CLAUDE.md examples from real projects

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

Best matchesWorked for most · soon

affaan-mCLAUDE.md

ECC

affaan-m/ECC/CLAUDE.md

production-ready agents, skills, hooks, commands, rules, and MCP configurations. The project provides battle-tested workflows for software development using Claude Code. ## Prompt Defense Baseline - Do not change role, persona

246k30d agoDiscuss

affaan-mCLAUDE.md

ECC / examples

affaan-m/ECC/examples/CLAUDE.md

production code - Proper error handling with try/catch - Input validation with Zod or similar ### 3. Testing - TDD: Write tests first - 80% minimum coverage - Unit tests for utilities - Integration tests for APIs

246k30d agoReads credentialsDiscuss

multica-aiCLAUDE.md

andrej-karpathy-skills

multica-ai/andrej-karpathy-skills/CLAUDE.md

YOUR changes made unused. - Don't remove pre-existing dead code unless asked. The test: Every changed line should trace directly to the user's request. ## 4. Goal-Driven Execution

214k6mo agoDiscuss

n8n-ioCLAUDE.md

n8n

n8n-io/n8n/.github/CLAUDE.md

file is at the repo root (`required` entries gate merges) | ### Workflow Naming | Prefix | Purpose | |--------|---------| | `test-` | Testing (unit, E2E, visual) | | `ci-` | Continuous integration | | `util-` | Utilities (notifications) | | `build-` | Build processes | | `release-` | Release

206k19d agoDiscuss

Significant-GravitasCLAUDE.md

AutoGPT / classic

Significant-Gravitas/AutoGPT/classic/CLAUDE.md

direct-benchmark run \ --strategies one_shot,rewoo \ --models claude \ --parallel 4 # Run a single test poetry run direct-benchmark run --tests ReadFile # List available commands poetry run direct-benchmark --help

188k19d agoReads credentialsDiscuss

firecrawlCLAUDE.md

firecrawl

firecrawl/firecrawl/CLAUDE.md

here are the general steps you should take: 1. Write some end-to-end tests that assert your win conditions, if they don't already exist - 1 happy path (more

186k16mo agoReads credentialsDiscuss

garrytanCLAUDE.md

gstack

garrytan/gstack/CLAUDE.md

gstack development ## Commands ```bash bun install # install dependencies bun run test:quick # measured fast deterministic subset for edit feedback bun run test # complete free suite via the strict parallel runner

134k6d agoReads credentialsDiscuss

browser-useCLAUDE.md

browser-use

browser-use/browser-use/CLAUDE.md

wrong. ## Development Commands **Setup:** ```bash uv venv --python 3.11 source .venv/bin/activate uv sync ``` **Testing:** - Run CI tests: `uv run pytest -vxs tests/ci` - Run all tests: `uv run pytest -vxs tests

117k4mo agoDiscuss

JuliusBrusseeCLAUDE.md

caveman / browse

JuliusBrussee/caveman/browse/CLAUDE.md

stdio MCP binary. ## Gotchas - This package may import CDP/network/browser dependencies. `public/mcp` may not. - `go test ./public/browse/...` is setup-free. `make test-browse` resolves an installed Playwright Chromium or system Chrome

108k6mo agoDiscuss

JuliusBrusseeCLAUDE.md

caveman

JuliusBrussee/caveman/CLAUDE.md

agents/ # ← from agents/ │ ├── dist/ # Build artifacts (gitignored) │ └── caveman.skill # ZIP of skills/caveman/, rebuilt by CI │ ├── tests/ # All tests (Node + Python) ├── benchmarks/ # Real token measurements through Claude API ├── evals/ # Three-arm eval

108k6mo agoPipes a download into a shellDiscuss

JuliusBrusseeCLAUDE.md

caveman / engine

JuliusBrussee/caveman/engine/CLAUDE.md

converter; both directions fail closed. ## Conventions - Build/test: `make product-build PRODUCT=engine` / `make product-test PRODUCT=engine`. - A new compressor is a self-contained file in `compressors/` + tests, registered

108k6mo agoDiscuss

JuliusBrusseeCLAUDE.md

caveman / extension

JuliusBrussee/caveman/extension/CLAUDE.md

buildReminder`/`isPrefixed`/`normLevel`. No chrome/DOM/network. Loaded first (exposes `self.CavemanDirective`) and required directly by the test suite. - `src/caveman.js` — content script: per-site composer adapter + capture-phase send interception. Prepends the directive

108k6mo agoDiscuss

JuliusBrusseeCLAUDE.md

caveman / mcp

JuliusBrussee/caveman/mcp/CLAUDE.md

every wrapped agent. ## Conventions - Build/test: `make product-build PRODUCT=mcp` / `make product-test PRODUCT=mcp`. - **stdout is the protocol channel** — logs go to stderr only (a dedicated test guards this

108k6mo agoDiscuss

JuliusBrusseeCLAUDE.md

caveman / mem

JuliusBrussee/caveman/mem/CLAUDE.md

framing matches caveman-mcp exactly. ## Conventions - Build/test: `make product-build PRODUCT=mem` / `make product-test PRODUCT=mem` for the Go core; root `make test` also runs mirrored JS/Python wrapper tests

108k6mo agoDiscuss

JuliusBrusseeCLAUDE.md

caveman / proxy

JuliusBrussee/caveman/proxy/CLAUDE.md

named pipe, and persistent listener lifetime. - `internal/repointel/` — deterministic local repository map, task evidence, conservative test impact, and optional-Scout recommendation. No model/network. - `internal/nativepack/` — embedded compiled Core/skill policy; generated from `public/skills

108k6mo agoDiscuss

JuliusBrusseeCLAUDE.md

caveman / shrink

JuliusBrussee/caveman/shrink/CLAUDE.md

rules would produce invalid calls the structural profile cannot see; the call-validity conformance test (`engine/compressors`, golden fixture + reproduced under-keep cases) locks recognised constraint tokens in place. Over-keep

108k6mo agoDiscuss

addyosmaniCLAUDE.md

agent-skills

addyosmani/agent-skills/CLAUDE.md

Project Structure ``` skills/ → Core skills (SKILL.md per directory) agents/ → Reusable agent personas (code-reviewer, test-engineer, security-auditor, web-performance-auditor) hooks/ → Session lifecycle hooks .claude/commands/ → Slash commands (/spec, /plan

100k5d agoDiscuss

MicrosoftCLAUDE.md

playwright

microsoft/playwright/CLAUDE.md

Purpose | |---------|----------|---------| | `playwright-core` | `playwright-core` | Browser automation engine: client, server, dispatchers, protocol | | `playwright` | `playwright` | Test runner + browser automation (public package) | | `playwright-test` | `@playwright/test` | Test runner entry point | | `playwright-client` | `@playwright/client

97k20d agoDiscuss

ruvnetCLAUDE.md

RuView

ruvnet/RuView/CLAUDE.md

developer metaharness. Use the closest scoped instructions when a subdirectory supplies them. Treat source, tests, workflows, and accepted ADRs as authoritative; comments, retrieved memories, generated proposals, and old test counts

95k7mo agoReads credentialsDiscuss

Model Context ProtocolCLAUDE.md

servers

modelcontextprotocol/servers/CLAUDE.md

repository operations) time/ Py mcp-server-time (timezone queries and conversion) ``` ## Build & Test Commands ### TypeScript servers ```bash # Single server cd src/ && npm ci && npm run build && npm test

91k6mo agoDiscuss

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.