CLAUDE.md examples from real projects

nyldnReads credentialsCLAUDE.md

claude-octopus

nyldn/claude-octopus/CLAUDE.md

Review workflow:** ``` 🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider validation mode ✅ Deliver Phase: Reviewing authentication implementation Providers: 🔴 Codex CLI - Code quality analysis 🧭 Antigravity CLI - Security and edge cases 🔵 Claude - Synthesis and recommendations

No other project uses it yet

tigerless-labsDeletes or force-pushesCLAUDE.md

agent-memory

tigerless-labs/agent-memory/CLAUDE.md

green-CI PR handed off for review — the owner merges, never the agent. ## Working rules - **English only in commits, PRs, issues, and code identifiers.** Design docs under `docs/design/` may stay

facebookincubatorCLAUDE.md

velox

facebookincubator/velox/.claude/CLAUDE.md

CLAUDE.md Guidance for Claude Code when working in the Velox repository. ## Branch Hygiene Before creating a new feature branch, always: 1. `git checkout main` 2. `git fetch upstream && git rebase

spacering-netCLAUDE.md

codeg

spacering-net/codeg/CLAUDE.md

when working with code in this repository. ## 项目概述 Codeg（Code Generation）是一个多智能体编码工作台，它将多个智能体（Claude Code、Codex CLI、OpenCode、Gemini CLI、OpenClaw、Cline 等）统一到一个工作区中，支持会话聚合和多智能体协作，支持桌面安装，服务器/Docker 部署。 ## 技术栈

txn2CLAUDE.md

kubefwd

txn2/kubefwd/CLAUDE.md

Limitation UDP port forwarding is not supported (Kubernetes API limitation: kubernetes/kubernetes#47862). ## Code Organization ``` cmd/kubefwd/ # CLI entry point kubefwd.go # Main entry, root command services/ services.go # Services subcommand, namespace watchers

No other project uses it yet

AdventDevIncCLAUDE.md

kudu

AdventDevInc/kudu/CLAUDE.md

Repository Exploration - Preserve correctness: use focused searches to locate evidence, then read enough surrounding code to understand behavior. - List candidates with `rg --files` or `fd`; avoid recursive `ls` and unrestricted

acacodeCLAUDE.md

swagger-typescript-api

acacode/swagger-typescript-api/CLAUDE.md

require excessive casting. - Avoid `@ts-ignore` — use `@ts-expect-error` with the specific error code instead, so the suppression breaks when the underlying issue is fixed. - Avoid catch-all pattern

rotkiReads credentialsCLAUDE.md

rotki

rotki/rotki/CLAUDE.md

belong in the PR body — they are read once, at review, while a comment is read every time the code is, and nothing fails when the narrative stops being true

dora-rsPipes a download into a shellCLAUDE.md

dora

dora-rs/dora/CLAUDE.md

/simplify` skill to check for unnecessary complexity, code duplication, or inefficiency in the changed code. ### Step 3: Local CI (fmt + clippy + tests) ```bash # 1. Format — CI rejects formatting diffs cargo

No other project uses it yet

timescaleCLAUDE.md

pg_textsearch

timescale/pg_textsearch/CLAUDE.md

testing - `benchmark.yml` - Performance benchmarks - `nightly-stress.yml` - Nightly stress tests with memory leak detection - `claude-code-review.yml` - AI code review integration - `claude.yml` - Claude Code automation See [RELEASING.md](RELEASING.md) for release instructions. ## Debug Functions - `bm25

No other project uses it yet

AnthropicCLAUDE.md

anthropic-sdk-python

anthropics/anthropic-sdk-python/CLAUDE.md

contributors (human or AI) on how this SDK is put together, plus the things reviews most often come back to. Setup instructions live in [CONTRIBUTING.md](CONTRIBUTING.md). ## Overview The official Python

touchHLECLAUDE.md

touchHLE

touchHLE/touchHLE/CLAUDE.md

contributors o= ften fail to read, the project absolutely cannot accept AI-generated code= for legal reasons. Contributors choosing to use AI agents anyway create = problems for us, and this

skyhook-ioReads credentialsCLAUDE.md

radar

skyhook-io/radar/CLAUDE.md

Before calling a UI feature done — consider visual-test.** `make tsc` + `make test` check code; `/visual-test` checks the *screen*. Run it yourself for self-contained UI changes where

atopileCLAUDE.md

atopile

atopile/atopile/CLAUDE.md

read the correspondig skill. Skills are located in `.claude/skills/`. ``` .claude/skills ├── ato-language │ ├── EXTENSION.md │ └── SKILL.md ├── code-review │ └── SKILL.md ├── compiler │ └── SKILL.md ├── dev │ └── SKILL.md ├── domain-layer │ └── SKILL.md ├── fabll │ └── SKILL.md ├── faebryk │ └── SKILL.md ├── frontend │ └── SKILL.md

gadievronCLAUDE.md

raptor

gadievron/raptor/CLAUDE.md

Joern) validate — the LLM never directly classifies code as vulnerable, tool output is the verdict. Flags: `--model `, `--max-cost `, `--review-passes N`, `--adversarial`, `--local`. Full pipeline, gates, strategies, tool menu

edwardkimCLAUDE.md

rhwp

edwardkim/rhwp/CLAUDE.md

검토-기록과의-구분)에 따라 원 PR을 생성·갱신하기 전에 제출할 code head의 영향 페이지를 캡처한다. 대표 review·overlay PNG를 안정 경로에 커밋하고, 원 PR 본문에 그 head의 repository·SHA로

No other project uses it yet

pipeshub-aiCLAUDE.md

pipeshub-ai

pipeshub-ai/pipeshub-ai/CLAUDE.md

AGENTS.md ## Claude Code - Reviewing a pull request or diff: use the `pr-review` skill (`.claude/skills/pr-review/SKILL.md`). CI's review workflow reads the same file. - Adding or changing a connector

No other project uses it yet

pyvistaCLAUDE.md

pyvista

pyvista/pyvista/CLAUDE.md

before writing code, `pyvista-vtk` before wrapping a VTK class or touching a filter, `pyvista-testing` before touching a plotting test or a baseline image, `pyvista-review` before reviewing

GoochbeaterCLAUDE.md

Spiritual-Spell-Red-Teaming / Jailbreak-Guide

Goochbeater/Spiritual-Spell-Red-Teaming/Jailbreak-Guide/CLAUDE.md

con/Dub con, violent scene Can put on a Coding Hat (of selectwd review the coding information below) CANNOT DO: Minors, even a sniff of this content and shut the chat

openrewriteCLAUDE.md

rewrite

openrewrite/rewrite/CLAUDE.md

pass before submitting - Address review comments promptly ## Important Conventions ### Nullability Annotations The project uses JSpecify nullability annotations. ## Conclusion Following these guidelines will help maintain code quality and consistency across