agent-guardrails

[🇨🇳 中文版](./README.zh-CN.md) | [🇬🇧 English](./README.md)

agent-guardrails is a merge gate for AI-generated code. It checks that AI changes match expectations *before* you merge.

• 🎯 Scope validation — AI only touches allowed files
• ✅ Test verification — tests must pass
• 🔍 Drift detection — catches parallel abstractions, interface changes
• 🛡 Protected paths — critical files stay untouched
• 🔧 Auto-fix — Tier-1 issues fixed automatically, zero side effects
• 🧬 Mutation testing — optional lightweight built-in slice catches vacuous tests (config-gated, default-disabled)

agent-guardrails is aimed first at overseas solo developers and small teams already using AI coding tools.

• solo founders shipping real product code with Claude Code, Cursor, Codex, Gemini, or OpenCode
• small product teams that want the same repo guardrails even when each developer uses a different agent
• consultants and agencies that need safer AI-assisted changes across multiple client repos

It is not primarily for one-off toy prompts or teams looking to replace their coding agent entirely.

AI coding tools already generate plenty of code. The paid opportunity is not "more code generation." It is:

• less manual setup before each task
• faster trust decisions at review time
• higher-signal repo-aware checks than prompt text alone can provide
• lower maintenance drift as AI edits accumulate over time
• safer deploy / rollback workflows for people shipping without a large platform team

OSS should remain a real merge gate. Paid tiers should help users get to a safe merge faster, more consistently, and with less cognitive overhead.

# 1. Install
npm install -g agent-guardrails

# 2. Set up in your project
cd your-repo
agent-guardra