CLAUDE.md examples from real projects

sigpCLAUDE.md

lighthouse

sigp/lighthouse/CLAUDE.md

Before You Start Read the relevant guide for your task: | Task | Read This First | |------|-----------------| | **Code review** | `.ai/CODE_REVIEW.md` | | **Creating issues/PRs** | `.ai/ISSUES.md` | | **Development patterns** | `.ai/DEVELOPMENT.md` | ## Critical Rules (consensus failures or crashes

openclawCLAUDE.md

acpx / agents

openclaw/acpx/agents/Claude.md

then select that session for later prompts: ```bash acpx --system-prompt "You are a code reviewer who challenges every implicit assumption." \ claude sessions new --name review acpx claude -s review

No other project uses it yet

ding113Reads credentialsCLAUDE.md

claude-code-hub

ding113/claude-code-hub/CLAUDE.md

with Biome bun run lint:fix # Auto-fix lint issues bun run format # Format code # Testing bun run test # Run unit tests (vitest) bun run test:ui # Interactive test

Intelligent-InternetCLAUDE.md

ii-agent

Intelligent-Internet/ii-agent/CLAUDE.md

OpenAI API google-genai # Gemini API stripe # Payments google-cloud-storage # File storage e2b-code-interpreter # Sandbox celery # Task queue apscheduler # Cron scheduling ``` ## Patterns ### Service Pattern Services take `db: AsyncSession

Norman-buryCLAUDE.md

research-writing-skill

Norman-bury/research-writing-skill/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Project purpose This repository is a **multi-platform skill/plugin** for research-paper writing

ResearAICLAUDE.md

DeepScientist

ResearAI/DeepScientist/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Project Overview DeepScientist is a local-first autonomous research studio that manages long

ClickHouseCLAUDE.md

clickhouse-go

ClickHouse/clickhouse-go/.claude/CLAUDE.md

globals or alternative constructors without a clear reason. --- ## Go Idioms Enforced Here Follow [Go Code Review Comments](https://go.dev/wiki/CodeReviewComments) in full. The rules below are the ones that matter

ForceInjectionCLAUDE.md

AI-fundamentals

ForceInjection/AI-fundamentals/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Repository overview AI Fundamentals is a Chinese-language knowledge repository covering the full

SQLMeshReads credentialsCLAUDE.md

sqlmesh

SQLMesh/sqlmesh/CLAUDE.md

begin by writing a failing test (or tests) that reflects the expected behavior 3. **Code Review**: After development work, invoke the `code-reviewer` agent to review the implementation 4. **Iteration

Emanuele-web04CLAUDE.md

remodex

Emanuele-web04/remodex/CLAUDE.md

hard a problem you can hand the model unsupervised. Taste covers UI/UX, code quality, API design, and copy. | model | cost | intelligence | taste | |---|---:|---:|---:| | gpt-5.6-sol | 9 | 8 | 5 | | sonnet

TanStackReads credentialsCLAUDE.md

ai

TanStack/ai/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Repository Overview TanStack AI is a type-safe, provider-agnostic

No other project uses it yet

bahdotshCLAUDE.md

wrkflw

bahdotsh/wrkflw/CLAUDE.md

understand what's in them — use `get_file_summary` - Read full source files to review code — use `get_file_summary` to triage, then `read_source` on specific symbols - Dump

liaohch3CLAUDE.md

claude-tap

liaohch3/claude-tap/.claude/CLAUDE.md

Claude Code Bridge This repository uses a single source of truth for engineering rules: - Follow [`../AGENTS.md`](../AGENTS.md) for all workflow, testing, and review requirements. Skill layout for multi-agent compatibility

PeerDB-ioCLAUDE.md

peerdb

PeerDB-io/peerdb/.claude/CLAUDE.md

result = 'failure' ORDER BY timestamp DESC` - The `reason` column holds the full failure trace/log. ## Code reviews guidelines - If you are deciding whether or not perform a code review, take into

InvoicePlaneReads credentialsCLAUDE.md

InvoicePlane

InvoicePlane/InvoicePlane/CLAUDE.md

instructions and security rules - `.github/copilot-instructions.md` — Copilot / AI coding conventions - `.junie/guidelines.md` — detailed security patterns and code-review checklist - `.github/improvements.md` — future enhancement ideas

No other project uses it yet

FluidInferenceCLAUDE.md

FluidAudio

FluidInference/FluidAudio/CLAUDE.md

Instructions**: Implementation first, explanation second 2. **Testing Policy**: Add unit tests when writing new code. 3. **Git Operations**: Never run `git push` unless explicitly requested. - **No Co-Author Tags

No other project uses it yet

vitodeployCLAUDE.md

vito

vitodeploy/vito/CLAUDE.md

different user, `cd`/`sudo` must run as the target user, not the login user. ## Code Review - `/review-pr [target-branch]` runs the three project reviewer agents (`php-laravel-reviewer`, `frontend-reviewer

CosmosOSReads credentialsCLAUDE.md

Cosmos

CosmosOS/Cosmos/.taskmaster/CLAUDE.md

session task-master next # Find next available task task-master show # Review task details # During implementation, check in code context into the tasks and subtasks task-master update-subtask

evinjohnnCLAUDE.md

natively-cluely-ai-assistant

evinjohnn/natively-cluely-ai-assistant/CLAUDE.md

change, and architectural decision must preserve correct behavior on both operating systems. --- ## MCP Tools: code-review-graph **IMPORTANT: This project has a knowledge graph. ALWAYS use the `code-review-graph

subsurfaceCLAUDE.md

subsurface

subsurface/subsurface/CLAUDE.md

commit messages and PR descriptions. Prefer small, focused commits over large sweeping changes. ## Code Review Rules When reviewing pull requests or commits: - ALWAYS use `git show -- ` to read the actual