CLAUDE.md examples from real projects

MemTensorCLAUDE.md

MemOS

MemTensor/MemOS/CLAUDE.md

integration-tester` | Read-write | Author and run integration / end-to-end cases under `tests/` | The main repo has no frontend stack, so no `frontend-dev` is provided; TypeScript sub-projects

No other project uses it yet

JeffallanCLAUDE.md

claude-skills

Jeffallan/claude-skills/CLAUDE.md

description:** ```yaml description: Use for debugging. First investigate root cause, then analyze patterns, test hypotheses, and implement fixes with tests. ``` **GOOD - Capability + trigger:** ```yaml description: Diagnoses bugs through root cause

ankidroidCLAUDE.md

Anki-Android

ankidroid/Anki-Android/CLAUDE.md

settings 'while you're in there'. ## Verification - For bug fixes, write the failing regression test FIRST and confirm it fails before applying

jina-aiCLAUDE.md

reader

jina-ai/reader/CLAUDE.md

engines, formatting profiles, abuse mitigation, deployment topology. - `CONTRIBUTING.md` — full env var table, dev workflow, test policy. - `cookbooks.md` — header recipes for common downstream pipelines (RAG, embedding, deep research, uploads, etc.). ## Common

No other project uses it yet

LeantimeReads credentialsCLAUDE.md

leantime

Leantime/leantime/CLAUDE.md

development server on port 8090 with: - Leantime app: http://localhost:8090 - MailDev (for email testing): http://localhost:8081 - phpMyAdmin: http://localhost:8082 (auth: leantime/leantime) - S3Ninja (for S3 testing): http://localhost

BeehiveInnovationsReads credentialsCLAUDE.md

zen-mcp-server

BeehiveInnovations/zen-mcp-server/CLAUDE.md

these instructions to efficiently run quality checks, manage the server, check logs, and run tests. ## Quick Reference Commands ### Code Quality Checks Before making any changes or submitting PRs, always

0xJackyCLAUDE.md

nginx-ui

0xJacky/nginx-ui/CLAUDE.md

database pagination for large datasets - Before committing backend changes, run the CI-equivalent unit test command: `GOWORK=off go test -tags=unembed -race -cover -count=1 ./...` - Keep `-count

No other project uses it yet

AudioKitCLAUDE.md

AudioKit

AudioKit/AudioKit/CLAUDE.md

guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Build & Test Commands AudioKit uses Swift Package Manager. The CI builds target iOS Simulator: ```bash # Build xcodebuild

jaredpalmerCLAUDE.md

tsdx

jaredpalmer/tsdx/CLAUDE.md

Version 2.0 is a complete rewrite using modern Rust-based tooling: bunchee (bundling), vitest (testing), oxlint (linting), and oxfmt (formatting). ## Development Commands ```bash bun install # Install dependencies bun run build

No other project uses it yet

facebookCLAUDE.md

hermes

facebook/hermes/CLAUDE.md

compact bytecode. ## Build Commands ### Default Build: ASan+Debug with -O1 Always build and test with AddressSanitizer enabled unless the user explicitly asks otherwise or there is a specific reason

tossCLAUDE.md

es-toolkit

toss/es-toolkit/CLAUDE.md

preferred language. ## Quick Reference ```bash corepack enable && yarn install # Setup yarn vitest run # Tests yarn vitest run src/array/chunk # Test specific function yarn lint # ESLint tsc --noEmit # Typecheck ``` ## Structure ``` src/{category

loft-shCLAUDE.md

vcluster

loft-sh/vcluster/CLAUDE.md

vCluster — Agent Instructions ## E2E TDD Workflow When doing test-driven development, ALWAYS follow the workflow in [.claude/e2e-tdd-workflow.md](.claude/e2e-tdd-workflow.md). Use the AGENT_SESSION env var to isolate your commands per session

No other project uses it yet

3b1bCLAUDE.md

videos

3b1b/videos/CLAUDE.md

extensions - `custom_config.yml` - Manim configuration with custom paths and rendering settings - `playground.py` - Sandbox file for testing and experimentation ### Video Project Structure Each video project typically contains: - Main scene files (e.g., `main.py

BrasilAPICLAUDE.md

BrasilAPI

BrasilAPI/BrasilAPI/CLAUDE.md

desenvolvedores e empresas em produção. ## Stack - **Framework:** Next.js 12, API routes em `pages/api/` - **Testes:** Vitest 3 (E2E, faz chamadas HTTP reais ao servidor local) - **Lint:** ESLint (Airbnb) + Prettier - **Commits:** Conventional

gui-csCLAUDE.md

Terminal.Gui

gui-cs/Terminal.Gui/CLAUDE.md

cwp-pattern.md` - Cancellable Workflow Pattern - `code-layout.md` - Backing fields, member ordering - `api-documentation.md` - XML documentation requirements - `testing-patterns.md` - Test patterns and requirements - `logging-tracing.md` - **No Console.WriteLine** - use Logging/TestLogging/Trace - `fragile-areas.md` - Code that must not be refactored

QuentinFuxaCLAUDE.md

WhisperLiveKit

QuentinFuxa/WhisperLiveKit/CLAUDE.md

Working on WhisperLiveKit Follow [CONTRIBUTING.md](CONTRIBUTING.md) for setup, validation, and test scope. ## Runtime boundaries - `TranscriptionEngine` loads models during startup and is shared within one process. `reset()` is for tests

tambo-aiReads credentialsCLAUDE.md

tambo

tambo-ai/tambo/CLAUDE.md

/code) when touching this repo. **Read @AGENTS.md first.** It owns architecture, naming, workflow rules, testing expectations, and anything code-related. Keep that file open—this doc just points you there

No other project uses it yet

storytoldCLAUDE.md

vectorcraft

storytold/vectorcraft/CLAUDE.md

notes from it. 3. Follow the autonomous operation protocol (`plan/execution-plan.md` §7): orient → plan → implement + test → verify → record → commit. Don't stop to ask unless §7 lists the decision

pwndbgCLAUDE.md

pwndbg

pwndbg/pwndbg/CLAUDE.md

exploit developers. It's written in Python and supports both GDB (mature, battle-tested) and LLDB (experimental, early-stage). **Important**: Read the developer documentation in `docs/contributing/` for comprehensive guidance. This

No other project uses it yet

hectorqinCLAUDE.md

reader

hectorqin/reader/CLAUDE.md

Commands Run from repo root (or `cd` into the package). CI runs install → typecheck → test → build per package: GitHub Actions `.github/workflows/ci.yml` (PRs and every branch push; also UI review, Android