跳到正文
TakoAPI
返回技能列表

agent-guardrails

由 olmmlo-cmd 提供

Coding Agents & IDEs
477下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Stop AI agents from secretly bypassing your rules.

描述

该技能的功能

Mechanical enforcement layer for AI agent project standards using git hooks, secret detection, deployment verification, and import registries. Born from real production incidents including server crashes, token leaks, and code rewrites. Enforces rules that markdown and prompt instructions cannot reliably maintain.

Git hooks and code-level checks enforce standards at 95-100% reliability compared to 40-70% for prompt rules and markdown instructions.

何时使用

  • Blocking AI agents from reimplementing existing functions instead of importing them
  • Catching hardcoded API keys before they reach version control
  • Verifying deployed code matches written code after agent tasks
  • Preventing deployment gaps where features are coded but never wired into production
  • Propagating enforcement improvements across projects via skill update feedback loops

示例工作流

输入

User asks: set up guardrails on my Python project

智能体
  1. 1

    Runs install.sh to install git pre-commit hook and scaffolding into the project

  2. 2

    Copies registry-template.py to create a module import registry

  3. 3

    Adapts agents-md-template.md into project AGENTS.md with mechanical enforcement rules

  4. 4

    Runs create-deployment-check.sh to generate .deployment-check.sh and DEPLOYMENT-CHECKLIST.md

  5. 5

    Installs the pre-commit-deployment git hook template

输出

Project now blocks secret commits, detects duplicate implementations, and verifies deployment wiring before any commit is accepted

安装

clawhub install olmmlo-cmd/agent-guardrails

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接