近乎消除AI代理在長時間任務中的規則違規，自動修正行為偏差，讓你不再煩惱。專為Claude Code、Codex CLI和Cursor設計的純工程零LLM掛鉤系統。掛鉤延遲約50-70毫秒，典型內部測試中約2%的Token開銷。
jhaizhou-ops/pinrule 是一個專為AI代理（如 Claude Code、Codex CLI 和 Cursor）設計的純工程掛鉤系統，旨在幾乎完全消除長時間任務中的規則違規。它透過自動修正行為偏差來避免用戶因規則違規而感到困擾，整個過程不依賴任何大型語言模型（LLM）調用，因此效能極高。在典型內部測試中，該系統的掛鉤延遲僅約50-70毫秒，Token開銷約為2%，對任務執行效率影響極小。此技能適用於需要嚴格遵守規則的長時間自動化任務，可顯著降低人工干預需求，提升開發流程的穩定性與可靠性。
npx skills add jhaizhou-ops/pinruleInstalled? Explore more 生產力與協作 skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →
Near-eliminate AI Agent rule violations in long tasks — auto-correct drift before it frustrates you. Pure-engineering zero-LLM hook system for Claude Code / Codex CLI / Cursor. ~50-70ms hook latency, ~2% token overhead in typical dogfood.
Source: https://github.com/jhaizhou-ops/pinrule
Discovered from GitHub repositories pushed in the last 24 hours for agent skills, Claude/Codex/Gemini workflows, MCP tooling, and adjacent AI-agent automation.
Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.