Plugin Catalog

Task to production. 12-phase pipeline: discovery, exploration, planning, implementation, review, and shipping.

Branch to merged PR in one command. Commits, pushes, creates PR, monitors CI, addresses reviewer comments, merges.

Lint agent configurations with 230 validation rules across 10+ AI tools. SARIF output for GitHub Code Scanning.

Kill AI slop before it ships. 3-phase detection pipeline finds debug statements, placeholder text, verbose comments.

Eight parallel analyzers check prompts, agents, plugins, docs, hooks, skills, and cross-file consistency. Certainty-graded findings.

Evidence-backed performance investigation. 10-phase methodology with baselines, profiling, and controlled experiments.

AST-based plan vs code analysis. JavaScript collectors + single Opus call. 77% token reduction vs multi-agent approaches.

Multi-agent code review. Up to 10 specialized role-based agents review security, performance, architecture, and more.

AST symbol and import mapping. Cached file-to-symbols map via ast-grep used by drift-detect and planners.

Keep docs in sync with code. Finds outdated references, stale examples, missing CHANGELOG entries.

Research any topic online. Progressive discovery gathers 10-40 sources, scores quality, creates structured guides with RAG index.

Cross-tool AI consultation. Ask Gemini, Codex, Claude, OpenCode, or Copilot for a second opinion on any question.

Structured multi-round AI debates. Proposer vs challenger with evidence-backed arguments and synthesis.

Browser automation and web testing toolkit for AI agents. Headless browser control, authentication, and page interaction.