Перейти к содержимому
TakoAPI
Назад к навыкам

agent-guardrails

от olmmlo-cmd

Coding Agents & IDEs
477Число загрузок по данным clawskills.sh
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Stop AI agents from secretly bypassing your rules.

Описание

Что делает этот навык

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.

Когда его использовать

  • 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

Пример сценария

ВВОД

User asks: set up guardrails on my Python project

АГЕНТ
  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

ВЫВОД

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

Установка

clawhub install olmmlo-cmd/agent-guardrails

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки