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 strzhao/autopilot --skill autopilot-projectgit 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/skills/strzhao/autopilot/autopilot-project)<a href="https://agentmods.dev/skills/strzhao/autopilot/autopilot-project"><img src="https://agentmods.dev/badge/skills/strzhao/autopilot/autopilot-project/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/strzhao/autopilot/autopilot-project"><img src="https://agentmods.dev/badge/skills/strzhao/autopilot/autopilot-project.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 | $0.00039 | $0.01226 |
| Opus 5.5 | $0.00016 | $0.00490 |
| Sonnet 5.5 | $0.00008 | $0.00245 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
autopilot-project 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 1mo 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.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autopilot Project — 多任务项目编排
管理 .autopilot/project/ 下的项目文件，为大型多任务目标提供 DAG 驱动的任务编排。
项目文件结构
.autopilot/project/
├── design.md # 整体架构设计
├── dag.yaml # 任务 DAG
└── tasks/
├── <id>.md # 任务简报（文件名 = dag.yaml id）
├── <id>.handoff.md # 任务完成后的交接文档
└── ...
DAG YAML 格式
project: "<name>"
created_at: "<ISO timestamp>"
tasks:
- id: "001-wire-schema"
title: "定义共享协议包"
depends_on: []
status: pending # pending | in_progress | done | failed | skipped
- id: "002-db-models"
title: "新增数据模型"
depends_on: ["001-wire-schema"]
status: pending
任务简报格式
---
id: "<文件名 stem，如 T4 → tasks/T4.md>"
depends_on: ["XXX", "YYY"]
---
## 目标
(一句话)
## 架构上下文
(从 design.md 摘取相关部分)
## 输入/输出契约
- 输入: ...
- 输出: ...
## 验收标准
1. ...
Handoff 格式
## 实现摘要
(做了什么，关键决策)
## 文件变更
(新增/修改的文件)
## 下游须知
(接口、约定、注意事项)
## 偏差说明
(与简报的任何偏差及原因)
核心原则
- 原子性: 每个任务是独立的 autopilot 运行，有完整的 design → implement → qa → merge 闭环
- 信息隔离: 任务间通过 handoff 文件传递上下文，不共享会话状态
- 上下文预算 <10KB: L0 DAG 概览 + L1 任务简报 + L2 依赖 handoff + L3 架构摘要
- Handoff 链: 每个任务完成后写 ≤500 字 handoff，只有直接下游读取
- 失败隔离: 一个任务失败不影响无依赖关系的其他任务
- 自动编排 + 人工兜底: 高信心时自动链接下一任务；低信心或失败时释放循环等待用户
- AI Native: 任务粒度、DAG 结构、handoff 内容由 AI 运行时判断，不硬编码规则
Auto-Chain 机制
任务完成时（phase=done），如果 AI 在 merge 阶段评估为高信心，stop-hook 自动启动下一个就绪任务：
- AI 通过设置 frontmatter
next_task字段信号高信心 - stop-hook 读取该字段并创建新状态文件（
auto_approve: true） auto_approve使下一个任务在高信心时跳过人工审批门（design 审批 + QA 审批）；standard 单任务 design 步骤 4 AI 自治默认（例外征询时不设）也可设置（详见 autopilot SKILL.md 步骤 4）- 所有任务完成后自动触发全项目 QA（
mode: "project-qa"）
全项目 QA（mode: "project-qa"）
stop-hook 检测到全部任务 status: done 后，创建 mode: "project-qa" 状态文件并从 phase: "qa" 开始。与单任务 QA 的差异：
- 加载：
.autopilot/project/design.md+dag.yaml+ 状态文件## 任务完成摘要（全 handoff 汇总） - 变更范围：项目创建以来的全部
git diff（而非单任务 diff） - Tier 调整：Tier 0 跳过（无项目级红队测试）；Tier 1 全量构建/测试/lint，重在验跨任务集成；Tier 1.5 从 design.md「跨任务设计约束 / Handoff 策略」提取集成场景（共享接口 / 数据流 / 命名一致性）；Tier 2 对照 design.md 审整体架构符合性 + 全变更范围质量
- 结果判定：全部 ✅ →
phase: "done"；有 ❌ →gate: "review-accept"（不进 auto-fix，项目级失败需人工判断修复范围与优先级）
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.
- 1mo ago Changed 29d16c528682
- 1mo ago First seen · 112 lines · 39 tokens per session scan A e00ad1c10252
autopilot-project is a skill published in the GitHub repository strzhao/autopilot (32 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 1,226 once invoked, about $0.0002 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 skills, from other repositories
continue
Autonomous work — find and execute ready tasks.
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.
sync
Rebuild PROJECTSTATE derived fields from artifact files.
prd
A Product Requirements Document (PRD) writer for large software initiatives. A PRD records the problem, goals, requirements, assumptions, and evidence before implementation begins.
roadmap
An implementation plan made from a technical specification, organized into phases, milestones, and dependencies.
debt
A command for showing and closing unanswered questions attached to project documents such as requirements, specifications, features, and designs. It can show questions for the whole project or for one document.