REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
此仓库是合集,包含 10 个 Skill;它是汇总多个来源 Skill 的清单
🏆 Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/ryanalberts-best-of-agent-harnesses)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 best-of-Agent-Harnesses | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | RyanAlberts | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 10 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 1,564 | 470,165 | 234,528 | 150,695 | 144,727 |
| 最近代码更新 | 2026年11月16日 | 2026年11月20日 | 2026年4月20日 | 2026年11月20日 | 2026年11月19日 |
| 许可证 | CC-BY-SA-4.0 | MIT | – | Apache-2.0 | MIT |
RyanAlberts 提供的 10 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
只安装你真正会用的。点开名称查看该 Skill 的安装方法
如果想要全部,可以让 AI 一次装好。安装前请先了解 2 点
上传到 Claude 网页版和应用:需要上传 10 次,每个 Skill 一个 ZIP 文件。打开下方列表中的各个 Skill 即可下载
Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
Checks which instruction files (AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, Copilot instructions) each coding agent loads from a repo, what gets cut or skipped, and whether the commands those files document still work. Use when the user asks whether Claude Code, Codex, Gemini CLI, Cursor, OpenCo…
Claim checker that audits a coding agent's statements that tests pass or a build is clean against its own session transcripts: whether a matching run happened before the claim, whether it passed, and whether code changed after it. Use when the user asks whether the agent really ran the tests, how o…
Guardrail tester that checks whether the permission rules and PreToolUse hooks already set up in Claude Code, Codex, Gemini CLI, OpenCode, or Cursor stop a battery of dangerous commands, including wrapped, reordered, and full-path forms that slip past prefix rules, and measures prompt friction on t…
Test-drives coding agents (Claude Code, Codex, Gemini CLI) on tasks mined from the user's own git history: each agent gets a past commit message in a fresh copy of the repo, and the repo's own tests score how many tasks it completes, dollars per task, minutes, and change size. Use when the user ask…
Regression check for coding agents: shows how the agent behaved before and after each harness update, model switch, or week in the user's own Claude Code or Codex history, and finds the point where it changed. Use when the user says the agent's quality dropped or it got worse, dumber, lazier, or de…
Rule enforcer that finds which written rules in AGENTS.md, CLAUDE.md, and GEMINI.md a coding agent keeps breaking, counts every violation in recent Claude Code, Codex, Gemini CLI, and OpenCode sessions, and turns each broken rule into a hook that blocks it, tested by replaying the past violations.…
Runaway guard: a hook that stops a live Claude Code or Codex session when the agent loops on the same tool call, keeps failing, or exceeds a dollar cap. Use when the user wants a spending cap, budget limit, or cost ceiling for interactive agent sessions (the built-in --max-budget-usd works only in…
Sandbox audit that probes, from inside a live coding-agent session, what the agent can really reach: secret files it can open, secret-like environment variables, files that git, the shell, the editor, or the harness later run (git hooks, shell startup files, harness settings), writes outside the pr…
Waste report for coding-agent sessions in Claude Code, Codex, Gemini CLI, and OpenCode: finds where tokens, money, and time were wasted, and the fix for each kind of waste. Use when the user asks where tokens or money went or why the bill is so high; about habits that burn tokens, such as re-readin…
Grades MCP tool definitions the way a model reads them: a clear purpose, described parameters, safe annotations such as readOnlyHint, and the token size of every tool. Use when an author wants to lint, grade, or review an MCP server's tools, tool descriptions, or input schemas before release; when…
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodexCursorGemini CLIGitHub CopilotOpenCode
依据开发者 README 和 repo 中的文件夹
此仓库有 10 个 Skill。请从上方列表选一个,该 Skill 的页面有完整安装方法,包括让 AI 安装和 ZIP 文件
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
已隐藏作者的命令 · 它不是从 GitHub 上的这个仓库安装 · 可改用本页其他已通过检查的方式
摘自开发者 README,会下载并运行开发者的代码
提问、分享技巧或报告无法使用。按“有帮助”数量排序。