CLAUDE.md examples from real projects

How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.

Best matches · from page 21Worked for most · soon

NeoLabHQCLAUDE.md

context-engineering-kit

NeoLabHQ/context-engineering-kit/CLAUDE.md

plugins` and `just sync-plugins-to-docs` commands. Do not update both manually. - Test plugins with Claude Code before committing using `plugins/customaize-agent:test-prompt` and `plugins/customaize-agent:test-skill` commands. ### When

1.5k6mo agoDiscuss

dvdsglCLAUDE.md

claude-canvas / canvas

dvdsgl/claude-canvas/canvas/CLAUDE.md

Canvas Plugin Development Use Bun for all development: - `bun run src/cli.ts` - Run CLI - `bun test` - Run tests - `bun install` - Install dependencies ## Structure ``` canvas/ ├── src/ # TypeScript source code │ ├── cli.ts # CLI entry

1.5k9mo agoDiscuss

dvdsglCLAUDE.md

claude-canvas

dvdsgl/claude-canvas/CLAUDE.md

Use Bun instead of Node.js, npm, pnpm, or vite.

1.5k9mo agoReads credentialsDiscuss

869413421CLAUDE.md

ai-moive-studio

869413421/ai-moive-studio/CLAUDE.md

开发服务器 # 构建 npm run build # 生产构建 npm run preview # 预览构建结果 # 测试 npm run test:e2e # E2E测试 npm run test:e2e:ui # E2E测试UI npm run test:e2e:debug # E2E调试模式 # 代码质量

1.5k10mo agoReads credentialsDiscuss

hyhmrrightCLAUDE.md

brooks-lint

hyhmrright/brooks-lint/CLAUDE.md

software engineering books. Six independent skills under `skills/` (PR Review, Architecture Audit, Tech Debt, Test Quality, Health Dashboard, Full Sweep) each produce findings in the Iron Law form: **Symptom → Source

1.5k11d agoReads credentialsDiscuss

Open-Source-LegalCLAUDE.md

OpenContracts

Open-Source-Legal/OpenContracts/CLAUDE.md

machine learning models. ## Baseline Commit Rules 1. Always ensure all affected (or new) tests pass - backend tests suite should only be run in its entirety for good reason

1.5k12mo agoDiscuss

umputunCLAUDE.md

ralphex

umputun/ralphex/CLAUDE.md

Claude Code integration commands. ## Build Commands ```bash make build # build binary to .bin/ralphex make test # run tests with coverage make lint # run golangci-lint make fmt # format code ``` ### Updating Dependencies

1.5k42d agoReads credentialsDiscuss

yigitkonurCLAUDE.md

cli-continues

yigitkonur/cli-continues/CLAUDE.md

TypeScript compile (tsc) → dist/ pnpm run dev # Run with tsx (no build step) pnpm test # Run unit tests (vitest) pnpm run test:watch # Watch mode pnpm run link # Build + pnpm

1.5k6mo agoDiscuss

ghostwrightCLAUDE.md

phantom

ghostwright/phantom/CLAUDE.md

exposes all capabilities as an MCP server. 30,000+ lines of TypeScript, 1,819 tests, v0.20.2. Apache 2.0, repo at ghostwright/phantom. ## Tech Stack | Layer | Technology | |-------|-----------| | Runtime | Bun (TypeScript-native, built

1.5k6mo agoReads credentialsDiscuss

win4rCLAUDE.md

ClawTeam-OpenClaw

win4r/ClawTeam-OpenClaw/CLAUDE.md

deps: pytest, ruff pip install -e ".[p2p]" # optional ZeroMQ P2P transport # Lint + test — same commands CI runs (.github/workflows/ci.yml) ruff check clawteam/ tests/ pytest tests/ # full suite pytest tests/test_spawn_backends.py

1.4k6mo agoDiscuss

daymadeCLAUDE.md

claude-code-skills

daymade/claude-code-skills/CLAUDE.md

budgets for blocking remediation loops whose capped exit is explicitly blocked, unshipped, or pending. Test advisory liveness across later fully-due windows, and leave current thresholds in the owning implementation

1.4k6mo agoPipes a download into a shellDiscuss

StripeCLAUDE.md

stripe-react-native

stripe/stripe-react-native/CLAUDE.md

CLAUDE.md See CONTRIBUTING.md for development workflow, setup, testing, and commit conventions. ## Verification After changes, run relevant tests before committing: - `yarn test` (TypeScript unit tests) - `yarn test:unit:ios` / `yarn test

1.4k15d agoDiscuss

plugin87CLAUDE.md

ux-ui-agent-skills

plugin87/ux-ui-agent-skills/CLAUDE.md

1.4k38d agoDiscuss

JetBrainsCLAUDE.md

compose-hot-reload

JetBrains/compose-hot-reload/CLAUDE.md

source project enabling instant UI code changes without restarting a Compose Multiplatform application. ## Build & Test ```bash # Build ./gradlew build # Run all tests ./gradlew check # Run a sample ./gradlew :samples:counter

1.4k4mo agoDiscuss

JwuthriCLAUDE.md

Tracely-ai

Jwuthri/Tracely-ai/CLAUDE.md

repository. Tracely is trace-native CI/CD for AI agents: **production trace → failure detection → regression test → CI/CD gate**. The trace is the source of truth; evals, clusters, cases, gates and trends

1.4k2mo agoReads credentialsDiscuss

yohey-wCLAUDE.md

multi-agent-shogun

yohey-w/multi-agent-shogun/CLAUDE.md

Claude Code + tmux multi-agent parallel dev platform with sengoku military hierarchy

1.4k4mo agoPipes a download into a shellDiscuss

CloudAI-XCLAUDE.md

claude-workflow-v2

CloudAI-X/claude-workflow-v2/CLAUDE.md

workflow document. Update frequently with new learnings. ## Quick Reference - **Plugin validation**: `claude plugin validate` - **Test locally**: `claude --plugin-dir ./` - **Formatting**: Prettier for MD/JSON, Black for Python ## Development Workflow ### Making Changes

1.4k9mo agoDiscuss

Prismer-AICLAUDE.md

PrismerCloud

Prismer-AI/PrismerCloud/CLAUDE.md

dependency of `@prismer/sdk`. Go module paths: `github.com/nicepkg/aip-sdk-go` (AIP) vs `github.com/Prismer-AI/PrismerCloud/sdk/prismer-cloud/golang` (Cloud). ## Build / Test / Release ```bash sdk/build/test.sh --scope aip|prismer-cloud|all # build/test/verify gates sdk/build/pack.sh --scope all --clean sdk/build/release.sh

1.4k6mo agoReads credentialsDiscuss

tigerless-labsCLAUDE.md

agent-memory

tigerless-labs/agent-memory/CLAUDE.md

roadmap. **Keep this current in real time** (see rule below). - **[docs/testing.md](docs/testing.md)** — test conventions and the per-file test map. - **[docs/experiments.md](docs/experiments.md)** — experiment protocol: what counts as a result, what

1.4k29d agoDeletes or force-pushesDiscuss

nrslibCLAUDE.md

takt

nrslib/takt/CLAUDE.md

ESLint on `src/`. `no-explicit-any` is error; unused vars must be prefixed `_`. | | `npm test` | Fast unit gate: type-contracts tsc, the test type-check (`tsconfig.tests.json`), then an adaptive number

1.4k16d agoReads credentialsDiscuss

CLAUDE.md vs AGENTS.md

About CLAUDE.md

What is CLAUDE.md?

A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.

Where does it go?

At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.

What should it contain?

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.md or AGENTS.md?

Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.