3,273 tagged ai-agents, measured the same way as everything else here.
Browse within: agentic-ai 236claude-code-plugin 215LLM 190cursor 178cli 127prompt-engineering 111agents-md 107Science 99agents 87ai-coding 82agentic-coding 62ai-tools 62skills 60ai-governance 54
briandconnelly/codex-in-claude
Plugin Claude Code
Bundles 8 skills, 1 MCP server · 994 tokens together
Call OpenAI Codex from Claude Code for delegation, review, and second opinions.
Plugin Claude Code
Non-custodial Solana swap & limit-order MCP server for AI agents. 21 tools (swap, limit, trailing, TWAP, DCA, combo orders) across Raydium, PumpSwap, Orca, Meteora. Jito MEV-protected. Ed25519 server-message verification. Private key never leaves the agent.
cyanheads/un-comtrade-mcp-server
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Access UN Comtrade international merchandise and services trade statistics — country lookups, HS commodity search, bilateral trade flows, balances, rankings, and data availability — via MCP. STDIO or Streamable HTTP.
Plugin Claude Code
Bundles 1 skill, 5 hooks · 12 tokens together
Shared memory and collision-avoidance for parallel Claude Code sessions. Warm-starts each session with what earlier ones learned, records what every agent does, and blocks two sessions editing the same file.
cyanheads/usaspending-mcp-server
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Access US federal award, recipient, agency, and spending analytics data from USAspending.gov via MCP.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 139 tokens together
An email client for AI agents. Reads any IMAP mailbox, or Gmail over its API, strictly read-only; archives the messages matching composable filter rules to disk as .eml plus markdown, and serves the archive over MCP. Rules can read a domain list a separate program owns, so an agent subscribes to mail by editing a text.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 118 tokens together
Local Chromium control and temporal visual evidence for AI agents.
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Look up genes, fetch sequences, predict variant consequences, find orthologs, and retrieve cross-database xrefs from Ensembl REST via MCP. STDIO or Streamable HTTP.
Plugin Claude Code
Bundles 4 skills · 335 tokens together
Skills for building and verifying Nifra apps: contract-first APIs, full-stack SSR on five UI libraries, and the check/assure/capabilities gates. Prefers Nifra's live MCP server over model recall.
Plugin Claude Code
Bundles 4 skills · 894 tokens together
Comptabilite, fiscalite, financement et epargne en France. Quatre roles : Comptable (/comptable) pour l entreprise ; Impots (/impots) pour le particulier ; Financement (/financement) pour l argent de l activite - banque et droit au compte, credit et rupture de credit, caution du dirigeant, tresorerie, mediation du…
Senavictors/bootstrap-agent-architecture-plugin
Plugin Claude Code
Bundles 9 skills, 1 agent · 1,018 tokens together
Orquestrador de arquitetura de agentes de IA para Claude Code, Cursor e Codex — bootstrap de projeto, papéis especializados (com MCP opcional para operações de risco), planejamento e geração de tasks, handoff entre sessões/ferramentas, checagem de Definition of Done com documentação viva (docs/ com estado…
Plugin Claude Code
Plugin marketplace listing 1 plugin: avoid-overkill.
Plugin Claude Code
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code.
Plugin Claude Code
Bundles 32 skills · 1,689 tokens together
Fulcrum-curated skills for Claude Code (jq, bat, gh, ripgrep-class CLI tools, security scanners, formatters).
Plugin Claude Code
Bundles 2 skills · 94 tokens together
Profile a software project and recommend a focused loadout of MCP servers, hooks, and skills for the active coding agent.
Plugin Claude Code
Bundles 1 skill · 106 tokens together
Read and write to any Skool community from your AI agent — posts, comments, members, classroom courses, files, and Auto DM. One HTTP call per action, never-throw contract, LLM-readable error hints. Backed by the Apify-hosted Skool All-in-One API actor.
ulpi-io/autonomous-engineering
Plugin Claude Code
Bundles 18 skills · 2,169 tokens together
Autonomous software delivery for Claude Code — 8 lifecycle phase skills (auto-spec → auto-ship) plus the loop/verify/checkpoint/budget primitives, with deterministic enforcement hooks and runnable Workflow templates.
Plugin Claude Code
Bundles 44 skills, 15 commands, 26 agents · 3,855 tokens together
Complete SDLC Workflow in a Plugin: 26 agents across 6 phases (planning, design, development, testing, deployment, operations), 43 knowledge skills, 14 orchestrator commands. Industry-standard SDLC best practices embedded in every agent.
Plugin Claude Code
Bundles 1 skill · 174 tokens together
An AI executive board of directors (CEO, CFO, COO, CLO, CISO sub-agent personas) that vets business ideas, debates them from each role's perspective, and delivers an integrated Go/No-Go board memo. Built to help executives pressure-test initiatives before presenting to a real board.
Plugin Claude Code
Bundles 24 skills · 803 tokens together
The core engineering loop for coding agents (Claude Code, Codex CLI): grill, spec, tickets, implement with TDD at agreed seams, review, commit, plus a user-gated compound step that turns session learnings into durable project memory. Basic spells a caster always has prepared.
michalstrnadel/source-to-skill
Plugin Claude Code
Bundles 1 skill · 100 tokens together
Turn YouTube videos, playlists, academic papers, books, web articles, and GitHub repos into agent skills.
Plugin Claude Code
Bundles 14 skills, 1 command, 1 agent · 863 tokens together
The full vibe-coding loop: scaffold an app or marketing site with a real design system, animate it with GSAP and a real motion system, replace the fake data with a real backend, unstick it when it breaks, strip the AI look, ship it, and demo it.
hdkhosravian/loop-contract-skill
Plugin Claude Code
Bundles 1 skill · 280 tokens together
Turns a rough, long-running request into a loop-engineered contract and then executes it — frozen scope counted from the source, an achievement oracle written red before the work, a distinct proof per item, and a completion gate that runs the oracle itself so "done" is a fact rather than a claim.
Plugin Claude Code
Cut routine git/gh approval prompts: auto-approve safe commands (read-only, staging, branch/worktree create, feature-branch commits & pushes) and confirm protected-branch or destructive ones.
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: