guardrails

Name: guardrails
Author: pedroberaldo87

pedroberaldo87 ★ 0

This Claude Code plugin provides global editing guardrails through hooks that lint and type-check code (JS/TS/Python), enforce LLM scope compliance to prevent UI edits from drifting outside the approved plan, and guard against Agent Teams misuse. The guardrails are portable across machines via environment variables, eliminating the need for hand-rolled hook configurations in ~/.claude/settings.json.

Code Review Security No API key detected runs shell

Install

> /plugin marketplace add pedroberaldo87/pedro-plugins/tree/HEAD/plugins/guardrails

> /plugin install guardrails

Source: https://github.com/pedroberaldo87/pedro-plugins/tree/HEAD/plugins/guardrails

What it's made of

1 skill · 6 hooks

Commands: 0
Agents: 0
Skills: 1
MCP servers: 0
Hooks: 6 · PostToolUse, PreToolUse, SessionStart

What it needs & plugs into

API keys: none
Paid services: none detected
External tools: %s askq-humanize.sh bootstrap lint-and-typecheck.sh null) scope-cop.sh tr
Talks to: nothing external detected

Analyzed 2026-11-11. Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.

Is this your plugin?

Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (pedroberaldo87).