How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
humanlayerCLAUDE.mdhumanlayer/12-factor-agents/CLAUDE.md
This project uses: - **Language/Framework**: [Add your stack here] - **Build Tool**: [Add your build commands] - **Testing**: [Add your test commands] - **Architecture**: [Describe your project structure] ## Core Principles (All Personas) 1. **READ
Steady5 mentions in 2 weeks
No other project uses it yet
VoltAgentCLAUDE.mdVoltAgent/awesome-claude-code-subagents/CLAUDE.md
Language/framework experts (TypeScript, Python, etc.) 03-infrastructure/ # DevOps, cloud, Kubernetes, etc. 04-quality-security/ # Testing, security auditing, code review 05-data-ai/ # ML, data engineering, AI specialists 06-developer-experience
Surging3 mentions in 2 weeks
1 project uses a version of this
apifyCLAUDE.mdapify/crawlee/.claude/CLAUDE.md
PATH issues in this environment. ## Pre-Commit Checks Always run `pnpm tsc-check-tests` (or the project's type-check command) before committing any TypeScript changes. Never assume type safety
No other project uses it yet
anomalycoCLAUDE.mdanomalyco/sst/CLAUDE.md
build:cli` - **Run CLI locally**: `cd examples/ && go run ../../cmd/sst ` - **Go tests**: `bun run test:cli` - **Typecheck**: `bun run typecheck` - **Generate docs**: `bun run docs:generate` - **Run docs locally
Steady19 mentions in 2 weeks
1 project uses a version of this
activepiecesDeletes or force-pushesCLAUDE.mdactivepieces/activepieces/CLAUDE.md
isNil()`, `spreadIfDefined()`, `spreadIfNotUndefined()`, `ActivepiecesError({ code, params })`, `SeekPage `, `formErrors`, `BaseModelSchema`, `chunk()`, `partition()`, `unique()`, `omit()`, `sanitizeObjectForPostgresql()` ## Testing ```bash npm run test-unit # Vitest: engine + shared npm run test-api # API integration
Steady2 mentions in 2 weeks
No other project uses it yet
homebridgeCLAUDE.mdhomebridge/homebridge/CLAUDE.md
/bin/homebridge.js -D -P example-plugins/` (expects an `example-plugins/` checkout next to plugins under test). - `npm run lint` / `npm run lint:fix` — ESLint via `@antfu/eslint-config` (flat config in `eslint.config.js
No other project uses it yet
karpathyReads credentialsCLAUDE.mdkarpathy/llm-council/CLAUDE.md
ranking criteria (not just accuracy/insight) - Support for reasoning models (o1, etc.) with special handling ## Testing Notes Use `test_openrouter.py` to verify API connectivity and test different model identifiers before adding
No other project uses it yet
Dao-AILabCLAUDE.mdDao-AILab/flash-attention/CLAUDE.md
Dependencies: `nvidia-cutlass-dsl>=4.6.2`, `torch`, `einops`, `apache-tvm-ffi`, `quack-kernels>=0.5.3`. ## Running Tests ```bash pytest tests/cute/test_flash_attn.py pytest tests/cute/test_flash_attn.py -k "test_flash_attn_output" -x # single test pytest tests/cute/test_flash_attn_mla.py
No other project uses it yet
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
No other project uses it yet
apacheCLAUDE.mdapache/skywalking/CLAUDE.md
runtime │ ├── mqe-grammar/ # MQE (Metrics Query Engine) grammar │ ├── mqe-rt/ # MQE runtime │ ├── server-testing/ # Shared test utilities (DSL test framework) │ ├── analyzer/ # Log and trace analyzers │ ├── ai-pipeline/ # AI/ML pipeline components
No other project uses it yet
go-delveCLAUDE.mdgo-delve/delve/CLAUDE.md
debugging internals, DWARF format, OS-specific process control, and Go runtime internals. ## Build and Test Commands ### Building ```bash make build # Build dlv binary make install # Install dlv to system make
No other project uses it yet
zama-aiCLAUDE.mdzama-ai/fhevm/relayer-http/CLAUDE.md
config/config.yaml # example configuration: name, log, http, kms_aggregator ├── monitoring/ # dashboard, alert rules and their tests, runbook, measurement design (design.md), generated references (OBSERVABILITY.md) ├── dev/ # local development tooling: Makefile, host run, flow
No other project uses it yet
dataeasePipes a download into a shellCLAUDE.mddataease/dataease/CLAUDE.md
Dmaven.test.skip=true ``` ### Run ```bash # Direct JAR execution java -jar core/core-backend/target/CoreApplication.jar # Docker (recommended for testing) curl -sSL https://dataease.oss-cn-hangzhou.aliyuncs.com/quick_start_v2.sh | bash # Default credentials: admin / DataEase@123456 # Local installer cd installer && /bin/bash
No other project uses it yet
CymChadCLAUDE.mdCymChad/BaseRecyclerViewAdapterHelper/CLAUDE.md
/gradlew :app:assembleDebug # build the demo APK ./gradlew clean ``` There is **no test source set** — there are no unit or instrumented tests in either module. Verify changes by compiling and/or
No other project uses it yet
plotlyCLAUDE.mdplotly/dash/CLAUDE.md
covers what you're touching, don't read them all up front: - `COMMANDS.md` - build, test, lint commands - `ARCHITECTURE.md` - backend, callbacks, pages, background callbacks, stores, async, security - `RENDERER.md` - frontend, crawlLayout, Redux
No other project uses it yet
getpaseoCLAUDE.mdgetpaseo/paseo/CLAUDE.md
teardown invariants, and Parcel comparison | | [docs/testing.md](docs/testing.md) | TDD workflow, determinism, real dependencies over mocks, test organization | | [docs/qa.md](docs/qa.md) | QA evidence bar for pull requests — platform matrix, version drift, performance
Steady14 mentions in 2 weeks
No other project uses it yet
quiiCLAUDE.mdquii/learn-go-with-tests/CLAUDE.md
Learn Go with Tests — writing guide This is Chris James's ("quii") book. When drafting or editing chapter prose, match his voice, not generic technical-writing tone. This file
No other project uses it yet
SuperClaude-OrgCLAUDE.mdSuperClaude-Org/SuperClaude_Framework/CLAUDE.md
directly. ### Required Commands ```bash # All Python operations must use UV uv run pytest # Run tests uv run pytest tests/pm_agent/ # Run specific tests uv pip install package # Install dependencies
No other project uses it yet
beekeeper-studioReads credentialsCLAUDE.mdbeekeeper-studio/beekeeper-studio/CLAUDE.md
Vuex for state management - **Desktop**: Electron 31.7.3 - **Build**: ESBuild (main process), Vite (renderer process) - **Testing**: Vitest for unit and integration tests (see `apps/studio/tests/VITEST_MIGRATION.md`); Playwright for e2e. **All new tests must
Steady4 mentions in 2 weeks
No other project uses it yet
jhao104CLAUDE.mdjhao104/proxy_pool/CLAUDE.md
tests/integration/ -m integration` - 运行全部测试：`pytest` - 查看覆盖率：`pytest --cov=. --cov-report=term-missing` ## 测试 ### 目录结构 ``` tests/ ├── conftest.py # 共享 fixtures（app、client、fake_redis、proxy_obj、reset_singleton） ├── unit/ # 纯逻辑，零外部依赖 │ ├── test_proxy.py
No other project uses it yet
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.
