🧪
Agent Evals Starter Kit
EvalsTestingAI Agents
A practical evaluation starter kit for AI agents: benchmark templates, regression suites, quality scoring rubrics, and go/no-go decision frameworks. Stop guessing if your agent got better.
🔒
AI Coding Agent Security Kit
SecurityAI AgentsClaude Code
Security patterns and hardening templates for AI coding agents. Covers secrets management, sandboxing, prompt injection defense, output validation, and audit logging for production agent deployments.
💥
AI Agent Database Blast-Radius Prevention Kit
AI AgentsDatabasesSafety
Prevent AI agents from destroying your database. Blast-radius analysis templates, read-only mode patterns, mutation guards, rollback procedures, and a pre-flight checklist for any agent with DB access.