Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 376,782 indexed, measured the same four ways as everything else here.
Join a Google Meet, Zoom, or Teams meeting as an AI presenter and DELIVER a presentation — slides on the bot's camera, narrated aloud, auto-advancing. Hand it a DOCUMENT (PDF, PowerPoint, or Word) or a TOPIC. A PowerPoint (already a deck) is shown as-is; a Word/PDF document is turned into a meaningful deck the agent…
A guided workflow for getting a project from GitHub or another source-code repository running in a local environment or another approved target. It checks the project and environment before installing, building, testing, or starting anything.
MCP server "chromadb-remote-mcp" as configured in meloncafe/chromadb-remote-mcp. Runs in Docker (devsaurus/chromadb-remote-mcp:latest). Needs 2 environment variables to run.
★not rated 12 2d agoA
tokens not measured
originalMIT
Install MCPfinder — a local MCP server that searches Official MCP Registry, Glama, and Smithery for 25,000+ MCP servers — into the user's AI client. Use when the user asks for a capability the agent doesn't have (database, API, Slack, filesystem, GitHub, Postgres, etc.) and no MCP tool-finder is already available, or…
Blend Codex headless (codex exec) nodes into Claude Code's Workflow (ultracode) orchestration — cross-model adversarial verification, judge panels with a Codex juror, and second-opinion generation.
★not rated 12 2mo agoA
tokens not measured
originalApache-2.0
Your AI compass from private sector to federal career — MCP server for USAJobs API. Runs locally from the federal-compass-mcp npm package. Needs 2 environment variables to run.
★not rated 12 4d agoA
tokens not measured
originalMIT
Reviews pull requests for security vulnerabilities, logic bugs, data loss risks, and API misuse. Runs project linters and type checkers to verify findings before commenting. Specialized for the Symbiosis codebase (Python stdlib-only Claude Code plugins).
Adversarial multi-agent code review. Your PR runs a gauntlet of up to seven concern-specialized agents, then survives deterministic verification, skeptical validation, and a blind challenge before anything reaches you. Prompt injection defense and flexible delivery (PR/MR comments, markdown, chat). Supports GitHub and.
★not rated 12
changed yesterdayA
tokens not measured
originalApache-2.0
A personal collection of Claude Code configuration, including tools and workflows for reading Twitter, making safe submissions, analysing screenshots, designing interfaces, and reviewing Codex work.
Strict tutor mode. Turns Claude into a teacher that paces one concept at a time, verifies understanding, gathers resources, reviews YOUR code, and hard-blocks itself from writing code for you.
★not rated 12▲
+1 2mo agoA
tokens not measured
originalMIT
Use this agent as the supreme technical authority and team leader — a hyper-active, self-evolving CTO that proactively manages, delegates, monitors, debates, and adapts the entire 26-agent team. Has ALL Claude Code tools and capabilities. Can dispatch any agent, create new agents, install MCPs/plugins, evolve any…
Autonomous, personalized research loops for Claude Code. Set a topic, walk away, come back to a quality-gated report adapted to your projects.
★not rated 12 4mo agoA
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: