CLAUDE.md examples from real projects

mauriceboeReads credentialsCLAUDE.md

NOMAD

mauriceboe/NOMAD/CLAUDE.md

failing condition blocks it: | Condition (new code) | Must be | |---|---| | Coverage | ≥ 80% | | Duplicated lines | ≤ 3% | | Security / reliability / maintainability rating | A | | Security hotspots reviewed | 100% | - **Duplication is the one that bites.** Desktop

yusufkaraaslanReads credentialsCLAUDE.md

Skill_Seekers

yusufkaraaslan/Skill_Seekers/CLAUDE.md

ignore=tests/test_mcp_server.py --ignore=tests/test_install_skill_e2e.py -q # Single test pytest tests/test_scraper_features.py::test_detect_language -vv -s # Code quality (must pass before push - matches CI) uvx ruff check src/ tests/ uvx ruff format

mindfold-aiCLAUDE.md

Trellis

mindfold-ai/Trellis/CLAUDE.md

symbols, 20870 relationships, 300 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely. > Index stale? Run `node .gitnexus/run.cjs analyze` from the project root

d2phapCLAUDE.md

ImageGlass / source

d2phap/ImageGlass/source/CLAUDE.md

# ImageGlass v10 ## Project Overview ImageGlass v10 is a complete rewrite in **C# with .NET

amir20CLAUDE.md

dozzle

amir20/dozzle/CLAUDE.md

work is done, report its size per feature (code, tests, generated) next to its user impact, so cuts happen before review time is spent. ## Project Overview Dozzle is a lightweight

No other project uses it yet

AndyMik90CLAUDE.md

Aperant

AndyMik90/Aperant/CLAUDE.md

null}` 4. Reset `bot_detection_state.json` to `{"reviewed_commits": {}}` — this is the gatekeeper; without clearing it, the bot detector skips already-seen commits ## Project Structure ``` autonomous-coding/ ├── apps/ │ └── desktop/ # Electron desktop application

benbjohnsonCLAUDE.md

litestream

benbjohnson/litestream/CLAUDE.md

Code Configuration Claude-specific optimizations for Litestream. See [AGENTS.md](AGENTS.md) for project documentation. ## Critical Coding Rules - **Always return errors, never log and continue.** The only exception is DEBUG logging

No other project uses it yet

coturnDeletes or force-pushesCLAUDE.md

coturn

coturn/coturn/CLAUDE.md

larger or multi-part effort, references to a prior discussion or review, what the code used to do, an issue/PR number as the only justification, or attribution. ## Memory allocation **MANDATORY

No other project uses it yet

idankReads credentialsCLAUDE.md

explainshell

idank/explainshell/CLAUDE.md

code (function signatures, return types, and non-obvious variables). Do not retroactively annotate existing code unless you are already modifying it. ## Environment - Python virtualenv: repo-local `.venv` - **CRITICAL**: Every Bash

bitwardenCLAUDE.md

clients

bitwarden/clients/.claude/CLAUDE.md

Bitwarden Clients - Claude Code Configuration ## Project Context Files **Read these files before reviewing to ensure that you fully understand the project and contributing guidelines** 1. `README.md` (read on demand

ComposioHQCLAUDE.md

agent-orchestrator

ComposioHQ/agent-orchestrator/CLAUDE.md

CLAUDE.md Read and follow [`AGENTS.md`](AGENTS.md) for repository layout, commands, coding conventions, and hard rules. ## App state lives under `~/.ao` only All app state, the daemon's data dir, `running.json

qazbnm456Reads credentialsCLAUDE.md

awesome-web-security

qazbnm456/awesome-web-security/CLAUDE.md

scripts/ci/templates/comment.{en,zh,jp}.md` — localized review comments. - `.github/workflows/pr-review.yml` — grades a PR; never posts. Two jobs: `verify` runs the PR's own code, `grade` runs the trusted base-branch scripts

No other project uses it yet

coleam00Pipes a download into a shellCLAUDE.md

context-engineering-intro / claude-code-full-guide

coleam00/context-engineering-intro/claude-code-full-guide/CLAUDE.md

names** before use - **Keep CLAUDE.md updated** when adding new patterns or dependencies - **Test your code** - No feature is complete without tests - **Document your decisions** - Future developers (including yourself) will thank

Model Context ProtocolCLAUDE.md

typescript-sdk

modelcontextprotocol/typescript-sdk/CLAUDE.md

CLAUDE.md The principles this SDK is built and reviewed by. They are not a checklist: apply them with judgement. 1. **Minimalism** — The SDK should do less, not more: prefer changes

No other project uses it yet

plantumlCLAUDE.md

plantuml

plantuml/plantuml/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Project Overview PlantUML is a tool that allows users to create UML diagrams

Orchestra-ResearchReads credentialsCLAUDE.md

AI-research-SKILLs

Orchestra-Research/AI-research-SKILLs/CLAUDE.md

idea to paper. Each skill provides expert-level guidance (200-500 lines) with real code examples, troubleshooting guides, and production-ready workflows. **Mission**: Enable AI agents to autonomously conduct

AgentWrapperCLAUDE.md

agent-orchestrator

AgentWrapper/agent-orchestrator/CLAUDE.md

CLAUDE.md Read and follow [`AGENTS.md`](AGENTS.md) for repository layout, commands, coding conventions, and hard rules. ## App state lives under `~/.ao` only All app state, the daemon's data dir, `running.json

humanlayerReads credentialsCLAUDE.md

humanlayer

humanlayer/humanlayer/CLAUDE.md

ready for plan", "plan in progress", "plan in review", "ready for dev", "in dev", "code review") - **get branch name**: `linear get-issue-v2 ENG-XXXX --fields branch` (use this when

No other project uses it yet

LangChainCLAUDE.md

open_deep_research / legacy

langchain-ai/open_deep_research/src/legacy/CLAUDE.md

planner model to generate a structured report outline - **Human-in-the-Loop**: Allows review and feedback on the report plan before execution - **Sequential Process**: Creates sections one by one with

nearaiCLAUDE.md

ironclaw

nearai/ironclaw/CLAUDE.md

IronClaw — Claude Code adapter @AGENTS.md Everything above (from `AGENTS.md`) is the canonical, tool-neutral contract. The rest of this file is Claude-specific. ## Skills and rules - Project skills live