38,263 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
MCP server Claude CodeCodexCursor +2
Route long-tail MCP servers through three lazy tools and reviewed declarative Methods. Runs locally from the @mentu/metamcp npm package.
Skill Claude CodeCodex
Orchestrates multi-agent hierarchical swarms using a divide-and-conquer architecture for complex, multi-system, or orthogonal engineering initiatives (e.g., concurrent backend, frontend, database, QA). Manages hierarchical Lead Agents and Specialists, disjoint work allocations, and strict parent-child communication.…
understudylabs/understudy-agent-tools
Plugin Claude Code
Bundles 43 skills, 1 command · 3,272 tokens together
Improve LLM apps and agents from real traces — reduce cost/latency, raise quality/reliability, capture traces, build evals, run local optimization (GEPA), compare models/providers, and route through Understudy.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Use when the user asks to orchestrate, outsource, delegate, or hand off a slice to another coding-agent CLI as a one-shot subagent — Claude Code, Codex, Grok Build, Cursor Agent, Antigravity CLI, Gemini CLI, OpenCode, or Droid — or to ask Claude, ask GPT, ask Codex, ask Grok, ask Gemini, ask Fable, ask Astra, get a…
Skill Claude CodeCodex
A tool for turning the writings, lectures, and clinical cases of a traditional Chinese medicine practitioner into an AI-usable skill. It captures that practitioner's models, decision rules, language, safety limits, and treatment perspectives.
Skill Claude CodeCodex
Designs and writes a focused artifact another agent runs — an agent persona in agents/, a workflow skill in skills/, or a pi session harness in .pi/harnesses/. Use when authoring a reviewer or specialist persona, a repeatable process skill, or a pi extension that reshapes a session — or when rewriting one that is…
Skill Claude CodeCodex
Build evaluation harnesses for agents and chatbots — golden sets, deterministic tool-selection checks, LLM-as-a-Judge, Bedrock RAG evaluation jobs, CI gates, and online drift monitoring. Use when an agent needs a quality gate before merge or a quality alarm in production.
Skill Claude CodeCodex
/neat extend is a set of six MCP surgical tools for long-tail instrumentation — three diagnostic (read-only), three operative (file-scope-restricted, idempotent, reversible, observable). The user's MCP agent reasons; NEAT operates. NEAT holds no LLM key and never auto-applies. No standalone CLI variant. Discovery is…
naoyoshinori/docker-gemini-cli
MCP server Gemini CLI
MCP server "mcpGateway", hosted remotely at mcp-gateway, as configured in naoyoshinori/docker-gemini-cli.
muranUSTB/skills-create_skills
Skill Claude CodeCodex
A guided assistant for creating Dify workflows. Dify is a platform for building AI applications, and the assistant produces workflow settings in YAML format that Dify can import.
Plugin Claude Code
Eval-driven multi-agent framework for building production Stellar dApps.
MCP server Claude CodeCodexCursor +2
Attestix - Attestation Infrastructure for AI Agents. DID-based agent identity, W3C Verifiable Credentials, EU AI Act compliance, delegation chains, and reputation scoring. 47 MCP tools across 9 modules. Runs locally from the attestix Python package.
Plugin Claude Code
Bundles 5 skills, 2 plugins · 478 tokens together
The five-skill discipline loop for long-running agent work: freeze a task's scope into a workorder, gate sensory output behind human review, log decisions so they survive a context reset, hand off state when work changes hands, and close out with evidence instead of claims.
PolarCoding85/convex-agent-skillz
Skill Claude Code
Build AI agents with persistent threads, tool calling, and streaming on Convex. Use when implementing chat interfaces, AI assistants, multi-agent workflows, RAG systems, or any LLM-powered features with message history.
shane9coy/Agent-Skill-Architecture-Guide
Skill Claude CodeCodex
Use when the user asks to copy, install, refresh, or update a repo-root AGENTS.md file from their canonical global instruction source. Also use when the user says "agent copy" or wants a repo-local AGENTS.md with global operating rules plus project-specific guidance.
Skill Claude CodeCodex
When a task requires discovering or calling already-configured MCP servers through mcpx, or generating project-local MCP routing skills, run mcpx @skill immediately to load the full usage guide.
prog-time/claude-config-template
Agent Claude Code
Replace this with your agent's description. This text is used by Claude to decide when to invoke the agent — write it as a set of trigger signals, not a general summary. Include typical user phrases in the languages you support.
andrew-hernandez-paragon/code-graph-context
Skill Claude CodeCodex
Coordinate multiple parallel subagents using stigmergic pheromone trails and/or explicit task queues in the code graph. Use when you need to parallelize work across multiple files or modules, run a swarm of agents, coordinate agents without direct messaging, or manage complex multi-step workflows. Triggers on "swarm"…
Plugin Claude Code
Bundles 9 skills, 2 commands, 2 hooks · 768 tokens together
A Korean-language AI development-partner persona for vibe coding, where a person guides an AI while building software. It combines an always-active core persona with additional viewpoints and domain guidance when needed.
Plugin Claude Code
Bundles 7 skills · 521 tokens together
Quality-gated skill authoring: create, recap, update, judge, and step-through-apply skills with HITL and an audit/feedback layer.
Plugin Claude Code
Bundles 44 skills, 71 commands, 18 agents, 3 hooks · 2,267 tokens together
Plan-Build-Run — Structured development workflow for Claude Code. Solves context rot through disciplined subagent delegation, structured planning, atomic execution, and goal-backward verification.
Skill Claude CodeCodex
Coordinate with other AI agents working on this same project. Use at the start of every session, and before editing any file, to adopt your identity, read the shared plan and task board, and lease the files you are about to change so two agents never edit the same file at once.
Cursor rule Cursor
A rule set that lets an AI assistant show short inner-monologue messages using the prefix “▎InnerOS:”.
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: