Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 372,033 indexed, measured the same four ways as everything else here.
Manages all git operations (commit, push, branch management, PR creation) in a standardized, safe, and consistent way. Automatically runs the code-review skill before any commit. Enforces Conventional Commits standard. Handles the full lifecycle: branch → review → commit → push → PR.
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
A code-review and design guide based on Clean Architecture. It checks how parts of the application depend on one another, how responsibilities are separated, and whether common SOLID design principles are followed.
★not rated 92▲
+3 5d agoA
tokens not measured
originalMIT
Use this to access external services/CLIs/APIs: Gmail/gh/Github/Stripe etc. or when running any bash command, script, or curl/wget that makes outbound HTTP calls. Make HTTP requests directly and the gateway injects credentials automatically.
Use for every task that plans, writes, edits, debugs, tests, refactors, reviews, or maintains code. Apply to professional repositories, scripts, apps, services, prototypes, beginner work, vibe coding, and bounded code changes inside large systems. Choose the fewest clear lines, files, paths, states, and abstractions…
Local browser automation with structured, verified outcomes. Use for web navigation, scraping and extraction, form interaction, screenshots and downloads, network or console checks, responsive testing, or page-scoped device emulation.
Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.
Use durable, explainable, self-improving memory across a coding session via the velesdb-memory MCP server. Trigger whenever the velesdb-memory MCP tools (remember/recall/recallfused/relate/why/feedback/forget/rememberextracted/extractionstatus/entity/memorystatus) are available and the work would benefit from…
Developer-workflow MCP server for catalyst-core: migration guidance, debugging, and task planning. Runs locally from the catalyst-mcp npm package. Needs 1 environment variable to run.
★not rated 92 3d agoA
tokens not measured
originalMIT
Plan and orchestrate end-to-end video production pipelines in ComfyUI with validation gates and error recovery. Handles img2vid, txt2vid, vid2vid, and multi-shot video production. Produces pipeline plans with correct step ordering (generate, validate, animate, validate, concat), model selection, retry strategies (seed…
Jarvis MCP – Browser-based voice input/output for AI Assistant conversations via MCP (Model Context Protocol). Runs locally from the @shantur/jarvis-mcp npm package.
Connect a new worker agent CLI to Agent Bridge. Use when the user wants to add a custom, unsupported, or in-house agent as an Agent Bridge worker; register a worker in agents.toml; write or debug an Agent Bridge adapter; or asks why a newly added worker does not appear in listagents, ignores model/effort, or starts a…
Comprehensive guide for building CLI and TUI applications - terminal internals, design principles, and battle-tested patterns When building CLI/TUI apps, implementing argument parsing, handling terminal input/output, escape codes, buffering, signals, or asking about terminal development concepts.
Add or retrofit Tenuo authorization for AI-agent tools and effects. Use when implementing Tenuo, protecting an MCP or framework tool, choosing a gateway, sidecar, or embedded enforcement boundary, or testing that an agent cannot exceed delegated authority. Do not use for a review-only audit of an existing warrant.
Production readiness audit for apps built with AI coding tools. Detects your stack, audits 5 domains, and produces a scored punch list with copy-paste fixes.
★not rated 91 yesterdayA
tokens not measured
originalMIT
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: