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 10Worked for most · soon

fengshao1227CLAUDE.md

ccg-workflow / dsh-ccg

fengshao1227/ccg-workflow/dsh-ccg/CLAUDE.md

dependency and a `dsh.profile.bundles` entry — `pnpm add` writes only the first. **Version**: 0.4.7 · **Tests**: 116 · **Runtime deps**: none · **Build step**: none --- ## What it is Seven role tools (`ccg_analyze

5.9k7mo agoDiscuss

fengshao1227CLAUDE.md

ccg-workflow / src

fengshao1227/ccg-workflow/src/CLAUDE.md

pnpm typecheck # 构建（unbuild → dist/cli.mjs + dist/index.mjs，inline 所有依赖） pnpm build # 测试（204 用例） pnpm test # 发布 —— 不要本地 npm publish；推 tag 由 GitHub Actions 经 OIDC 发布

5.9k7mo agoReads credentialsDiscuss

fengshao1227CLAUDE.md

ccg-workflow / templates

fengshao1227/ccg-workflow/templates/CLAUDE.md

/ccg:debug` | 多模型调试：后端诊断 + 前端诊断，交叉验证定位问题 | | `optimize.md` | `/ccg:optimize` | 多模型性能优化：后端优化 + 前端优化 | | `test.md` | `/ccg:test` | 多模型测试生成：智能路由后端测试 / 前端测试 | ### 代码质量（2 个） | 命令文件 | slash command | 描述 | |----------|--------------|------| | `review.md` | `/ccg:review` | 多模型代码审查：无参数时自动审查

5.9k7mo agoDiscuss

epoko77-aiCLAUDE.md

im-not-ai

epoko77-ai/im-not-ai/CLAUDE.md

문자 변경률 게이트 │ ├── build_quick_rules.py # taxonomy quick 메타 → quick-rules.md 빌드 (ID 드리프트 차단) │ ├── build_social_preview_v2.py │ └── make_thumbnail.py ├── tests/ # pytest — metrics 단위 + 청킹 + 빌드 sync + golden 픽스처 │ ├── test_metrics.py · test_metrics_v2.py · test_chunking.py · test_quick_rules_build.py · test_sanitize.py │ └── golden/ # 윤문

5.8k8d agoDiscuss

VercelCLAUDE.md

streamdown / website

vercel/streamdown/apps/website/.claude/CLAUDE.md

prop instead of `React.forwardRef` **Solid/Svelte/Vue/Qwik:** - Use `class` and `for` attributes (not `className` or `htmlFor`) --- ## Testing - Write assertions inside `it()` or `test()` blocks - Avoid done callbacks in async tests - use async/await

5.7k14mo agoDiscuss

unicity-sphereCLAUDE.md

sphere-sdk

unicity-sphere/sphere-sdk/CLAUDE.md

docs-only changes exempt); squash-merge after green CI (`.github/workflows/ci.yml`: verify:version + typecheck + typecheck:tests + lint + build + test:run on Node 22 and 24, plus a separate `test:mutation

5.4k7d agoReads credentialsDiscuss

breaking-brakeCLAUDE.md

cc-wf-studio

breaking-brake/cc-wf-studio/CLAUDE.md

issue per run) and `next-qa` (implementation — builds one per run) grow the automated test suite on the **`auto-qa`** branch (queue = Issues labeled `qa`, memory = `docs/qa-log.md`). `auto-qa` branches

5.4k3mo agoDiscuss

CloudflareCLAUDE.md

vibesdk

cloudflare/vibesdk/CLAUDE.md

Register it in `ThinkAgent.getTools()` 4. Update the relevant prompt or skill 5. Add focused tests **Add API Endpoint:** 1. Define types in `src/api-types.ts` 2. Add to `src/lib/api-client.ts` 3. Create service

5.4k2mo agoDiscuss

weave-osCLAUDE.md

router

weave-os/router/CLAUDE.md

task/PR/caller, no multi-paragraph. If removing wouldn't confuse, don't write. - **Non-tautological tests** — every test must assert behavior that breaks if prod code deleted. ## Layer model and import

5.4k16d agoDiscuss

SenteLabsAICLAUDE.md

OpenExecutive

SenteLabsAI/OpenExecutive/CLAUDE.md

pipeline ``` ## Key Commands ```bash make dev # Start FastAPI (port 8000) + Next.js (port 3000) make test # Run pytest make lint # ruff check + mypy make check # everything CI checks: lint, unit tests

5.3k5d agoReads credentialsDiscuss

awarexoneCLAUDE.md

Agentic-Bug-Hunter

awarexone/Agentic-Bug-Hunter/CLAUDE.md

/token-scan`, etc.) | Skill | Domain | |---|---| | `skills/bug-bounty/` | Master workflow — recon to report, all vuln classes, LLM testing, chains | | `skills/bb-methodology/` | **Hunting mindset + 5-phase non-linear workflow + tool routing + session discipline** | | `skills/web2-recon/` | Subdomain

5.2k4mo agoDiscuss

VercelCLAUDE.md

examples / cms-sanity-graphql-fragments

vercel/examples/starter/cms-sanity-graphql-fragments/CLAUDE.md

Sanity) - **Generate Types**: `npm run schema:generate` (generate GraphQL types from Sanity schema) - **No test command configured** - check with user if tests are needed ## Code Style - **Formatter**: Biome with

5.2k8mo agoDiscuss

SaladDayCLAUDE.md

cc-switch-cli

SaladDay/cc-switch-cli/CLAUDE.md

Rust code cargo fmt --check # Check formatting, matching CI cargo clippy # Run lints cargo test # Run all tests cargo test provider_switch # Run tests whose names contain provider_switch cargo

5.1k18d agoReads credentialsDiscuss

entireioCLAUDE.md

cli

entireio/cli/CLAUDE.md

persistent checkpoint storage. - `cmd/entire/cli/session/`: session state shared across worktrees. - `cmd/entire/cli/integration_test/`: simulated-hook integration tests. - `e2e/`: real-agent tests and deterministic Vogon canary. - `internal/entireclient/`: API clients, authentication, and user directories

5.1k3mo agoDiscuss

clideyCLAUDE.md

whodb

clidey/whodb/CLAUDE.md

risky, architectural, or ambiguous changes. - Use subagents only for bounded sidecar work: exploration, review, test triage, or documentation lookup. - Prefer separate worktrees for parallel implementation sessions. - When a task touches

5k7d agoDiscuss

PeonPingCLAUDE.md

peon-ping

PeonPing/peon-ping/CLAUDE.md

usage, sound packs, remote dev, mobile notifications), see [README.md](README.md). ## Commands ```bash # Run all tests (requires bats-core: brew install bats-core) bats tests/ # Run a single test file bats

5k6mo agoPipes a download into a shellDiscuss

RyanFitzgeraldCLAUDE.md

devportfolio

RyanFitzgerald/devportfolio/CLAUDE.md

site uses Tailwind CSS v4 with the Vite plugin configuration - No linting or testing framework is currently configured - All components are in `.astro` format (not React/Vue/etc) - The project uses

5k14mo agoDiscuss

NVIDIACLAUDE.md

Model-Optimizer / debugger

NVIDIA/Model-Optimizer/tools/debugger/CLAUDE.md

detected) | ModelOpt source, used as workdir | | `/hf-local` | HuggingFace model cache | ### Examples ```bash # Run PTQ test bash tools/debugger/client.sh run "bash hf_ptq/scripts/huggingface_example.sh" # Run pytest bash tools/debugger/client.sh run "python -m pytest tests/gpu

5k7d agoDiscuss

NVIDIACLAUDE.md

Model-Optimizer / launcher

NVIDIA/Model-Optimizer/tools/launcher/CLAUDE.md

Dump resolved config uv run launch.py --yaml examples/Qwen/Qwen3-8B/megatron_lm_ptq.yaml --to-yaml resolved.yaml # Run unit tests uv pip install pytest uv run python3 -m pytest tests/ -v ``` ## YAML Config Format The `--yaml

5k7d agoDiscuss

HS435116CLAUDE.md

rapid-code

HS435116/rapid-code/CLAUDE.md

atoms - `src/renderer/features/agents/main/active-chat.tsx` - Main chat component - `src/main/lib/trpc/routers/claude.ts` - Claude SDK integration ## Debugging First Install Issues When testing auth flows or behavior for new users, you need to simulate a fresh install: ```bash

13mo agoDeletes or force-pushesDiscuss

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.