38,381 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.
Implement a set of tk tickets in parallel using a DAG-driven agent team with continuous dispatching. Spawns a pool of up to 4 implementers and up to 2 quality reviewers at startup (sized to the input ticket count, so a single-ticket run gets 1 + 1); dispatches tickets as they unblock without wave boundaries. Quality…
Visualize all Claude Code configuration as a beautiful HTML dashboard. Use when the user asks to "inspect config", "show my setup", "what skills/plugins do I have", "generate config dashboard", "audit my Claude Code setup", or invokes "/inspect".
Use ccmux to run and steer durable interactive Claude Code sessions inside tmux. Use when the user mentions Claude Code tmux, ccmux, delegating work to Claude Code without print mode, live steering, Remote Control, AGENTS.md import, or installing the claude-code-tmux npm or Pi package.
Claude Code user-level engineering system: 5 agents, 5 skills, 10 hooks, 4 commands, multi-platform support. Based on the Claude Code Engineering Practice course.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Start or join a local XYZ discussion shared by two or more Claude, Codex, or other agent sessions through a compact six-digit ID. Use when a prompt says “Join XYZ AgentChorus #123456 as agent number two… — use the agent-chorus skill” (older invitations omit the trailing clause, and the legacy phrase “Join XYZ…
Use when user says "evaluate claude.md", "audit my agents.md", "check claude.md quality", "is my CLAUDE.md helping", "optimize my context file", "review my CLAUDE.md", "analyze my context files", "quality of my claude md", "check my agents.md", "audit context files", or "improve my CLAUDE.md".
Build and install Soul Code persona skills from the bundled persona dataset. Use when the user wants to generate, install, list, or switch to stylized coding personas such as CTRL, BOSS, LOVE-R, or MUM.
Convenes a multi-model "council" to answer a question, then synthesizes a single best answer — inspired by Karpathy's llm-council. Each member runs through its own subscription/sign-in CLI, not an API key: ChatGPT (the desktop app, via chatgpt-ask), Gemini (Antigravity agy), and Claude (claude -p), with Codex (codex…
Guide users through creating, reviewing, and improving OpenClaw skills following proven best practices. Use when someone asks to "create a skill", "write a SKILL.md", "make an OpenClaw skill", "publish to ClawHub", "review my skill", "improve my skill", "optimize skill description", "skill frontmatter help", "what…
Agent session telemetry for Claude Code — captures structured events from 14 hook lifecycle events with msgpack compression, optional encryption, and a real-time terminal dashboard.
★not rated 5 5mo agoA
tokens not measured
originalMIT
Auto-discover and communicate with any AI agent given its URL via API. Supports REST APIs (OpenAI, Anthropic, Ollama), WebSockets, and Gradio apps. Claude Code acts as the user, automatically detecting the agent's API interface and sending messages. Use when: (1) User provides an API endpoint URL, (2) Need to automate…
Response and engineering discipline for Claude Code, Codex, Pi, and OpenCode: no filler or hedging, RCA-formatted problem reports, docs-first implementation, root-cause fixes, behavior-level tests, and executed verification.
★not rated 5
changed 8d agoA
tokens not measured
originalMIT
Applies the right skill-design patterns when you create or improve an agent Skill, so you don't have to hand-pick them. Ships a catalog of 38 reusable behavioral patterns.
★not rated 5 3mo agoA
tokens not measured
originalMIT
Talk to a ccgateway agent directly from Claude Code. Spawns an isolated subagent session with the agent's full identity (CLAUDE.md, SOUL.md, IDENTITY.md, AGENTS.md) and ccgateway skills injected. Usage: /talk.
Use when answering questions about current Codex behavior, configuration, CLI features, hooks, skills, plugins, sessions, compaction, permissions, or other Codex-specific interfaces from official documentation.
Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code. Runs locally from the @claude-flow/cli npm package. Needs 5 environment variables to run.
Portable agent skills from Sunlight Research, starting with subagent-driven deep research.
★not rated 5 2mo agoA
tokens not measured
originalMIT
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: