跳到主要内容
知仓学习社ZHICANG

plan-implementation

Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.

不碰外部(只输出文字)无严重或高危命中a5c-ai/babysitter

它会碰到什么

扫了多少2 个文本文件,2 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

  • For medium and high stakes changes (low stakes can proceed inline)
  • When structured execution with verification is needed

Process

  1. Load plan - Validate plan exists and is approved
  2. Stakes enforcement - High: halt without plan. Medium: ask. Low: proceed.
  3. Worktree isolation - Offer git worktree based on stakes level
  4. Execute steps - For each: mark in-progress, locate files, read, modify, verify, mark complete
  5. Phase checkpoints - Summarize and ask: continue, review, or pause
  6. Failure handling - Stop immediately, investigate, propose fix, get approval for deviations
  7. Code review - Run code-reviewer agent (APPROVE / APPROVE_WITH_NITS / REQUEST_CHANGES)
  8. Security review - Run security-reviewer agent (halt if failed)
  9. Completion summary - Steps completed, files changed, test status, plan location

Key Rules

  • Follow the plan strictly; deviations require explicit approval
  • Verify before declaring done; run verification after each step
  • Track progress visibly via plan document updates
  • Read files before modifying them
  • Complete code and security reviews before finishing

Tool Use

Invoke via babysitter process: methodologies/rpikit/rpikit-implement

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。