agentleFS

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 13Worked for most · soon
fleetdmCLAUDE.md

fleet

fleetdm/fleet/.claude/CLAUDE.md

description format in the `handbook-pr` skill instead. The template is a code checklist, and `check-pr-template` doesn't run on handbook-only changes. - Add a `## AI` section

Steady8 mentions in 2 weeks

No other project uses it yet

7.2k6d agoReviewMountCreate a free account to mount
rddmwmddrCLAUDE.md

android-ad-cleaner

rddmwmddr/android-ad-cleaner/CLAUDE.md

progress`(已认领、正在改)。见 `docs/agents/triage-labels.md`。 ### Release followup 发版后要催哪些复测、报告者确认前不关闭哪些 issue,见 `docs/agents/release-followup.md`。每次发版都要过一遍这张清单。 ### Code review 派审查的方法与规则见 `docs/agents/code-review.md`:基线钉 SHA、评审期间不改工作区、默认三轴。 ### Domain docs single-context:根目录 `CONTEXT.md` + `docs/adr/`。见 `docs/agents/domain.md

Steady2 mentions in 2 weeks

No other project uses it yet

7.1k23d agoReviewMountCreate a free account to mount
HapeLeeReads credentialsCLAUDE.md

legado-with-MD3

HapeLee/legado-with-MD3/CLAUDE.md

Build / Test / Run ```bash # Quick compile check (Kotlin only, no dex/package — fastest for verifying code compiles) .\gradlew.bat :app:compileAppDebugKotlin # Assemble all variants ./gradlew assembleAppRelease # Assemble without R8 (for crash debugging

7k57d agoReviewMountCreate a free account to mount
sdkmanCLAUDE.md

sdkman-cli

sdkman/sdkman-cli/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Project Overview SDKMAN! CLI is a bash-based command-line tool for managing

6.9k24mo agoReviewMountCreate a free account to mount
flexpriceReads credentialsCLAUDE.md

flexprice

flexprice/flexprice/CLAUDE.md

browsing. - Read **`graphify-out/GRAPH_REPORT.md`** only for broad architecture review or when query/path/explain do not surface enough context. - After modifying code in ways that change structure or dependencies, run **`graphify

6.9k7mo agoReviewMountCreate a free account to mount
j3ssieReads credentialsCLAUDE.md

osmedeus

j3ssie/osmedeus/CLAUDE.md

ship alongside the engine, vendored into this repo so they version together with the code they talk to. | Directory | Standalone repo | Purpose | |-----------|-----------------|---------| | `platform/osmedeus-dashboard` | `osmedeus/osmedeus-dashboard` | Next.js UI; built into `public/ui

6.6k7mo agoReviewMountCreate a free account to mount
Arthur-FicialCLAUDE.md

apfel

Arthur-Ficial/apfel/CLAUDE.md

merge (correctness, test coverage, architectural consistency) - **P2** nice to have (code quality, follow-up PR acceptable) ### 6. Architecture review - Does it fit the golden goal (UNIX tool + OpenAI server + chat

6.6k4mo agoReviewMountCreate a free account to mount
k3d-ioCLAUDE.md

k3d

k3d-io/k3d/CLAUDE.md

issues/PRs before opening new ones to avoid duplicates. The project follows the Contributor Covenant Code of Conduct (`CODE_OF_CONDUCT.md`). ## Conventions - All Go source files have the MIT license copyright header - Import

Steady4 mentions in 2 weeks

No other project uses it yet

6.6k4y agoReviewMountCreate a free account to mount
wadituCLAUDE.md

czsc

waditu/czsc/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## 项目概述 CZSC(缠中说禅技术分析工具)是基于缠中说禅理论的综合性量化交易Python库,提供技术分析、信号生成、回测和市场分析等功能。本项目专注于实现缠论的分型、笔、线段等核心概念的自动识别,以及基于此的多级别量化交易策略。 ## 🏛️ 开发宪法(Constitution

6.6k6mo agoReviewMountCreate a free account to mount
epoko77-aiCLAUDE.md

im-not-ai

epoko77-ai/im-not-ai/CLAUDE.md

report`면 사람 검토 권고. 수렴 판정은 LLM 재탐지가 아니라 `verify_gates.py`(결정적, exit code)가 내린다. `verify_change_rate.py`는 기존 연동을 위해 보존한다. ## 에이전트 구성 (9개 — 역할 구분 필수) **런타임 3종

6.6k53d agoReviewMountCreate a free account to mount
SentryCLAUDE.md

MobileBuildMCP

getsentry/MobileBuildMCP/CLAUDE.md

errors from outdated dependencies; upgrade the dependency instead - Always ask before removing functionality or code that appears to be intentional - Do not add fallback behavior by default. If required context

6.5k53d agoReviewMountCreate a free account to mount
rizsottoCLAUDE.md

Bear

rizsotto/Bear/CLAUDE.md

parsing | `crates/semantic/CLAUDE.md` | | Edit or add compiler interpreter YAML | `crates/semantic/compilers/CLAUDE.md` | | Edit the YAML-to-Rust code generator | `build-support/compilers-codegen/CLAUDE.md` | | Add or change a host capability probe | `build-support/platform-checks/CLAUDE.md` | | Touch

6.5k22d agoReviewMountCreate a free account to mount
czlonkowskiCLAUDE.md

n8n-skills

czlonkowski/n8n-skills/CLAUDE.md

Write code for the AI-agent-callable Custom Code Tool (`@n8n/n8n-nodes-langchain.toolCode`) - Critical distinction from Code node: return a string (not `[{json:{...}}]`), `$fromAI()` not available, different sandbox - Unstructured (`query` string

No other project uses it yet

6.5k3mo agoReviewMountCreate a free account to mount
jacob-bdCLAUDE.md

notebooklm-mcp-cli

jacob-bd/notebooklm-mcp-cli/CLAUDE.md

core/ # Low-level API client (no business logic) │ ├── client.py # Internal batchexecute API calls │ ├── constants.py # Code-name mappings (CodeMapper class) │ └── auth.py # AuthManager for profile-based token caching └── utils/ ├── config.py # Configuration

6.5k2d agoReviewMountCreate a free account to mount
op7418CLAUDE.md

CodePilot

op7418/CodePilot/CLAUDE.md

必要时追加真实凭据 smoke 或 E2E,并把结果写入相关执行计划的 Smoke Ledger。 ## 汇报与完成状态 **完成状态词典(禁止混用):** `Code complete`(代码改完)/ `Tests pass`(测试过)/ `Smoke passed`(真实路径跑通)/ `Review passed`(复审无 blocker)/ `Release ready`(可发版)/ `Shipped`(已 push/tag/release)。不要把

6.5k5mo agoReviewMountCreate a free account to mount
jacob-bdCLAUDE.md

notebooklm-mcp

jacob-bd/notebooklm-mcp/CLAUDE.md

core/ # Low-level API client (no business logic) │ ├── client.py # Internal batchexecute API calls │ ├── constants.py # Code-name mappings (CodeMapper class) │ └── auth.py # AuthManager for profile-based token caching └── utils/ ├── config.py # Configuration

6.5k11d agoReviewMountCreate a free account to mount
FlorianBruniauxCLAUDE.md

claude-code-ultimate-guide

FlorianBruniaux/claude-code-ultimate-guide/CLAUDE.md

audits, and codebase reviews. ### Public content must be portable Apply this rule to guides, evaluations, examples, changelogs, indexes, exports, and landing content, including code blocks, tables, captions, and link targets

Steady2 mentions in 2 weeks

No other project uses it yet

6.4k9d agoReviewMountCreate a free account to mount
valhallaCLAUDE.md

valhalla

valhalla/valhalla/CLAUDE.md

clarifying question, or when flagging something important. Do not append it to every comment, code review note, or short follow-up; that becomes noise. Use it as a human would

6.4k8d agoReviewMountCreate a free account to mount
Q00CLAUDE.md

ouroboros

Q00/ouroboros/CLAUDE.md

tracking link; do not expand the PR. Only the maintainer decides scope expansion. Keep review comments tied to the declared boundary and directly evidenced behavior. The declared boundary cannot waive

No other project uses it yet

6.4k4mo agoReviewMountCreate a free account to mount
uItraworkersCLAUDE.md

claw-code-parity

uItraworkers/claw-code-parity/CLAUDE.md

consistent with generated guidance and tests. - `tests/` contains validation surfaces that should be reviewed alongside code changes. ## Working agreement - Prefer small, reviewable changes and keep generated bootstrap files aligned with

768mo agoReviewMountCreate a free account to mount
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.