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 17Worked for most · soon

StripeCLAUDE.md

stripe-cli

stripe/stripe-cli/CLAUDE.md

CLAUDE.md ## Build & Test Commands ```bash make build # Build binary (runs go generate first) make test # Run tests with race detector and coverage make lint # Run golangci-lint v2 make

2.2k4mo agoDiscuss

777geniusCLAUDE.md

Team Provisioning - `pnpm lint:fix` - Lint and auto-fix - `pnpm format` - Format code - `pnpm test` - Run all vitest tests - `pnpm test:watch` - Watch mode - `pnpm test:coverage` - Coverage report - `pnpm

2.2k4mo agoDeletes or force-pushesDiscuss

StripeCLAUDE.md

stripe-ruby

stripe/stripe-ruby/.claude/CLAUDE.md

stripe-ruby ## Testing - Run all tests: `just test` - Tests use Rake (`bundle exec rake test`) - Typecheck: `just typecheck` (Sorbet, requires Ruby >= 2.7) ## Formatting & Linting - Format: `just format` (uses rubocop with

2.2k55d agoDiscuss

wondelaiCLAUDE.md

skills

wondelai/skills/CLAUDE.md

done, lean-startup, design-sprint, inspired-product, continuous-discovery, 37signals-way | | **Product/Strategy** | mom-test, negotiation, monetizing-innovation, lean-analytics | | **Strategy/Growth** | crossing-the-chasm, blue-ocean-strategy, traction-eos, obviously-awesome

2.2k3mo agoDiscuss

AgriciDanielCLAUDE.md

claude-blog

AgriciDaniel/claude-blog/CLAUDE.md

blog-reviewer.md # Quality scoring (no Bash, post v1.7.0 hardening) blog-translator.md # Multilingual translation (no Bash, v1.7.0) tests/ # 250+ pytest checks incl. delivery-contract + security suites ``` ## Commands | Command | Purpose | |---------|---------| | `/blog write` | Write

2.1k2mo agoDiscuss

ShopifyCLAUDE.md

hydrogen

Shopify/hydrogen/CLAUDE.md

encrypt any newly added secrets. Some of the secrets inside are used in E2E tests, so we must also be careful to NEVER `console.log` (or otherwise leak/print) anything that

2.1k6mo agoDiscuss

ShopifyCLAUDE.md

hydrogen / cookbook

Shopify/hydrogen/cookbook/CLAUDE.md

code to explain why, not what - Naming: Follow existing recipe patterns (kebab-case) ## Testing ```bash # Run all cookbook tests pnpm test # Run validation tests only pnpm test -- validate.test.ts # Full validation

2.1k6mo agoDiscuss

ShopifyCLAUDE.md

hydrogen / e2e

Shopify/hydrogen/e2e/CLAUDE.md

Testing Guidelines ## Quick Reference ### The Golden Rules 1. **Use role-based locators** - Never CSS classes unless absolutely necessary 2. **Assert absence broadly, presence specifically** - Wide net for "not there", scoped

2.1k6mo agoDiscuss

CloudflareCLAUDE.md

templates

cloudflare/templates/CLAUDE.md

template management and validation - **Turbo build system** for managing multiple projects - **Playwright E2E tests** for template validation ## Essential Commands ### Development Commands ```bash # Check all templates and code quality pnpm

2.1k9mo agoDiscuss

AnthropicCLAUDE.md

anthropic-sdk-typescript

anthropics/anthropic-sdk-typescript/CLAUDE.md

throws ` requires Node.js or a Node-compatible runtime`. Add runtime and type-level parity tests, and keep the internal import lazy. - Never hide imports from bundlers (`webpackIgnore` comments, variable specifiers

2.1k4mo agoDiscuss

LumiwealthCLAUDE.md

lumibot

Lumiwealth/lumibot/CLAUDE.md

exact package candidate before downstream Dev. - The consuming BotSpot candidate must pass every Playwright test owned by its scope locally before Dev; focused tests never qualify. If Agent is scoped

2.1k19d agoReads credentialsDiscuss

gregghCLAUDE.md

claude-code.nvim

greggh/claude-code.nvim/CLAUDE.md

interactions, and various utilities to enhance AI-assisted development within Neovim. ## Essential Commands - Run Tests: `env -C /home/gregg/Projects/neovim/plugins/claude-code lua tests/run_tests.lua` - Check Formatting: `env -C /home/gregg/Projects/neovim/plugins/claude-code stylua lua/ -c` - Format Code

2.1k17mo agoDiscuss

AnthropicCLAUDE.md

cwc-workshops / agent-battle

anthropics/cwc-workshops/agent-battle/CLAUDE.md

often loses to three targeted lines they wrote themselves. Point them at `--eval` to test their own ideas fast. - Encourage them to **read** `my_agent.py` lines 30-80 before changing anything

2.1k4mo agoDeletes or force-pushesDiscuss

arcsin1CLAUDE.md

oh-my-ppt

arcsin1/oh-my-ppt/CLAUDE.md

刷新机制 - 修 bug 优先补最小定向回归测试，必要时覆盖相邻入口 - 验证时跑最相关的最小测试集；不要跑 `npm run lint` 或 `npm run build` ## Testing - 框架：Vitest + happy-dom，测试文件放 `tests/unit/` 下，按功能域分子目录，文件名 `*.test.ts` - 跑测试：`pnpm test`，跑单个文件：`pnpm

2.1k3mo agoDiscuss

digitalsambaCLAUDE.md

claude-code-video-toolkit

digitalsamba/claude-code-video-toolkit/CLAUDE.md

Validate everything without uploading (also reports auth readiness) uv run tools/youtube_upload.py --video out/video.mp4 --title "Test" --dry-run --json-out ``` **Setup is OAuth, not an API key** (uploads act on behalf

2.1k21d agoReads credentialsDiscuss

agentset-aiCLAUDE.md

agentset

agentset-ai/agentset/docs/CLAUDE.md

orient structure. Break up text-heavy paragraphs. - Prerequisites at start of procedural content - Test all code examples before publishing - Match style and formatting of existing pages - Include both basic

2.1k8mo agoDiscuss

LetsFGCLAUDE.md

LetsFG

LetsFG/LetsFG/CLAUDE.md

restate. ## Rule 8 — Fail loud "Completed" is wrong if anything was skipped silently. "Tests pass" is wrong if any were skipped. Default to surfacing uncertainty, not hiding it. ## Metrics source

2.1k20d agoDiscuss

superglue-aiCLAUDE.md

superglue

superglue-ai/superglue/CLAUDE.md

CLAUDE.md ## Quick Reference ```bash npm run dev # Start all (turbo) npm run test # Vitest npm run lint:fix # Prettier npm run type-check # TS check ``` Ports: 3000 (GraphQL

2.1k12mo agoDiscuss

StripeCLAUDE.md

stripe-python

stripe/stripe-python/.claude/CLAUDE.md

stripe-python ## Testing - Run all tests: `just test` - Run a specific test by name: `just test-one test_name` - Run a specific test file: `just test tests/path/to/test_file.py` ## Formatting & Linting - Format

2.1k55d agoDiscuss

omnimind-aiCLAUDE.md

OmniBot

omnimind-ai/OmniBot/CLAUDE.md

debug APK (develop flavor) ./gradlew assembleDevelopDebug # Build release APK (production flavor) ./gradlew assembleProductionRelease # Run tests ./gradlew test # Run instrumented tests ./gradlew connectedAndroidTest # Lint checking ./gradlew lint # Install debug

2k6mo agoDiscuss

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.