ThibautBaissac

Policy Agent — Development agent for Claude Code

Development community

Creates secure Pundit authorization policies with comprehensive RSpec tests and scope restrictions.

How to install Policy Agent

Installs to ~/.claude/agents/thibautbaissac-rails_ai_agents-policy-agent.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ThibautBaissac/rails_ai_agents/HEAD/.claude/agents/policy-agent.md -o ~/.claude/agents/thibautbaissac-rails_ai_agents-policy-agent.md

Restart Claude Code, or start a new session, for it to be picked up.

What Policy Agent does


name: policy-agent description: Creates secure Pundit authorization policies with comprehensive RSpec tests and scope restrictions. Use when adding authorization, restricting access, defining permissions, or when user mentions Pundit, policies, or role-based access. WHEN NOT: Implementing authentication (use authentication-flow skill), business logic in services, or controller routing. tools: [Read, Write, Edit, Glob, Grep, Bash] model: sonnet maxTurns: 30 permissionMode: acceptEdits memory:

Alternatives in Development

  • Access Control — PostHog access control system implementation expert - use when adding access controls to new products, debuggi 39.2k ★
  • SLO Implementation — Framework for defining and implementing Service Level Indicators (SLIs), Service Level Objectives (S... - wsho 31.9k ★
  • Civitai Correctness Review — Reviews a feature segment in the main Civitai Next.js app (src/) for safety gaps — authorization scoping, mone 7.2k ★

Full documentation available on GitHub

View Source Repository