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 7Worked for most · soon
kurikomi-labsCLAUDE.md

komi-store

kurikomi-labs/komi-store/CLAUDE.md

terse output. - **karpathy-guidelines** — anti-overcomplication, minimal diffs, surface assumptions, verifiable success criteria. Every coding task. - **one-skill-to-rule-them-all** — watch for skill-capture opportunities during multi-step

1 project uses a version of this

20k6mo agoReviewMountCreate a free account to mount
AnthropicReads credentialsCLAUDE.md

claude-quickstarts / assistant-ui

anthropics/claude-quickstarts/managed-agents/assistant-ui/CLAUDE.md

multiagent: { type: "coordinator", agents: [...] }` roster so the analyst hands its numbers to a toolless reviewer. The handoff events (`session.thread_created`, `agent.thread_message_sent/received`) already arrive on the stream; the reducer

19k40d agoReviewMountCreate a free account to mount
AnthropicReads credentialsCLAUDE.md

claude-quickstarts / sentry-autofix

anthropics/claude-quickstarts/managed-agents/sentry-autofix/CLAUDE.md

asks to turn off a LaunchDarkly flag for the broken code path while the pull request waits for review. Keep it host-side like `open_pull_request`, with the flag

19k40d agoReviewMountCreate a free account to mount
storytoldCLAUDE.md

pdfcraft

storytold/pdfcraft/CLAUDE.md

bound recursion with depth limits or seen-sets. - Handle lock poisoning. - No `unsafe` (`unsafe_code = "forbid"`). - Every crash fix gets a synthetic regression test. See `AGENTS.md` §4. - **Rust only

19k1d agoReviewMountCreate a free account to mount
emcie-coCLAUDE.md

parlant

emcie-co/parlant/CLAUDE.md

again until you get it. 4. Implement the tests first. Ask for confirmation and code review. 5. Once tests are approved, once again suggest your implementation plan for making them

No other project uses it yet

18k22mo agoReviewMountCreate a free account to mount
muratcankoylanCLAUDE.md

Agent-Skills-for-Context-Engineering

muratcankoylan/Agent-Skills-for-Context-Engineering/CLAUDE.md

skills) - `SKILL.md` (root) - Collection-level metadata and skill map - `.claude-plugin/marketplace.json` - Claude Code marketplace manifest (single bundled plugin, v2.6.0) - `.plugin/plugin.json` - Open Plugins format manifest (v2.6.0) ## Build & Test Commands

No other project uses it yet

18k3mo agoReviewMountCreate a free account to mount
CannerCLAUDE.md

WrenAI

Canner/WrenAI/.claude/CLAUDE.md

downstream. - Every assertion must be capable of failing. An assertion about a condition the code cannot produce is noise. - Confirm the test actually runs in CI. Some test files

Steady7 mentions in 2 weeks

No other project uses it yet

18k22mo agoReviewMountCreate a free account to mount
ben-manesCLAUDE.md

caffeine

ben-manes/caffeine/.claude/CLAUDE.md

JCache) conformance When to read which doc: - Concurrency or thread-safety work → `synchronization.md` - Reviewing code → `design-decisions.md` first (prevents false positives); an audit reads it at the auditor's Phase

No other project uses it yet

18k22d agoReviewMountCreate a free account to mount
questdbCLAUDE.md

questdb

questdb/questdb/CLAUDE.md

configs, "Not changed" lists). The code and its tests carry those. - **A PR may ship with known bugs whose risk is low.** `review-pr` rates each bug a change introduces

17k11d agoReviewMountCreate a free account to mount
joewalnesCLAUDE.md

websocketd

joewalnes/websocketd/CLAUDE.md

just apologize — fix the system. ## Evolving preferences When the user expresses a coding preference, convention, or correction during a session, offer to encode it into this CLAUDE.md file

No other project uses it yet

17k55d agoReviewMountCreate a free account to mount
foambubbleCLAUDE.md

foam

foambubble/foam/CLAUDE.md

CLAUDE.md @AGENTS.md The rest of this file is specific to Claude Code. ## Slash commands Defined in `.claude/commands/`: - `/research-issue ` — researches a GitHub issue into `.agent/tasks/ - .md`. Before working on an issue

No other project uses it yet

17k33d agoReviewMountCreate a free account to mount
weaviateCLAUDE.md

weaviate

weaviate/weaviate/CLAUDE.md

fixed or pinned by a failing test. Never fix only the reproduction a reviewer gave you. If a bug exists in journey X, enumerate every realistic adjacent journey

No other project uses it yet

17k48d agoReviewMountCreate a free account to mount
rust-langCLAUDE.md

rust-analyzer

rust-lang/rust-analyzer/CLAUDE.md

code fixtures and `expect-test` snapshots. Follow the nearest existing test helper and fixture convention rather than introducing a new test harness. - Before planning or writing fixture-based tests, review

No other project uses it yet

17k18mo agoReviewMountCreate a free account to mount
javascript-obfuscatorCLAUDE.md

javascript-obfuscator

javascript-obfuscator/javascript-obfuscator/CLAUDE.md

# JavaScript Obfuscator - Project Documentation ## Project Overview **JavaScript Obfuscator** is a powerful, enterprise-grade code

No other project uses it yet

16k11mo agoReviewMountCreate a free account to mount
GLipsReads credentialsCLAUDE.md

Figma-Context-MCP

GLips/Figma-Context-MCP/CLAUDE.md

APIs. If that fails, you may search the code directly or search the web for more detail. ## Communication Style When reviewing plans, providing feedback, or analyzing approaches, be genuinely critical

No other project uses it yet

16k4mo agoReviewMountCreate a free account to mount
organicmapsCLAUDE.md

organicmaps / android

organicmaps/organicmaps/android/CLAUDE.md

Extend `BaseMwmFragmentActivity` and override `onSafeCreate()` (not `onCreate()`) -- ensures C++ core is initialized before activity code runs - Use `BaseMwmFragment` with `OnBackPressListener` interface - Thread safety: use `Handler(Looper.getMainLooper())` for UI updates from

16k6mo agoReviewMountCreate a free account to mount
organicmapsCLAUDE.md

organicmaps

organicmaps/organicmaps/CLAUDE.md

commit must compile on all platforms and pass tests; exceptions are possible for easier code review, if PR will be squashed, or for android using string ids before strings regenerated

16k6mo agoReviewMountCreate a free account to mount
organicmapsCLAUDE.md

organicmaps / iphone

organicmaps/organicmaps/iphone/CLAUDE.md

patterns - UIKit is the default. SwiftUI is currently limited to `OMapsWidgetExtension` Live Activity code. - Prefer programmatic UIKit for new screens; keep existing storyboards/XIBs when editing legacy flows. - Validate UI approaches

No other project uses it yet

16k6mo agoReviewMountCreate a free account to mount
GreyDGLCLAUDE.md

PentestGPT

GreyDGL/PentestGPT/CLAUDE.md

Claude guide Internal instructions for Claude Code in this repository. Read [`docs/architecture.md`](docs/architecture.md) before architecture work. The root `README.md` is the public project page and must not be edited unless

No other project uses it yet

16k4mo agoReviewMountCreate a free account to mount
spreeReads credentialsCLAUDE.md

spree

spree/spree/CLAUDE.md

sanitize data, and follow best practices for secure coding. Use tools like static analysis, code reviews, and penetration testing to identify and fix security issues before they become a problem

Steady12 mentions in 2 weeks

No other project uses it yet

16k3mo 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.