agentleFS
Sign inSign up

CLAUDE.md examples from real projects

How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.

Popular:code reviewtestingpdfMCP serverfrontendsecuritydocumentation
Best matches · from page 13Worked for most · soon
“testing” remove filterHugging Face remove filter
geekjourneyxCLAUDE.md

md2wechat-skill

geekjourneyx/md2wechat-skill/CLAUDE.md

platforms/openclaw/md2wechat/SKILL.md` 5. 这类任务不以“代码改完”为完成标准，必须完成高价值入口文档校准，防止代码和文档漂移 6. 这类任务如果会触发 CI 或 release，不要只跑 `go test`。必须先跑和云端一致的本地 gate：`make quality-gates` ### 新增命令 / 新增功能后的测试闭环 新增命令和新增功能，不能只要求“补测试”，而要按第一性原理补**有效测试**。 先问 3 个问题

3.7k2mo agoDiscuss
strukto-aiCLAUDE.md

mirage

strukto-ai/mirage/CLAUDE.md

same layout and the same semantics. ## Development ### Commands - Python lives in `python/` (`mirage/`, `tests/`). Setup: `cd python && uv sync --all-extras --no-extra camel`. Add dependencies with `uv add`. Test

3.7k2mo agoDiscuss
sergebulaevCLAUDE.md

linkedin-skills

sergebulaev/linkedin-skills/CLAUDE.md

scheduledTime`, `platformSettings` on a draft or scheduled post), and `DELETE /delete-post/ `. Also `post-logs`, `test-connection`, `platform-limits` and `webhooks`. Prefer editing a scheduled post over delete-and-recreate. - **Image

3.6k4mo agoReads credentialsDiscuss
dembrandtCLAUDE.md

dembrandt

dembrandt/dembrandt/CLAUDE.md

dembrandt.com --mobile node dist/index.js dembrandt.com --slow node dist/index.js dembrandt.com --stealth node dist/index.js install-browser ``` ### Testing ```bash npm test # unit tests npm run liveness # live extraction smoke on sites-smoke.json (same

3.6k10mo agoDiscuss
bytebaseCLAUDE.md

dbhub

bytebase/dbhub/CLAUDE.md

compiled server - Dev: `pnpm run dev` - Runs server with tsx (no compilation needed) - Test: `pnpm test` - Run all tests - Test Watch: `pnpm test:watch` - Run tests in watch mode - Integration

3.6k12d agoReads credentialsDiscuss
simonlin1212CLAUDE.md

TradingAgents-astock

simonlin1212/TradingAgents-astock/CLAUDE.md

ticker_component` 已加兜底自动转码，但不同模型表现仍有差异。 ### 测试 **干净 clone（`pip install -e .` 不带 `[agentsdk]`）跑 `pytest tests/` 应当是 512 passed / 13 skipped / **0 failed**（v0.5.20 实测，Python 3.13）。出现 failed 就是真回归。** 需要可选依赖的用例用

3.6k10d agoDiscuss
JetBrainsCLAUDE.md

kotlinconf-app

JetBrains/kotlinconf-app/CLAUDE.md

development mode) ./gradlew :app:webApp:wasmJsBrowserDevelopmentRun # Run backend server ./gradlew :backend:run # Run backend tests ./gradlew :backend:test # Run shared module tests (JVM target) ./gradlew :app:shared:jvmTest # Run core

3.6k3mo agoDiscuss
skyhook-ioCLAUDE.md

radar

skyhook-io/radar/CLAUDE.md

embed step! cd web && npm run build && cd .. && go build -o radar ./cmd/explorer ``` ### Build / test / run `make help` lists every target — read the Makefile when uncertain

3.5k36d agoReads credentialsDiscuss
ding113CLAUDE.md

claude-code-hub

ding113/claude-code-hub/CLAUDE.md

Code** - Never use emoji characters in any code, comments, or string literals 2. **Test Coverage** - All new features must have unit test coverage of at least 80% 3. **i18n Required

