------| | `logger.go` | 异步 Logger（buffered channel + 单 worker goroutine）；日志文件创建于 `os.TempDir
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
