菜单
This skill should be used for the autopilot loop (scripts/autopilot.sh), scoped verify + lint to avoid global noise, monitor feeding, subagent spawning, PLAN.md / MEGA-PLAN.md management, continuous "YOLO" operation without human in the loop, and log-based coordination.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/aphrody-code/bxc --skill bxc-autopilot-autonomy命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | bxc Autopilot & Autonomy |
| description | This skill should be used for the autopilot loop (scripts/autopilot.sh), scoped verify + lint to avoid global noise, monitor feeding, subagent spawning, PLAN.md / MEGA-PLAN.md management, continuous "YOLO" operation without human in the loop, and log-based coordination. |
| version | 0.1.0 |
Key: always scope the verify/lint commands to the feature packages + relevant src (see the bxc-verify command and verify-enforcer agent).
The loop reads PLAN.md, runs scoped checks, appends to log, sleeps.
Services for instant MCP + caching: Reactivate via scripts/bxc-control.sh deploy (or sudo systemctl start bxc bxc-crawler). bxc-crawler.service runs the 24/7 AutonomousCrawler daemon (populates Redis bxc:cache:url:* + SQLite). bxc.service runs the API/CDP server. All crawlers (recursive, get_url_*, mirror background) now cache-first for instant MCP fetches (tools check Redis → SQLite → live only on miss). Use in agents for fresh-yet-cached web data alongside xai/x tools.
Use for any long-running autonomous development or maintenance of bxc-like projects.