3.4k2mo agoReads credentialsDiscuss
RunMaestroCLAUDE.md

Maestro

RunMaestro/Maestro/CLAUDE.md

storage, or error pattern | [AGENT-INFRA.md](docs/agent-guides/AGENT-INFRA.md) | | UI component, modal, or theme usage | [UI-PATTERNS.md](docs/agent-guides/UI-PATTERNS.md) | | Test mock, factory, or setup pattern | [TEST-PATTERNS.md](docs/agent-guides/TEST-PATTERNS.md) | | Renderer service or constant | [RENDERER-SERVICES.md](docs/agent-guides/RENDERER-SERVICES.md) | | Process spawning

3.4k50d agoDiscuss
MicrosoftCLAUDE.md

Power-Fx

microsoft/Power-Fx/CLAUDE.md

Debug, Release, DebugAll, ReleaseAll, Debug462, Debug70) dotnet build src/Microsoft.PowerFx.sln -p:Configuration=Release # Run all tests dotnet test src/Microsoft.PowerFx.sln # Run tests for a specific project dotnet test src/tests/Microsoft.PowerFx.Core.Tests.Shared/Microsoft.PowerFx.Core.Tests.Shared.csproj # Run a single

3.4k4mo agoDiscuss
MicrosoftCLAUDE.md

Power-Fx / src

microsoft/Power-Fx/src/CLAUDE.md

Windows # Default configuration is DebugAll if not specified # Output packages go to src/outputpackages/ ``` ### Running Tests ```bash # From src/ directory .\runLocalTests.cmd [Configuration] # Windows (uses VSTest) # Or using dotnet CLI (from solution

3.4k4mo agoDiscuss
himself65CLAUDE.md

finance-skills

himself65/finance-skills/CLAUDE.md

MONOREPO manifest — declares sub-plugins opencli-plugins/ # Source for opencli adapters (Node code, has tests) tradingview/ # TradingView desktop reader (drives the tradingview-reader skill) opencli-plugin.json # Per-plugin manifest package.json # Node

3.3k56d agoDiscuss
giancarloerraCLAUDE.md

SocratiCode

giancarloerra/SocratiCode/CLAUDE.md

discover candidate entry points (auto-detected via orphans, conventional names like `main()`, framework routes, tests). - `codebase_symbol` gives a 360° view of one function: definition, callers, callees. - `codebase_symbols` lists

3.3k7mo agoDiscuss
samberCLAUDE.md

cc-skills-golang

samber/cc-skills-golang/CLAUDE.md

Bash(benchstat:*)` | Benchmark or performance skills | | `Bash(dlv:*)` | Troubleshooting or debugging skills | | `Bash(gotests:*)` | Testing skills that generate test scaffolding | | `Bash(protoc:*)` | gRPC or protobuf skills | | `Bash(swag:*)` | Swagger/OpenAPI skills

3.3k42d agoPipes a download into a shellDiscuss
liaohch3CLAUDE.md

claude-tap

liaohch3/claude-tap/.claude/CLAUDE.md

single source of truth for engineering rules: - Follow [`../AGENTS.md`](../AGENTS.md) for all workflow, testing, and review requirements. Skill layout for multi-agent compatibility: - Canonical skills directory: `.agents/skills/` - Claude compatibility path

3.2k37d agoDiscuss
cortex-docsCLAUDE.md

cortex

cortex-docs/cortex/CLAUDE.md

running in watch mode, if yes do not start another process - if need browser testing prefer using playwright mcp tools

3.2k39d agoDiscuss
punitaraniCLAUDE.md

fli

punitarani/fli/CLAUDE.md

structures ## Development Commands ### Core Development Tasks ```bash # Install dependencies uv sync --all-extras # Run tests (use these specific commands) make test # Standard test suite (offline only) make test-fuzz

3.2k11d agoDiscuss
TanStackCLAUDE.md

ai

TanStack/ai/CLAUDE.md

published package changed. **Ponytail skill (mandatory).** Before planning, writing, or editing application code, tests, or examples, load `.claude/skills/ponytail/SKILL.md` and follow it. Do not design or implement without it. Ponytail does

3.1k13d agoReads credentialsDiscuss
GH05TCREWCLAUDE.md

pentestagent

GH05TCREW/pentestagent/CLAUDE.md

PentestAgent — CLAUDE.md ## Project overview **PentestAgent** (v0.2.0) is an AI-powered penetration testing framework built in Python. It wraps LiteLLM to support any provider (Anthropic, OpenAI, etc.) and exposes

3.1k9d agoReads credentialsDiscuss
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.