Borrowing it
Nothing to install: this file belongs to strzhao/autopilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/strzhao/autopilot/main/CLAUDE.mdgit clone --depth 1 https://github.com/strzhao/autopilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/strzhao/autopilot/claude-md)<a href="https://agentmods.dev/instructions/strzhao/autopilot/claude-md"><img src="https://agentmods.dev/badge/instructions/strzhao/autopilot/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/strzhao/autopilot/claude-md"><img src="https://agentmods.dev/badge/instructions/strzhao/autopilot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01603 | $0.01603 |
| Opus 5.5 | $0.00641 | $0.00641 |
| Sonnet 5.5 | $0.00321 | $0.00321 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
autopilot CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code 插件市场
String 维护的 Claude Code 插件集合。
- 维护者: String Zhao（[email protected]）
- 仓库: https://github.com/strzhao/autopilot.git
插件索引
详细能力见各插件 plugins/<name>/README.md 与 SKILL.md，本表只做导航。
| 插件 | 版本 | 类型 | 一句话 |
|---|---|---|---|
| autopilot | v3.80.0 | Skill + Hook | AI 自动驾驶 loop engine：状态机驱动目标→合并全流程闭环 + 红蓝对抗 + QA 谓词闸门 + 知识工程 + worktree 自动初始化。品牌与版本演进史见 README 与 git log |
| writer-skill | v1.12.0 | Skill | 写作技能包：博客向 / 技术文档向 / 专业技术博客向 / 阮一峰风格 / 文章评价 |
| summarizer | v1.0.0 | Skill | 多模态内容摘要（文章/视频/音频 → flomo） |
| task-notifier | v1.1.0 | Hook | 任务完成系统提示音 |
⚠️ 核心开发原则
源码唯一性（Single Source of Truth）
所有插件修改必须在本仓库源码（plugins/）中进行，禁止直接改 ~/.claude/plugins/cache/。
- 缓存目录是只读副本，在那里改不会回流到仓库，会导致版本分叉
- 历史教训：autopilot v2.8.0 一次 SKILL.md 整体重写曾意外回退 v2.9.0~v2.10.0 的功能，缓存却继续迭代到 v2.13.0，源码与运行版本长期不一致
- 流程：改源码 → 提交 → 重新安装插件
版本管理（升级时必须全部同步）
| 文件 | 说明 |
|---|---|
plugins/<name>/.claude-plugin/plugin.json |
插件系统据此检测新版本，遗漏 = 用户无法更新 |
plugins/<name>/package.json（如存在） |
npm 包版本 |
.claude-plugin/marketplace.json |
仓库级索引，按 name 字段定位条目更新 version |
本文件「插件索引」表中的 vX.Y.Z |
列表展示版本号 |
autopilot-commit 已通过"读 CLAUDE.md + grep 校验"动态发现这些位置，新增版本文件时同步更新本表即可。
description 只写能力简介：plugin.json / marketplace.json 的 description 保持一段可读的能力概述（百字级），禁止把版本变更说明以括号追加进去（历史教训：v3.38→v3.74 逐版追加堆到 ~10KB 且两处不同步，v3.74.2 已瘦身）。变更说明只进插件 README 顶部版本块与 git log；改 marketplace.json 条目时按 name 字段 select 定位（.plugins[0] 未必是目标插件）。
开发规范
- Skill 插件：
plugins/<name>/skills/<skill-name>/SKILL.md必需。详见document/skill_best_practices.md - Hook 插件：
plugins/<name>/hooks/hooks.json配置匹配规则，脚本用${CLAUDE_PLUGIN_ROOT}引用，超时默认 10s。详见document/hooks.md - MCP 配置：
.mcp.json中用${ENV_VAR}引用敏感信息，禁止硬编码
贡献流程
- 新建
plugins/<name>/与.claude-plugin/plugin.json - 实现功能 + 写 README.md
- 更新
.claude-plugin/marketplace.json与本文件「插件索引」 - 本地验证后提交 PR
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed 4d1b9e8a7878
- 10d ago Changed · +1 lines · +123 tokens per session 48d3de61c400
- 17d ago Changed · -1 lines · -40 tokens per session e96b9d824ad7
- 1mo ago Changed · +2 lines · +137 tokens per session fe9098c6bd65
- 1mo ago Changed c22aeac6cddf
- 1mo ago Changed 9defa5695701
- 1mo ago Changed c9add835c00d
- 1mo ago Changed f468b6b171bf
- 1mo ago Changed · -5,640 tokens per session 92581fb4ec13
- 1mo ago First seen · 80 lines · 7,023 tokens per session scan A 85e9f88353de
autopilot CLAUDE.md is an instructions file published in the GitHub repository strzhao/autopilot (32 stars, last pushed yesterday), licensed MIT. It adds 1,603 tokens to every session, about $0.0064 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.