s0912758806p/agentic-sop-to-work

README preview

# agentic-sop-to-work

[![Claude Code Plugin](https://img.shields.io/badge/Claude_Code-plugin-D97757?logo=claude&logoColor=white)](https://claude.com/claude-code) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Version](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fraw.githubusercontent.com%2Fs0912758806p%2Fagentic-sop-to-work%2Fmain%2Fplugins%2Fagentic-sop-kit%2F.claude-plugin%2Fplugin.json&query=%24.version&label=version&color=blue&prefix=v)](plugins/agentic-sop-kit/.claude-plugin/plugin.json) [![Skills](https://img.shields.io/badge/skills-3-8A2BE2)](plugins/agentic-sop-kit/skills)

> **Loop Engineering** — make an agent's loop produce **verifiable progress**, stay **honest**, and stay **bounded**, by deterministic mechanism rather than vibes. `agentic-sop-kit` is the reference toolkit: it turns a human SOP into a **controlled loop**, not a one-shot script — no fabrication, no "mega-agent" rot.
> **Loop Engineering** — 用確定性機制(不是 vibes)讓 agent 的迴圈**每次迭代產生可驗證進度、不自我欺騙、不失控**。`agentic-sop-kit` 是它的參考工具包:把人工 SOP 變成一條**受控迴圈**——不臆造、不退化成 mega agent。

```
/plugin marketplace add s0912758806p/agentic-sop-to-work
/plugin install agentic-sop-kit@agentic-sop-to-work
/reload-plugins
```

**🌐 [English](#english) ・ [繁體中文](#繁體中文)**

### 🗺️ At a glance · 運作一覽

![Agentic-SOP flow — Human SOP → single-tool skills → run.py → per-step gate → DRAFT → human approval, with a Stop-hook regression gate guarding every change](assets/flow.gif)

*Human SOP → single-tool skills → orchestrated flow (gated · branch · map) → DRAFT → human approval; a Stop-hook regression gate guards every change.<br>Human SOP → 單一工具 skill → 編排流程（閘門・分支・map）→ DRAFT → 人核准；Stop-hook 回歸閘門守住每次變更。*

View full repository on GitHub →