38,215 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.
Plugin Claude Code
Bundles 39 skills, 18 commands, 14 agents, 6 hooks · 2,664 tokens together
Unified Claude Code plugin merging superpowers workflows (TDD, debugging, planning) with everything-claude-code productivity (agents, learning, hooks, rules).
MCP server Claude CodeCodexCursor +2
Pass the baton between coding agents: convert sessions across Claude Code, OpenCode, Codex & more. Runs locally from the @kasabeh/baton-mcp npm package.
MCP server Claude CodeCodexCursor +2
Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks. Runs locally from the audrey npm package. Needs 2 environment variables to run.
WenyuChiou/agent-collab-skills
Plugin Claude Code
Provider-neutral, policy-aware collaboration skills with checkpoints, proposal-only memory, and human acceptance gates.
Skill Claude CodeCodex
Create, extend, or modify Agent Zero plugins. Follows strict full-stack conventions (usr/plugins, plugin.yaml, Store Gating, AgentContext, plugin settings). Use for UI hooks, API handlers, lifecycle extensions, or plugin settings UI.
Skill Claude CodeCodex
A task-execution procedure for an AI agent, written in Chinese, that emphasizes understanding the goal, confirming the task, completing all steps, checking the result, and delivering it. It also requires the agent to reveal assumptions and constraints.
baochunli/pi-collaborating-agents
Skill Claude CodeCodex
Operating guide for coordinator and spawned subagents using the collaborating-agents extension. Covers agentmessage actions, subagent spawning, subagent session inspection, reservations, delivery semantics, limits, defaults, and failure handling.
Plugin Claude Code
Bundles 1 skill, 4 agents · 347 tokens together
Tech-lead orchestration mode: the top-tier model keeps architecture and decisions, a role roster of cheaper subagents does the implementation, the routine, the digging and the review. Save tokens without losing quality.
Plugin Claude Code
Bundles 1 skill, 4 agents, 3 hooks · 283 tokens together
Turns Fable 5 into a token-frugal orchestrator: Fable keeps judgment, tiered Opus/Sonnet/Haiku agents do the labor.
Command Claude Code
Enable AMAW (Autonomous Multi-Agent Workflow) mode for the current task. Spawns cold-start sub-agents at REVIEW + POST-REVIEW phases instead of using main-session self-review.
Skill Codex
Discover relevant specialist skills from the live awesome-skills list and install them when appropriate. Use proactively for non-trivial tasks that may benefit from a reusable specialist capability not already available, or when the user asks what skills or tools to use. Check the live list before searching for…
Skill Claude Code
Guides creation or update of a SKILL.md: chooses the right frontmatter fields (description vs whentouse, argument-hint, model, effort, allowed-tools, paths, disable-model-invocation, etc.), runs two pressure tests, and follows the approval flow before writing.
Cursor rule Claude CodeCursor
Mandatory agent delegation, skill loading, and sub-agent usage directives for ALL tasks in ALL contexts.
Plugin Claude Code
Bundles 1 skill, 3 hooks, 1 MCP server · 36 tokens together
Compile provenance-backed context and enforce verified Change Bundles for each behavior-bearing logic unit.
Stunspot/nova-the-optimal-ai-mind
Plugin Claude Code
Bundles 27 skills · 429 tokens together
Nova the Optimal AI Free: one vivid Nova front door, ambient MIND, governed continuity, projects, personal knowledge, and twenty-six native practical capabilities.
MCP server Claude CodeCodexCursor +2
Intent-bound action authorization for AI agents — authorise before a credential is used, require human approval for sensitive actions, and prove every action traces back to the instruction that authorised it. Runs locally from the delego Python package. Needs 1 environment variable to run.
Plugin Claude Code
Bundles 3 skills, 9 commands, 1 agent, 8 hooks · 380 tokens together
Plan-Execute-Review development workflow with brainstorming, executor agent, and adversarial code review loop.
Skill Codex
Implement OpenAI Harness Engineering practices in any repository. Use when setting up or refactoring agent-first workflows, writing or upgrading AGENTS.md and PLANS.md, creating deterministic smoke/test/lint/typecheck harness commands, defining strict architecture boundaries and data-shape contracts, wiring…
shadowrootdev/awesome-agent-skills-mcp
MCP server Claude CodeCodexCursor +2
MCP server with 100+ AI agent skills from Anthropic, Vercel, Trail of Bits, Hugging Face & more. Runs locally from the awesome-agent-skills-mcp npm package. Needs 4 environment variables to run.
Skill Claude CodeCodex
Delegate coding tasks to Codex AI for implementation, analysis, and alternative solutions. Use when you need a second AI perspective, want to explore different approaches, or need specialized Codex capabilities for complex coding tasks.
Skill Claude Code
Activate once per session to route substantive requests to the right installed skill. Two modes: suggest (interactive, ranked proposals) or auto (silent with attribution footer). Trigger: /skill-router on | /skill-router on --auto | /skill-router status.
Skill Claude CodeCodex
Use when a complex task needs parallel decomposition into independent subtasks, when multiple agents must work simultaneously without conflicts, or when recursive task delegation is required.
Skill Claude CodeCodex
Operate Tandem as a multi-agent, multi-device MCP orchestrator. Use it when an MCP-capable caller needs to start, inspect, steer, interrupt, or coordinate Claude, Codex, shell, or Hermes sessions on the local hub or another enrolled device. Also covers the optional Claude-only relay. Begin the first response with…
Cursor rule Cursor
AGNO mixed execution patterns combining sequential, parallel, conditional, and dynamic execution strategies for complex workflow orchestration.
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: