ReAct Agent
1105Agent Claude Code
A reasoning agent that works through a problem by repeating three steps: think, act, and observe the result.
38,013 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.
Agent Claude Code
A reasoning agent that works through a problem by repeating three steps: think, act, and observe the result.
MCP server Claude CodeCodexCursor +2
Unified MCP & Skill management gateway, shared across AI agents, 99% context token savings. Runs locally from the aai-gateway npm package.
Skill Claude CodeCodex
Perception automatically analyzes video segments from Eye using cloud VLM (Gemini). Working Memory tracks cross-segment event context. Results flow to ReflectWorld (storage) and Act (rules) via PostProcessor — all automatic.
10xChengTu/harness-engineering
Skill Claude CodeCodex
A Chinese-language guide to preparing software projects for reliable work by coding agents. It covers project instructions, documentation, code checks, tests for agent output, prompts, and ways to coordinate multiple agents.
Plugin Claude Code
Bundles 2 skills · 246 tokens together
AI Adoption, three skills for working with your Claude history. token-doctor diagnoses where your Claude Code + Cowork spend goes (length distribution, marathon share, cache rebuilds, per-project health), writes a doctor-style terminal report, and optionally fans out parallel Haiku subagents over your top sessions for.
Skill Claude CodeCodex
Manage octo's agent profiles through conversation — create, modify, delete, list, and bind agents to IM chats by calling REST APIs. This skill is exclusive to the Default Agent (full-access). Use when the user wants to manage agents conversationally, e.g. "create a code review agent", "list all agents", "bind agent X…
christopherarter/superpowers-reasonix
Skill Claude CodeCodex
Creating, editing, or testing a Reasonix skill? Load first, before you deploy it.
Skill Claude CodeCodex
A guide to the concepts and capabilities of the PAI assistant application.
louchi1984-coder/deepseek-claude-code-worker-mcp
MCP server Claude CodeCodexCursor +2
MCP server "deepseek-worker-mcp" as configured in louchi1984-coder/deepseek-claude-code-worker-mcp. Runs locally from the deepseek-worker-mcp npm package.
MCP server Claude CodeCodexCursor +2
N-to-1 MCP Orchestration. Unified gateway for multiple MCP servers with intelligent tool discovery. Runs locally from the @portel/ncp npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server for AI sub-agent delegation across Cursor, Claude, Codex, Gemini, and GLM. Runs locally from the sub-agents-mcp npm package. Needs 10 environment variables to run.
Skill Claude CodeCodex
AI fleet project execution (orchestrator=PM, marketing agent, backend dev agent, video agent). Fast-iteration architecture pivots and inter-agent task delegation across multi-hour sessions. Use when a user assigns a multi-agent project with "take it as a team" instruction.
Skill Claude CodeCodex
A tool that delegates coding, codebase exploration, implementation, review, and verification work to a persistent Codex CLI agent. It is intended for requests that explicitly ask Codex to act or continue an existing Codex task.
Skill Claude CodeCodex
AI agent harness for coordinating Claude and GPT to make and execute extremely robust plans.
Plugin Claude Code
Bundles 15 skills, 8 agents · 2,737 tokens together
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Skill Claude Code
Wire an AI agent's telemetry into Kyoko and prove one real run shows up.
Plugin Claude Code
Documentation-first development methodology. AI-ready docs = automatic code generation. 10-20x velocity.
Skill Claude CodeCodex
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
LearnPrompt/andrej-karpathy-skills
Plugin Claude Code
Bundles 15 skills · 1,637 tokens together
14 Karpathy-inspired working methods + 1 methodology router, distilled from his 2023-2026 public X posts and Gists into executable agent skills: agentic-engineering, vibe-to-agentic, autoresearch, llm-simulator, llm-wiki, minimalism, supply-chain-hygiene, understanding-first, idea-files, output-evolution…
MCP server Cursor
MCP server "keep-mcp-pipx" as configured in feuerdev/keep-mcp. Launched with pipx run --no-cache --spec . mcp. Needs 3 environment variables to run.
Skill Codex
Use when the user asks to invoke, delegate to, or collaborate with Codex on any task. Also use PROACTIVELY when an independent, non-Claude perspective from Codex would add value — second opinions on code, plans, architecture, or design decisions.
Skill Claude CodeCodex
Use this skill when the user is building against Anthropic APIs or SDKs, including @anthropic-ai/sdk, anthropic, or Agent SDK integrations.
agent-skills-hub/agent-skills-hub
Skill Claude CodeCodex
Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash.
Skill Claude CodeCodex
A Codex-based coding agent for implementing features, fixing bugs, refactoring code, testing, and reviewing changes.
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: