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.
Skill Claude Code
Audit skill SKILL.md files for compliance with the agentskills.io specification and house conventions. Checks frontmatter fields (name, description, compatibility, metadata, argument-hint), metadata sub-fields (author, scope, layer, confirms), and layer/suffix consistency. Use when adding new skills, reviewing skill…
Skill Claude CodeCodex
Navigating LLM tooling workflows. Use when choosing recall, search, SQLite, MCP, secret-safety, or skill validation tools.
teixeirazeus/fablize-for-hermes
Skill Claude CodeCodex
A harness that makes any model see a task through to the end — with evidence and verification — as procedure, not as luck. Enforces verification grounding (run & observe artifacts before declaring done), multi-story decomposition with an evidence gate, a systematic investigation protocol, and early-stop prevention.…
Plugin Claude Code
Bundles 14 skills, 2 MCP servers · 1,096 tokens together
Comprehensive Smalltalk development toolkit for AI-driven development.
Plugin Claude Code
Bundles 2 skills, 3 agents · 291 tokens together
Four independent, provider-agnostic skills for product specification, code review, spec-driven implementation, and Moss change summaries.
Plugin Claude Code
Bundles 35 skills, 9 commands, 13 agents · 2,876 tokens together
13 agents, 36 skills, 19 commands, 15 hooks — spec-driven, multi-agent orchestration for Claude Code with per-phase model tiers, opt-in lifecycle hooks, and optional cross-device semantic memory.
Plugin Claude Code
Bundles 9 skills, 9 commands, 3 agents, 12 hooks · 917 tokens together
AI development loop — orchestrator distributes tasks to headless workers, independent auditor verifies, structural enforcement auto-blocks downstream on upstream failure. Full-cycle validated with 10-scenario test harness.
Command Claude Code
Run the evolution pipeline. Depth depends on evolution-config.yaml (tier + schedule).
johnpeterman72/CursorRIPER.agent
Cursor rule Cursor
Core RIPER Sigma framework - referenced by all agents.
MCP server Claude CodeCodexCursor +2
Mirror MCP: Introspection for LLMs. Runs locally from the mirror-mcp npm package.
Cursor rule Cursor
Objective: To continuously enhance project-specific guidance and AI behavior by reflecting on user interactions and proactively suggesting improvements to .cursor/rules or relevant documentation like CLAUDE.md.
Skill Claude CodeCodex
Triggers: /shared-brainstorm command, or when the user says "brainstorm with my team" / "get team input" / "ask the group".
Cursor rule Cursor
This repo has a GraphPilot structural code-graph available via MCP. Use it before grep on structural questions.
MCP server Claude CodeCodexCursor +2
Auto-instrument AI agent frameworks with runtime security. One line to govern LangChain, CrewAI, OpenAI, Anthropic — injection blocking, PII masking, action policy, audit trail. Zero code changes. Runs locally from the agent-aegis Python package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Dynamically load Claude Code skills into AI agents without copying files. Runs locally from the agent-skill-loader npm package.
monktechnologiesofficial/starter-repo
Cursor rule Cursor
Project 2 - Autonomous Ticket Triage Agent - supervisor + Triager / Investigator / Responder + HITL.
MCP server Claude CodeCodexCursor +2
MCP server "human-loop-mcp-server" as configured in boorich/mcp-human-loop. Runs locally from the Human Loop MCP Server npm package.
Plugin Claude Code
Bundles 24 skills · 3,714 tokens together
Collection of skills including skill creation, MCP server development, E2E testing, and unit testing guides for TypeScript/NestJS projects.
MCP server Claude CodeCodexCursor +2
Intelligent Perplexity research MCP server with model selection, multi-model synthesis, and research history. Runs locally from the @familyitguy/perplexity-mcp npm package.
agentveil-protocol/agentveil-sdk
Skill Claude CodeCodex
AgentVeil action-control workflows for AI agent systems. Evaluate risky actions with Runtime Gate, route human approvals, resume approved execution, fetch signed receipts, inspect agent public profiles, check advisory reputation, submit signed attestations, discover agents by capability, and verify audit evidence…
Plugin Claude Code
Bundles 26 skills, 4 hooks, 2 plugins · 1,594 tokens together
Verify CLAUDE.md/AGENTS.md references, compile typed specs, and test the agent harness.
Cursor rule Cursor
Cursor rule "bmad-roles" from omril321/automated-notebooklm, covering 👥 bmad role system for cursorriper σ, symbol: β (beta), version: 1.0.0, 📋 role definition system and 🎭 role mappings.
jrjsmrtn/project-orchestration-skills
Plugin Claude Code
Bundles 13 skills · 897 tokens together
Skills for AI-assisted project orchestration following best practices for software development lifecycle, architecture documentation, and quality automation.
Plugin Claude Code
Bundles 13 skills, 1 hook · 590 tokens together
Unified spec-to-execution workflow system. Combines spec rigor, autonomous execution, and native task orchestration with parallel agent dispatch. Swarms-ready architecture.
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: