Audit your AI agent configs before you run them — prompt injection, rogue MCP servers, credential-exfil. Plus dependency vetting.
Agent Claude Code
Use PROACTIVELY when starting a new feature, service, or MVP, or when a design decision needs to be made before code is written. Designs system architecture, data flow, API contracts, database schema, and a minimal-but-scalable implementation plan. Invoke for "design", "architecture", "how should we structure", "new…
Agent Claude Code
Use when something is broken, failing, flaky, or behaving unexpectedly, and the cause isn't obvious. Reproduces the issue, traces the real root cause, explains why it fails, surfaces hidden edge cases, and proposes the most robust fix. Invoke for "bug", "error", "crash", "failing test", "works locally but not in…
Agent Claude Code
Use to prepare an app for production deployment or improve its operational setup. Designs deployment architecture, CI/CD pipelines, containerization, monitoring and logging, and reliability/scaling. Invoke for "deploy", "CI/CD", "Docker", "Kubernetes", "pipeline", "monitoring", "logging", "infrastructure", "uptime"…
Agent Claude Code
Use when something is slow, memory-hungry, or won't scale under load, or before shipping a hot path to high traffic. Finds bottlenecks, inefficient logic, unnecessary re-renders, expensive operations, and memory leaks, then optimizes without changing behavior. Invoke for "slow", "performance", "optimize", "memory…
Agent Claude Code
Use when code needs to be cleaned up, restructured, or made more maintainable WITHOUT changing what it does. Handles reverse-engineering an unfamiliar codebase, separating concerns, reducing coupling, removing duplication, and applying clean architecture. Invoke for "refactor", "clean up", "restructure", "reduce…
Agent Claude Code
Use to audit code for security problems before shipping, after a sensitive change, or on request. Inspects for vulnerabilities, auth flaws, API weaknesses, injection risks, sensitive-data exposure, and infrastructure risk, then reports findings by severity with attack scenarios and fixes. Invoke for "security review"…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: