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.
Skill Claude CodeCodex
Use Afu Brain as a MASL butler brain before executing OpenClaw or other agent tools. It turns private owner memory and human intent into safe decisions, skill routing, and approval gates.
AlexAI-MCP/GPT5.6-SOLTELU-Model-Inverter
Skill Claude CodeCodex
Optimize quality per token across GPT Codex, GPT Work, and Codex CLI by automatically selecting the best-fit GPT-5.6 Luna, Terra, or Sol profile and reasoning effort for the main task and every delegated subtask. Prioritize direct visible Codex execution and importance-aware subagent routing. Use automatically for…
Skill Claude CodeCodex
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill…
Plugin Claude Code
Bundles 1 skill · 115 tokens together
Autonomous native-tmux supervisor for Grok: launches a Dad/Son pane pair, keeps recurring supervision loops alive, records trajectory evidence, and gates checkpoint acceptance on real verification.
Skill Claude Code
A review and scaffolding guide for agent skills, including Claude and Cursor skills. It checks their instructions, descriptions, workflows, scripts, parameters, references, and delivery checklists, and can generate a skill template.
Plugin Claude Code
Bundles 2 skills · 109 tokens together
Skills for registering and using AgentKit — prove your agent is backed by a real human to get free or discounted access to x402 endpoints.
Skill Claude CodeCodex
Design and create traceable loop systems for user tasks. Use when the user invokes /loop-skill or asks to build, design, scaffold, run, or improve an iterative workflow with generations, audits, rewrites, logs, validators, max iterations, and explicit exit conditions.
danialhasan/ticket-swarm-workflow
Skill Codex
Use when Squad agent behavior, prompts, tool manifests, eval traces, trajectories, datasets, or applied-AI harness changes need to be engineered through source traces, golden/regression/challenge/canary cases, scorers or judges, and regression receipts before product claims or implementation closeout.
modelcontextprotocol-servers/google-search-mcp
Cursor rule Cursor
Rules for an AI coding assistant that explain MCP, a standard way for AI applications to connect to tools and sources of information. They cover MCP architecture, implementation, applications, servers, and clients.
Skill Claude CodeCodex
A scoring scale for evaluating how well a CLI is designed for AI agents, based on the "Rewrite Your CLI for AI Agents" principles.
Skill Claude CodeCodex
Use when a user is trying to discover an installable or reusable skill or workflow, especially when they ask for a skill for a task, want to compare nearby skill categories, or need help narrowing discovery results.
Skill Claude Code needs its repo
Deterministic outer-loop optimizer for a skill that already carries a frozen eval (produced upstream by an eval source such as create-skill-eval). Runs the frozen eval across user-chosen agents on fresh headless sessions via a pluggable adapter, grades quality/cost/perf, keeps the pareto-best variant, and versions…
Myr-Aya/GouvernAI-claude-code-plugin
Plugin Claude Code
Bundles 1 skill, 1 command, 1 hook · 117 tokens together
Achieve flow state safely with Claude Code. Auto-approves routine work, gates risky actions, hard-blocks dangerous patterns. Dual enforcement (skill + hooks), token cap for cost governance, full audit trail. Zero dependencies.
stuinfla/claude-code-internals
Skill Claude Code
Complete reverse-engineering of Claude Code's source architecture (v2.1.88) covering 50 internal systems.
Plugin Claude Code
Dev Team Kit — 73 specialist skills + 16 dispatchable subagents + 43 slash commands for coding agents. Spec-driven development, path-scoped rules system, anti-AI writing, memory consolidation, silent-failure hunting, context budgeting, skills-vs-agents disambiguation and more.
Skill Claude CodeCodex
Guide a learner through preparing for the Anthropic Claude Certified Architect – Foundations (CCA-F) exam using the Explain → Feynman → Quiz → Notes method with spaced-repetition reviews. Activates on "let's study CCA-F", "CCA-F prep", "study Claude certification", "Claude Certified Architect prep", continuation of an…
Plugin Claude Code
Bundles 81 skills, 42 agents, 7 hooks · 3,887 tokens together
Ferrox Factory is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
Skill Claude CodeCodex
Instructions for sending design-focused software tasks to the local Kimi Code command-line tool. It is intended for interface design, frontend work, repository exploration, review, and analysis of images or videos.
stevengonsalvez/agents-in-a-box
Plugin Claude Code
Plugin marketplace listing 5 plugins: reflect, ainb-fleet, ainb-hooks, caveman-stats, illustration.
Skill Claude Code
Keep app behavior in Harn while shared hosts draw the view and provide files, network, and browser features.
georgemarmelstein/superjurista-dev
Plugin Claude Code
Bundles 11 skills, 22 commands, 7 agents · 1,861 tokens together
Meta-ferramentas para criar sistemas agenticos judiciais: agentes, orquestradores, skills, teams e scaffold completo do SuperJurista.
Skill Claude CodeCodex
A skill that researches a person or vague need, extracts a way of thinking, and turns it into a reusable advisor skill.
Skill Codex
Delegate analytical, sandboxed, or long-running work to the Google Antigravity (agy) CLI through a JSON-bridge wrapper. Use when you need a second opinion, want to isolate side effects in a worktree, or need to run a long agent loop without blocking the main conversation.
Skill Claude Code
A structured workflow for software engineering tasks. It routes work through one of three levels, from a quick path to a full 11-step process, with checklists, approval gates, rollback rules, and records of decisions.
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: