The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.
Agent Claude Code
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
Agent Claude Code
Identifies code simplification opportunities for clarity and maintainability while preserving exact functionality. Use after writing or modifying code. Focuses on recently changed code unless told otherwise. Reports findings with before/after suggestions. Advisory only - does not modify files.
Agent Claude Code
Use proactively to understand HOW code works. Analyzes implementation details, traces data flow, and documents technical workings with precise file:line references. The more specific your request, the better the analysis.
Agent Claude Code
Comprehensive codebase exploration - finds WHERE code lives AND shows HOW it's implemented. Use when you need to locate files, understand directory structure, AND extract actual code patterns. Combines file finding with pattern extraction in one pass.
Agent Claude Code
Analyzes code comments for accuracy, completeness, and long-term value. Verifies comments match actual code behavior. Use after generating documentation, before PRs with comment changes, or when auditing for comment rot. Advisory only.
Agent Claude Code
Reviews documentation affected by code changes. Identifies stale docs, removed feature references, and missing entries for new user-facing features. Reports findings with specific fixes. Advisory only - does not modify files.
Agent Claude Code
Analyzes PR test coverage for quality and completeness. Focuses on behavioral coverage, not line metrics. Identifies critical gaps, evaluates test quality, and rates recommendations by criticality (1-10). Use after PR creation or before marking ready.
Agent Claude Code
Autonomous code quality agent that scans for rule violations, fixes them in an isolated worktree, runs validation, creates a PR, and updates memory with findings for future runs.
Agent Claude Code
Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a TypeScript Agent SDK app has been created or modified.
Agent Claude Code
Hunts for silent failures, inadequate error handling, and inappropriate fallbacks in code changes. Zero tolerance for swallowed errors. Use after implementing error handling, catch blocks, or fallback logic.
Agent Claude Code
Specialized agent for triaging GitHub issues. Fetches issues, reads the codebase for context, and applies type/effort/priority/area labels via gh CLI. Use when the triage skill delegates issue labeling work.
Agent Claude Code
Analyzes type design for encapsulation, invariant expression, and enforcement quality. Use when introducing new types, reviewing PRs with type changes, or refactoring existing types. Provides qualitative feedback and ratings (1-10) on four dimensions. Pragmatic focus.
Agent Claude Code
Need information beyond training data? Modern docs, recent APIs, or current best practices? Searches strategically, fetches relevant content, and synthesizes findings with proper citations. Re-run with refined prompts if initial results need more depth.