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 14Worked for most · soon

rpamisCLAUDE.md

comet / eval

rpamis/comet/eval/CLAUDE.md

Shared Python runner, Docker helpers, loaders, validators local/ # Local suite: task corpus, treatments, skills, tests, logs langsmith/ # LangSmith suite entrypoint and logs ``` The LangSmith suite intentionally reuses `local/tasks`, `local/treatments

3.1k10d agoReads credentialsDiscuss

stravuCLAUDE.md

crystal

stravu/crystal/CLAUDE.md

arm64 # Build for macOS (Apple Silicon only) pnpm build:linux # Build for Linux ``` ### Testing ```bash pnpm test # Run Playwright tests pnpm test:ui # Run tests with Playwright UI pnpm test

3.1k12mo agoDiscuss

Chachamaru127CLAUDE.md

claude-code-harness

Chachamaru127/claude-code-harness/CLAUDE.md

Development Rules ### Commit Messages Follow [Conventional Commits](https://www.conventionalcommits.org/): `feat:` / `fix:` / `docs:` / `refactor:` / `test:` / `chore:` ### Version Management Keep all version surfaces in sync via `./scripts/sync-version.sh` (the script

3.1k48d agoDeletes or force-pushesDiscuss

MaxMiksaCLAUDE.md

Auto-Company

MaxMiksa/Auto-Company/CLAUDE.md

3.1k13mo agoReads credentialsDiscuss

blazickjpCLAUDE.md

arxiv-mcp-server

blazickjp/arxiv-mcp-server/CLAUDE.md

Streamable HTTP. ## Setup and validation Use the locked uv environment: ```bash uv sync --extra test --extra dev uv run black --check . uv run pytest ``` Apply formatting with: ```bash

3.1k2mo agoReads credentialsDiscuss

SynkraAICLAUDE.md

aiox-core

SynkraAI/aiox-core/.claude/CLAUDE.md

Development stories (active/, completed/) ├── packages/ # Shared packages ├── pro/ # Pro submodule (proprietary) ├── squads/ # Squad expansions └── tests/ # Testes ``` --- ## Framework vs Project Boundary O AIOX usa um modelo de 4 camadas

3.1k4mo agoDiscuss

Google CloudCLAUDE.md

professional-services / agent-eval

GoogleCloudPlatform/professional-services/tools/agent-eval/CLAUDE.md

3.1k31d agoReads credentialsDiscuss

jakubkrehelCLAUDE.md

make-interfaces-feel-better

jakubkrehel/make-interfaces-feel-better/CLAUDE.md

skills add jakubkrehel/make-interfaces-feel-better`. It is documentation-only; there is no build, lint, or test tooling. ## Structure The skill lives in `skills/make-interfaces-feel-better/`: - `SKILL.md` is the entry point. Its YAML frontmatter contains

3.1k2mo agoDiscuss

coderCLAUDE.md

claudecode.nvim

coder/claudecode.nvim/CLAUDE.md

official IDE extensions. Built with pure Lua and zero dependencies. ## Common Development Commands ### Testing - `mise run test` - Run all tests using busted with coverage - `busted tests/unit/specific_spec.lua` - Run specific test file

3k4mo agoDiscuss

allenpeng0705CLAUDE.md

EnvoyMesh

allenpeng0705/EnvoyMesh/CLAUDE.md

Search, Profile, Settings, etc.) │ │ ├── src/context/ # NodeStateContext (shared state, event-driven) │ │ ├── src/lib/ # storage.ts, display.ts, direct-call-client.ts │ │ └── test/ # Component + context tests (vitest + testing-library) │ ├── envoygo/ # ★ PRODUCT mobile app — Flutter thin client (pair

3k4mo agoReads credentialsDiscuss

MicrosoftCLAUDE.md

playwright-dotnet

microsoft/playwright-dotnet/CLAUDE.md

driver (needs Node.js/npm on PATH) dotnet build ./src # build the entire solution ``` ## Running tests Follow `.github/workflows/tests.yml` for the canonical sequence. ```bash # Install browsers (pick one: chromium, firefox, webkit) pwsh

3k3mo agoDiscuss

rlaopeCLAUDE.md

oh-my-hermes

rlaope/oh-my-hermes/CLAUDE.md

NETWORK_CLIENT_BRIDGES`. Third-party Jev plugins are still never called. ## Build & Test ```sh PYTHONPATH=tests uv run python -m unittest discover -s tests -v # full suite PYTHONPATH=tests

3k20d agoDeletes or force-pushesDiscuss

michaelshimelesCLAUDE.md

ralphy

michaelshimeles/ralphy/CLAUDE.md

Boundaries - Never Modify - PRD files during execution - `.ralphy/progress.txt` - `.ralphy-worktrees` - `.ralphy-sandboxes` - `*.lock` files ### Testing - Write tests for new features - Run tests before committing: `bun test` - Ensure linting passes

3k8mo agoDiscuss

ax-llmCLAUDE.md

ax

ax-llm/ax/docs/CLAUDE.md

commands from the root. ## Model Selection When you name a model anywhere (examples, defaults, tests), use a **current** generation — newer beats biggest. The provider enums are the source of truth

2.9k6d agoReads credentialsDiscuss

AnthropicCLAUDE.md

commerce-agents

anthropics/commerce-agents/CLAUDE.md

docs/`: `safety.md`, `backends.md`, `deployment.md`. `scripts/`: install, demo, smoke, screenshots, check, deploy, verify. - `tests/`: the suites that span packages (both roles on all three paths); each package keeps its own `tests

2.9k30d agoDiscuss

VRSENCLAUDE.md

OpenSwarm

VRSEN/OpenSwarm/CLAUDE.md

custom APIs - **instructions-writer**: Write optimized instructions using prompt engineering best practices - **qa-tester**: Test agents with actual interactions and tool validation ## Orchestration Responsibilities 1. **User Clarification**: Ask questions

2.9k6mo agoReads credentialsDiscuss

aaron-he-zhuCLAUDE.md

aaron-marketing-skills

aaron-he-zhu/aaron-marketing-skills/CLAUDE.md

pitch-narrative-builder` · `narrative-enablement-kit` · `proof-point-packager`; **Evaluate:** `narrative-quality-auditor` · `message-test-designer` · `narrative-resonance-monitor` · `narrative-drift-monitor` - **SEO/GEO · CORE-EEAT+CITE (16):** **Survey:** `keyword-research

2.8k21d agoDiscuss

kaitrannttCLAUDE.md

ccs

kaitranntt/ccs/CLAUDE.md

only when explicitly needed. - Never touch the user's real `~/.ccs/` or `~/.claude/` in tests. Use `getCcsDir()` from `src/utils/config-manager.ts`; it respects `CCS_HOME`. - Do not commit directly

2.8k10mo agoDiscuss

tradermontyCLAUDE.md

claude-trading-skills

tradermonty/claude-trading-skills/CLAUDE.md

files are stored in `skill-packages/` and should be regenerated after any skill modifications. ### Testing Skills Skills are tested by invoking them in Claude Code conversations: 1. Copy skill folder

2.8k2mo agoReads credentialsDiscuss

overwirehqCLAUDE.md

claude-code-telegram

overwirehq/claude-code-telegram/CLAUDE.md

only make run # Run the bot make run-debug # Run with debug logging make test # Run tests with coverage make lint # Black + isort + flake8 + mypy make format # Auto-format with

2.8k19d 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.