VercelCLAUDE.mdnext-skills
vercel-labs/next-skills/CLAUDE.md
The skills here have moved to https://github.com/vercel/next.js/tree/canary/skills See AGENTS.md.
CLAUDE.md examples from real projects
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Most stars first · from page 28Worked for most · soon
VercelCLAUDE.md
Human-Agent-SocietyCLAUDE.mdCORAL
Human-Agent-Society/CORAL/CLAUDE.md
An orchestration system for autonomous coding agents — agents follow a CORAL.md guide, run experiments, share knowledge, and loop forever. Core pattern: Spawn agents → agents read CORAL.md → commit changes → grader daemon scores them → repeat Key concepts: - Agents are the optimizers — Claude Code (or Codex / Cursor / Kiro / OpenCode) subprocesses, each in its own git worktree. - Shared state via .coral/ — split into public/ (visible to agents through a runtime-specific symlink like…
shanraisshanCLAUDE.mdcodex-cli-best-practice
shanraisshan/codex-cli-best-practice/CLAUDE.md
A best practices reference repository for Codex CLI (v0.121.0+) and Claude Code, demonstrating the Agent → Skill orchestration pattern through a weather data system example. This is a documentation and configuration reference, not a traditional application codebase. Maintained by Shayan Raees (@shanraisshan). Companion repos: claude-code-best-practice, codex-cli-hooks, claude-code-hooks. The repo demonstrates four interconnected systems: Run it: codex then prompt "Fetch the current weather for Dubai in Celsius and create the SVG weather card output using the repo." Profiles (codex --profile <name>):…
zhu1090093659CLAUDE.mdspec_driven_develop
zhu1090093659/spec_driven_develop/CLAUDE.md
Read AGENTS.md first. It is the shared project-level instruction source for Codex, OpenCode, Cursor, Claude Code, and other Markdown-aware coding agents. Claude Code-specific reminders:
NVIDIACLAUDE.mdNVFlare
NVIDIA/NVFlare/CLAUDE.md
NVIDIA FLARE (NVFlare) is a domain-agnostic, open-source Python SDK for federated learning. It allows ML/DL workflows to be adapted to a federated paradigm, enabling secure, privacy-preserving distributed multi-party collaboration. Key capabilities: PyTorch/TensorFlow/Scikit-learn/XGBoost support, horizontal and vertical FL, built-in FL algorithms (FedAvg, FedProx, FedOpt, Scaffold, Ditto), privacy preservation (differential privacy, homomorphic encryption, PSI). NVFlare uses a server-client federated architecture: - Server: Runs a Controller that schedules Tasks and aggregates results - Clients: Run Executors that execute tasks on local data -…
NVIDIACLAUDE.mdNVFlare / auto-fl-research
NVIDIA/NVFlare/research/auto-fl-research/CLAUDE.md
Read program.md first. Treat it as the general control plane. Then read the active task profile; use tasks/cifar10/profile.md by default. Use AGENTS.md and the active task's mutation_schema.yaml only as supporting guardrails.
Pantheon-SecurityCLAUDE.mdmedusa
Pantheon-Security/medusa/CLAUDE.md
Unit tests ALONE are not sufficient. Before any git push, git tag, gh release create, or twine upload — all four commands below MUST run green AND their output MUST…
im4codesCLAUDE.mdimcodes
im4codes/imcodes/CLAUDE.md
IM.codes is a specialized instant messenger for AI coding agents — a three-tier system for remote terminal access, file browsing, multi-agent workflows, and session management: Node.js process that manages AI agent sessions via tmux. Entry point: src/index.ts (commander CLI). Self-hosted Node.js backend (Hono). Has its own tsconfig.json and node_modules.
lich0821CLAUDE.mdccNexus
lich0821/ccNexus/CLAUDE.md
ccNexus 是一个智能 API 端点轮换代理，专为 Claude Code 和 Codex CLI 设计。 核心功能： - 多端点轮换与自动故障转移 - API 格式转换（Claude ↔ OpenAI ↔ Gemini） - Codex Token Pool 管理（自动轮换、刷新、失效隔离） - 实时统计与监控 - WebDAV 云同步 两种运行模式： - 桌面模式：基于 Wails v2 的跨平台 GUI 应用（cmd/desktop/） - 服务器模式：无头 HTTP API 代理（cmd/server/） 代理层 (internal/proxy/proxy.go) - 管理多个 API 端点，自动故障转移 - 跟踪当前端点和活动请求 - 使用连接池优化的 HTTP 客户端 - 处理流式和非流式响应 转换器 (internal/transformer/) - 在不同 API 格式之间转换请求和响应 - 支持流式传输的增量转换 - 处理工具调用和函数调用 - 类型定义：internal/transformer/types.go 存储层 (internal/storage/sqlite.go) - SQLite WAL 模式数据库 - 管理端点、凭证、使用统计、应用配置 - 线程安全操作 代理服务器提供以下端点（internal/proxy/proxy.go…
iamfakeguruCLAUDE.mdagent-md
iamfakeguru/agent-md/CLAUDE.md
No summary in the file. Open it to read it.
bitjaruCLAUDE.mdstyleseed / engine
bitjaru/styleseed/engine/CLAUDE.md
A design-method engine whose goal is to make expert design judgment repeatable by coding agents, not to replace designers with aesthetic preferences. Preserve approved project choices; surface unsupported choices rather than silently replacing the project's design system. PRODUCT-PRINCIPLES.md defines the goal and authority boundaries. Different product jobs use different output grammars. Skins provide materials; they never define the method. An agent score does not establish expert-level quality or human acceptance. Resolve the artifact boundary first. If either .styleseed/project.json or .styleseed/artifacts/index.json…
guanyangCLAUDE.mdopen-agent-hub
guanyang/open-agent-hub/CLAUDE.md
Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed. Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment. Don't assume. Don't hide confusion. Surface tradeoffs. Before implementing: - State your assumptions explicitly. If uncertain, ask. - If multiple interpretations exist, present them - don't pick silently. - If a simpler approach exists, say so. Push back when warranted. - If something is unclear, stop. Name what's confusing. Ask. Minimum code that…
bouobCLAUDE.mdtickets_hunter
bouob/tickets_hunter/CLAUDE.md
本檔提供給 AI 編碼工具（Claude Code、Cursor、Copilot、Aider 等）與外部貢獻者， 說明 Tickets Hunter 的架構約定、程式碼規範與提交流程。 專案：Tickets Hunter — 多平台搶票自動化系統 授權：GNU GPL 貢獻流程：見 CONTRIBUTING.md 本專案是一項 AI 輔助軟體工程實驗，程式碼主要透過自然語言指令與 AI 協作產生。 歡迎 fork 後用不同的 AI 工具實驗，但請遵守下方的法律與倫理邊界。 - 本軟體僅供教育與研究用途，完整條款見 LEGAL_NOTICE.md。…
russelleNVyCLAUDE.mdthree-man-team
russelleNVy/three-man-team/CLAUDE.md
Grep before Read. Never read a whole file to find one thing. Do not re-read files already in context this session. Project Owner role is set by the human. Do not ask.
luongnv89CLAUDE.mdasm
luongnv89/asm/CLAUDE.md
agent-skill-manager (asm) — a TypeScript CLI plus ink/React TUI that manages Agent Skills installed for Claude Code, Codex, Gemini, and OpenClaw. npm test is vitest run src/, and that argument is a substring filter on the test path, not a directory — website-src/src/tests/ matches it too, so npm run test:site is a subset of npm test, not a separate leg. Only tests/e2e/ is excluded. Measured timings and evidence: docs/AGENT_ENVIRONMENT.md. npm run test:coverage is vitest run --coverage src/ with @vitest/coverage-v8 (5.x,…
MicrosoftCLAUDE.mdpower-platform-skills / power-automate
microsoft/power-platform-skills/plugins/power-automate/CLAUDE.md
This is the marketplace plugin wrapper for FlowAgent (Power Automate cloud flow tooling). Flow-definition rules, the two-provider auth model (Azure CLI + MSAL), the error reference, and known issues are documented in references/ — see definition-reference.md, connection-patterns.md, and error-troubleshooting.md. Read those before building or editing flows. This file only covers plugin-local specifics; see AGENTS.md (this folder) for the tool-routing rule. - skills/ — verb-first user-invocable skills (create-flow, build-flow, debug-flow, diagnose-flow, manage-flows, browse-flows, manage-desktop-flows, route-environments, setup) - references/ — shared docs…
PipelexCLAUDE.mdpipelex
Pipelex/pipelex/CLAUDE.md
make targets activate the virtual environment themselves; anything else (pytest, pipelex, pipelex-dev) runs from .venv/bin/ (.venv\Scripts\ on Windows), never bare. The Makefile is the reference for every target and alias;…
PipelexCLAUDE.mdpipelex
Pipelex/pipelex/docs/CLAUDE.md
This file documents non-obvious architectural decisions for the docs site (docs.pipelex.com). Read this before modifying anything under docs/. Legacy URL paths (e.g. home/1-features/) are redirected to current clean paths (e.g.…
PipelexCLAUDE.mdpipelex / tests
Pipelex/pipelex/tests/CLAUDE.md
Instead of running the full suite (make agent-test) every time, run only the tests relevant to what you changed. Replace <paths> with the test directories from the mapping below. Concatenate…
apifyCLAUDE.mdmcpc
apify/mcpc/CLAUDE.md
mcpc is a universal command-line client for the Model Context Protocol (MCP), which maps MCP to intuitive CLI commands for shell access, scripts, and AI coding agents. mcpc can connect to any MCP server over Streamable HTTP or stdio transports, securely login via OAuth credentials and store credentials, and keep long-term sessions to multiple servers in parallel. It supports all major MCP features, including tools, resources, prompts, asynchronous tasks, and notifications. mcpc is handy for manual testing of MCP servers,…
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.