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.
Plugin Claude Code
Bundles 6 skills · 361 tokens together
Governança de projeto para desenvolver com agentes: a estrutura que sustenta o projeto (PRD, roadmap, demandas versionadas) e o ciclo que leva cada demanda da ideia ao registro do que foi feito.
Plugin Claude Code
Bundles 1 command, 1 agent · 125 tokens together
Call K-EXAONE 236B (LG AI Research, served by FriendliAI) from Claude Code via the opencode CLI: /k-exaone.
Plugin Claude Code
BlueStep tooling for Claude Code — bluestep-tools for B6P component workspaces (spec-driven skills, b6p CLI integration, subagents, hooks, platform reference) and core-tools for every other repo (core rule set, /task, /plan, subagents).
Agent Claude Code
GSD-Lite Protocol — Pair programming with AI agents while maintaining ownership of reasoning and decisions.
Skill Claude CodeCodex
Control Planchette, the terminal IDE this session may be running in: list its terminals, open one, send a prompt to another agent, wait for it to finish, and read its output. Use only when the user explicitly asks to inspect or drive Planchette terminals, or to hand work to another agent beside this one. Do not use…
Open-Agent-Tools/General-OAT-Skills
Plugin Claude Code
Bundles 10 skills · 683 tokens together
Dev workflow and AI agent development skills for Claude Code.
xisanpi/skill-map-codex-plugin
Skill Codex
Semantically analyze a Codex Skill and its execution-bearing local references, generate a validated interactive structure map, open it in a browser, and return a reopen link. Use when a user asks what a Skill does, wants to understand or visualize a Skill, provides or tags a SKILL.md for explanation, or asks for a…
Skill Claude Code
Senior architect review for multi-agent systems, prompt engineering, and agent harness design. Three modes: AUDIT (full system evaluation with 13-dimension scoring and cross-session trend tracking), REVIEW (focused prompt/skill teardown), DESIGN (architecture thinking partner — new systems, existing system evolution…
MarceloSoares1970/engineering-with-governance
Skill Claude CodeCodex
Governance guidelines for AI-assisted engineering — they reduce the costliest LLM mistakes in code with side effects. Load when the environment has no governance rules of its own, or to read/review the text. If the rules are already in the project instructions, don't reload, as it would repeat in condensed form what…
Agent Claude Code
Orquestador principal. Recibe la solicitud del usuario, selecciona el workflow adecuado y coordina a los subagentes. NUNCA implementa directamente.
Plugin Claude Code
Bundles 24 commands, 19 agents, 6 hooks · 2,479 tokens together
For people who know what they want to build and need help shipping it. A single Go binary that carries the why from idea to shipped reality, usable as a plugin in compatible agent harnesses.
Skill Codex
Form, transfer, continue, or receive an independent AoA responsibility with a role-bearing actor. Use when an obligation needs its own holder, mandate, or continuity across incarnations. Ordinary tasks and native Codex helpers do not need this skill.
Command Claude Code
This page describes the llm.agent automation command in Cerb, which interfaces with Large Language Models (LLMs) to maintain conversation history and manage tool use. The command automatically handles authentication, API calls, chat history, and tool invocation. To use this command, you provide a systemprompt, one or…
Skill Claude CodeCodex
Ask which skill or flow fits your situation. A router over the skills in this repo.
Agent Claude Code
Orchestrates feature development across the project. Receives an approved implementation plan, identifies affected files, delegates work to the developer, routes changes through code review and security review gates, coordinates fixes when a gate fails, then hands off to the tester for a gated commit and the…
Cursor rule Cursor
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 agent · 419 tokens together
A reasoning framework based on the Yi Jing, an ancient Chinese text, for examining opposing forces, breaking systems into states, and considering how situations may change. It is presented as a thinking discipline, not fortune-telling.
Cursor rule Cursor
Mandatory agentic development process — feature analysis, architecture, tasks, squad development, review.
Plugin Claude Code
Bundles 1 skill, 1 hook · 131 tokens together
Pre-execution layer for Claude Code. Before implementing anything, scans for existing skills, MCP servers, CLI tools, plugins, repos, templates, SDKs, or APIs that already solve the task, presents the best candidate (or a shortlist) with risk and effort, and asks for approval before writing code.
Skill Claude CodeCodex
Use whenever the user is building an app by directing an AI agent and wants it to survive production, or mentions "the book", "the handbook", "Vibe Coding with Confidence", or asks where to start, what to do next, how to structure, test, ship, secure, or operate what they are building. Also use when they paste a…
Plugin Claude Code
Bundles 2 commands · 11 tokens together
Local web dashboard for managing Claude Code skills, MCP servers, plugins, agents, and custom commands.
Plugin Claude Code
Bundles 11 skills, 5 hooks · 461 tokens together
Master of Panes — orchestrate parallel Claude Code dev sessions across tmux panes with state tracking, auto-cleanup, and slash commands.
MCP server Claude CodeCodexCursor +2
An AST-based context router to reduce AI token usage. Provides code skeletons and structural symbols to LLM agents (Cursor, Claude, Antigravity) for efficient codebase context routing. Runs locally from the @penqwin/mcp npm package.
MCP server Claude CodeCodexCursor +2
Local Fusion MCP server — panel→judge→synthesis on the Claude CLI subscription, no OpenRouter. Runs locally from the fusion-mcp Python package.
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: