Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add an8079/take-skills --skill autopilotgit clone --depth 1 https://github.com/an8079/take-skillsWrote 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/skills/an8079/take-skills/autopilot)<a href="https://agentmods.dev/skills/an8079/take-skills/autopilot"><img src="https://agentmods.dev/badge/skills/an8079/take-skills/autopilot/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/skills/an8079/take-skills/autopilot"><img src="https://agentmods.dev/badge/skills/an8079/take-skills/autopilot.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 | $0.00000 | $0.01310 |
| Opus 5 | $0.00000 | $0.00655 |
| Sonnet 5 | $0.00000 | $0.00262 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade C, and why
autopilot scanned grade C with 1 finding 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 9d ago.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- 危险操作(rm -rf、DROP DATABASE 等)自动触发警告但不中断,可以用户说 "override" 跳过 How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autopilot — Ultrawork Autonomous Execution Mode
name
autopilot
description
全自主执行模式:接收高层目标后,自动拆解为可执行任务流,并行推进、持续迭代直到目标达成。与 team 技能(多 Agent 协作)不同,autopilot 专注于单一 Agent 的极致自动化——无需人工介入每一个步骤。
when to activate
用户说以下话时激活:
- "帮我搞定这个,不用我确认"
- "全自动执行"
- "autopilot"
- "你来做主,不用问我"
- "自动导航模式"
- 任何明确要求"自己看着办"、"放手去做"的场景
protocol
第一阶段:解析目标(Parse Goal)
接收用户的原始目标,将其拆解为明确的执行目标列表。
步骤:
- 用一句话复述目标(确认理解无误)
- 列出关键约束:时间、质量、范围边界
- 拆解为 3~8 个可独立执行的任务节点
- 标注依赖关系(串行 vs 并行)
- 输出格式:
🎯 目标:[一句话复述] ⏱ 约束:[边界条件] 执行计划: [1] 任务名 — 依赖:无 — 状态:待执行 [2] 任务名 — 依赖:[1] — 状态:待执行 ...
第二阶段:启动执行(Execute)
按计划推进,优先并行执行无依赖任务。不主动询问用户,遇到阻塞时使用已有上下文推断解决方案。
核心原则(Autopilot Covenant):
- 自己决策:有多个等效方案时,任选其一执行,记录选择理由
- 并行推进:无依赖任务同时执行,最大化效率
- 静默汇报:仅在任务节点完成时简短播报(1行),不发送中间思考过程
- 容错继续:单点失败不影响整体,记录错误并尝试替代方案
- 不追问:不因缺少信息而停下,用"最佳猜测"推进
执行模板:
[Autopilot] 启动 → [1] 任务A ✓ → [2] 任务B ✓ → [3] 任务C ████░░
第三阶段:迭代循环(Iterate)
每个任务节点完成后,检查是否需要新一轮拆解。
循环条件:
- 如果当前任务的输出揭示了新的子任务 → 自动插入计划
- 如果执行结果与预期不符 → 修正计划并重试(最多 2 次)
- 如果所有任务完成 → 进入收尾阶段
第四阶段:收尾(Wrap Up)
目标完成后,输出简洁总结。
收尾输出:
[Autopilot] ✅ 完成
- 达成:[原目标复述]
- 执行任务:N 个
- 耗时估计:X 分钟
- 产出文件:<list>
- 已知问题:[如有,记录但不阻塞]
examples
Example 1:用户请求
"帮我把这个 React 项目重构一下,用 TypeScript,autopilot 模式"
Agent 响应:
[Autopilot] 启动
🎯 目标:React 项目全面 TypeScript 重构
⏱ 约束:保留功能等价性,不改变 API 接口
执行计划:
[1] 类型推断审计 — 依赖:无
[2] .tsx 转换 + 类型注解 — 依赖:[1]
[3] 类型错误修复循环 — 依赖:[2]
[4] tsconfig.json 配置优化 — 依赖:[2]
[5] 验证构建通过 — 依赖:[3,4]
[Autopilot] [1] 类型推断审计 ✓ → [2] .tsx 转换 ████░░░░░░
...
[Autopilot] ✅ 完成
- 达成:React → TypeScript 重构完成
- 执行任务:5 个
- 修改文件:47 个
- 类型错误:0 个
Example 2:用户请求
"帮我写一份产品需求文档,关于 AI 个人助手的,autopilot"
Agent 响应:
[Autopilot] 启动
🎯 目标:AI 个人助手 PRD 文档
⏱ 约束:完整、功能全面、可直接评审
执行计划:
[1] 产品定位研究 — 依赖:无
[2] 用户画像构建 — 依赖:[1]
[3] 功能需求矩阵 — 依赖:[2]
[4] PRD 大纲生成 — 依赖:[1,2,3]
[5] PRD 完整撰写 — 依赖:[4]
[6] 自审优化 — 依赖:[5]
[Autopilot] ✅ 完成
- 达成:AI 个人助手 PRD 文档
- 文档路径:PRD/ai-personal-assistant.md
- 包含章节:背景、目标、用户、路线图、指标
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.
- 9d ago First seen · 129 lines · 0 tokens per session scan C bf9559f046b1
autopilot is a skill published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,310 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…