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 xushuodasd/VIBE-Claude-Plugin --skill vibe-autopilotgit clone --depth 1 https://github.com/xushuodasd/VIBE-Claude-PluginWrote 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/xushuodasd/vibe-claude-plugin/vibe-autopilot)<a href="https://agentmods.dev/skills/xushuodasd/vibe-claude-plugin/vibe-autopilot"><img src="https://agentmods.dev/badge/skills/xushuodasd/vibe-claude-plugin/vibe-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/xushuodasd/vibe-claude-plugin/vibe-autopilot"><img src="https://agentmods.dev/badge/skills/xushuodasd/vibe-claude-plugin/vibe-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 | $0.00027 | $0.02873 |
| Opus 5 | $0.00014 | $0.01437 |
| Sonnet 5 | $0.00005 | $0.00575 |
| Haiku 4.5 | $0.00003 | $0.00287 |
Grade A, and why
vibe-autopilot 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 11d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
自动驾驶工作流 (Autopilot 24/7)
1. 文档目的
赋予 AI “全自动、不间断”的执行能力。在需求沟通阶段充分提问与确认，但一旦进入正式开发阶段，自动串联所有 VIBE 工作流（编码 -> 测试 -> 审查 -> 迭代），期间禁止停顿等待用户确认，自动采用最优解执行，直到最终交付。
2. 自动驾驶核心法则 (Smart Autopilot)
- 需求期充分沟通：在需求分析和架构设计阶段，必须主动向用户提问，澄清模糊点，确保方向完全正确。
- 开发期绝对静默 (NO HUMAN PAUSES)：一旦需求确认并进入正式编码阶段（阶段二），禁止提问。除非遇到严重且无法自行解决的环境死锁，否则禁止使用“您看这样可以吗？”、“需要我继续吗？”等话术，遇到分支选择时直接采用最优解。
- 状态机依赖 (Document as State)：禁止依赖大脑记忆！所有的进度、状态必须实时更新到
tasks.md中。如果感觉上下文变慢或混乱，主动提示用户使用/clear清理上下文，随后读取tasks.md即可满血复活。 - 事不过三熔断机制 (Circuit Breaker)：在处理报错、跑测试或解决依赖冲突时，如果同一个问题连续尝试修复超过 3 次均失败，必须立即停止死磕！将该任务在
tasks.md中标记为[Blocked]，记录原因，然后强制跳过，去执行下一个未完成的任务。
3. 24小时全链路循环引擎
当用户触发此工作流时，严格按照以下顺序执行：
阶段一：需求沟通与架构规划（允许且鼓励提问）
- 自动执行
vibe-analyze-req：当用户是从头开始一个全新项目时，触发此技能。与用户进行多轮对话，澄清项目背景、核心功能、UI 风格（如深色工业风）等细节。 - （如果是已有项目的新需求，则触发
vibe-analyze-new）。 - 生成核心文档：确认需求后，生成 PRD（需求文档），并自动执行
vibe-architecture和vibe-database生成架构与数据库文档。 - 自动执行
vibe-plan生成tasks.md（任务拆解清单）。 - 最后一次确认：向用户展示
tasks.md并询问“是否可以开始全自动开发？”。一旦用户同意，进入阶段二。
阶段二：无人值守编码循环 (Subagent-Driven Loop - 开发期绝对静默)
由于 AI 上下文窗口有限，对于 tasks.md 中的复杂任务，必须采用**子智能体分发（Subagent Delegation）**策略。
读取 tasks.md 中的任务，针对每一个未完成的最小模块任务执行以下死循环（全自动，零打断，遇问题按最优解自动处理）：
- 工作树隔离 (Git Worktree / Branching)：在开始新任务前，建议在一个新的 Git 分支上进行开发，确保主分支的安全。
- API契约校验：确认该模块对应的 API 文档已存在，严格按照 API 文档的入参/出参约束进行开发。
- 最小模块编码 (企业级分层)：
- 隔离上下文，仅针对当前最小模块生成代码。
- 严格遵循企业级规范（前端：Components/Hooks/API Clients；后端：Controller/Service/Repository）。
- 自动触发
vibe-frontend或vibe-backend。
- 测试与组装：编码完毕后，立即触发
vibe-test运行单元测试（RED-GREEN-REFACTOR），将通过测试的模块与其他模块进行组装。- 如果测试失败：自动修复代码，重新运行。
- 如果测试成功：进入下一步。
- 安全与质量：触发
vibe-security与vibe-review检查当前代码块。 - 美化（如果是前端任务）：触发
vibe-ui-beautify注入工业风和“果汁感”动画。 - 打勾：在
tasks.md中将该任务标记为已完成[x]，并提交代码 (Git Commit)。 - 继续：自动读取下一个
[ ]任务，重复阶段二，直至系统拼装完毕。
阶段三：自动交付与文档更新
- 端到端真机验证：所有任务完成后，触发
vibe-e2e启动项目、打开浏览器、逐页验证功能可用性。P0/P1 问题必须修复后才能继续交付。 - 自动触发
vibe-api-docs更新接口文档。 - 自动更新
AI_DEVELOPMENT_DOC.md记录本次无人值守开发过程中的踩坑和经验。 - 向用户输出最终的交付总结报告。
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.
- 11d ago First seen · 180 lines · 27 tokens per session scan A 9de35105d58a
vibe-autopilot is a skill published in the GitHub repository xushuodasd/VIBE-Claude-Plugin (4 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 2,873 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
hotfix
Single-issue workflow for quick fixes and small changes that don't need full epic tracking. Creates a branch, implements the fix, commits with issue tracking, and closes.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR workflow, AI code review, and issue tracker bridge sync. Primary execution interface for multi-session feature work.
council-review
Perform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review", "carmack review", or invoke /council-review. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js)…
council-plan
Architect a feature with the Carmack Council before writing code. Use when explicitly asked to plan a feature, do a "council plan", "carmack plan", or invoke /council-plan. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo…
test-architect
Map testable surfaces, audit existing tests for quality, and write test specifications that prevent AI shortcuts. Use when asked to "audit tests", "specify tests", "test architect", "map test coverage", or invoke /test-architect. Two modes — audit (evaluate existing tests against Beck's principles) and specify (write…