How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
CannerCLAUDE.mdCanner/WrenAI/.claude/CLAUDE.md
Development Commands ### core/wren-core (Rust) ```bash cd core/wren-core cargo check --all-targets # compile check cargo test --lib --tests --bins # tests (set RUST_MIN_STACK=8388608) cargo fmt --all # format cargo clippy
AnthropicCLAUDE.mdanthropics/claude-quickstarts/CLAUDE.md
computer-use-demo:local` ### Testing & Code Quality - **Lint**: `ruff check .` - **Format**: `ruff format .` - **Typecheck**: `pyright` - **Run tests**: `pytest` - **Run single test**: `pytest tests/path_to_test.py::test_name -v` ### Code Style - **Python**: snake
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/assistant-ui/CLAUDE.md
noEmit` - `npm run lint` — eslint (the copy-in `components/` are ignored on purpose) - `npm test` — the reducer's golden-turn test; run it whenever the event mapping changes ## Conventions - Name
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/copilot-kit-ag-ui/CLAUDE.md
serves `web/dist` if present. - `npm run typecheck` covers both workspaces. There are no tests. Verify changes by running the app. ## Design notes - `package.json` pins one `rxjs` version via `overrides
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/daily-brief/CLAUDE.md
environment.yaml`'s allowlist does not apply to them. 5. **Keep the deployment paused while testing** (`agents/setup.sh` pauses it on creation; manual runs work while paused). `scripts/reset-state.sh` empties the state store
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/self-hosted-sandboxes/CLAUDE.md
runbook: setup, deploy, register the `session.status_run_started` webhook in the Console, test. Their environment key and webhook secret go in the provider's own secret store, never
AnthropicCLAUDE.mdanthropics/claude-quickstarts/managed-agents/sentry/CLAUDE.md
user the reason before reaching for `--force`. Schedule with `uv run python deploy.py`. Smoke-test with `uv run python run_now.py
ag-ui-protocolCLAUDE.mdag-ui-protocol/ag-ui/CLAUDE.md
mode pnpm dev # Run linting pnpm lint # Run type checking pnpm check-types # Run tests pnpm test # Format code pnpm format # Clean build artifacts pnpm clean # Full clean build pnpm
img2threejsCLAUDE.mdimg2threejs/img2threejs/CLAUDE.md
explicitly planned. - When changing schema, gates, generators, or review behavior, add or update focused tests. - Keep `SKILL.md`, `README.md`, `CHANGELOG.md`, and `ROADMAP.md` consistent when release-facing behavior changes. - Reference the companion
chenhg5CLAUDE.mdchenhg5/cc-connect/CLAUDE.md
exceeds ~80 lines - Naming: `New()` for constructors, `Get/Set` for accessors, avoid stuttering (`feishu.FeishuPlatform` → `feishu.Platform`) ## Testing ### Requirements - All new features must include unit tests - All bug fixes should include a regression
open-metadataCLAUDE.mdopen-metadata/OpenMetadata/CLAUDE.md
request/ingestion/search paths, the invariants that hold); read [DEVELOPER.md](DEVELOPER.md) for **how to build, test, and add an entity or connector** (deep dives + end-to-end checklists). Consult [docs/index.md](docs/index.md
MicrosoftCLAUDE.mdmicrosoft/playwright-python/CLAUDE.md
Lines that no longer apply must be removed. - `tests/async/`, `tests/sync/` — pytest suites. Most new tests are added to the async file with a sync mirror. - `DRIVER_VERSION` — the single source
yusufkaraaslanCLAUDE.mdyusufkaraaslan/Skill_Seekers/CLAUDE.md
phases done; remaining cosmetic items listed there). ## Essential Commands ```bash # REQUIRED before running tests or CLI (src/ layout) pip install -e . # Run all tests (NEVER skip - all must pass before
NVIDIACLAUDE.mdNVIDIA/TensorRT-LLM/agent-flow/CLAUDE.md
command to make sure that there are no style issue. * Always add tests when adding new features, and always make sure that all test cases can pass before committing
walkinglabsCLAUDE.mdwalkinglabs/learn-harness-engineering/CLAUDE.md
Electron (via scripts/dev.js) npm run check # Type-check both tsconfig.json and tsconfig.node.json npm run test # Vitest run (single run) npm run test:watch # Vitest watch mode ``` ## Repository Structure - `docs/` — VitePress
CoplayDevCLAUDE.mdCoplayDev/unity-mcp/CLAUDE.md
enables AI-driven game development workflows - creating GameObjects, editing scripts, managing assets, running tests, and more. ## Architecture ```text AI Assistant (Claude/Cursor) ↓ MCP Protocol (stdio/HTTP) Python Server (Server/src/) ↓ WebSocket + HTTP Unity
e2b-devCLAUDE.mde2b-dev/E2B/CLAUDE.md
make codegen`, which re-fetches them before generating. Create or update tests covering affected codepaths and run them using `pnpm run test`. Generate a changeset with `pnpm changeset
coleam00CLAUDE.mdcoleam00/context-engineering-intro/claude-code-full-guide/CLAUDE.md
pyproject.toml - **Use venv_linux** (the virtual environment) whenever executing Python commands, including for unit tests. ### Project Architecture Follow strict vertical slice architecture with tests living next to the code they
coleam00CLAUDE.mdcoleam00/context-engineering-intro/CLAUDE.md
PLANNING.md`. - **Use venv_linux** (the virtual environment) whenever executing Python commands, including for unit tests. ### 🧱 Code Structure & Modularity - **Never create a file longer than 500 lines of code
nanobrowserCLAUDE.mdnanobrowser/nanobrowser/CLAUDE.md
checking - `pnpm lint` - Run ESLint with auto-fix - `pnpm prettier` - Format code with Prettier **Testing**: - `pnpm e2e` - Run end-to-end tests (builds and zips first) - `pnpm zip` - Create extension
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.
