38,442 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 Codex
Execute an existing multi-agent plan in this repository: run an execution preflight against docs/tasks.md and the kickoff prompt, then hand them to a fresh orchestrator that spawns development, QA, and independent-review agents until reviewed code is on disk. Use for requests to run the build, kick off or start…
hwchany0ung/claude-agent-playbook
Skill Claude CodeCodex
Guide for running multiple Claude Code agents concurrently. Identifies parallelizable tasks, manages dependencies, and integrates results. Based on real multi-agent workflows.
Skill Claude CodeCodex
Runtime helper for autonomous-research-loop ledgers plus headless drive, host-owned multi-agent panel phases (--panel on, auto, or off), and the default cross-platform force-loop kit (bootstrap/start/drain with enforce/hard/notify defaults). Use to initialize, append, validate, inspect, smoke-test, drive, or…
Skill Claude CodeCodex
Publish skills and tools to the public agent-toolkit repo. Use when user says "publish skill", "push to marketplace", or wants to share skills publicly.
Plugin Claude Code
Bundles 5 skills · 462 tokens together
Reusable Claude Code skills for software development workflows.
TriangulosTecnologia/devanity-skills
Skill Claude Code
Guard and improve a repository's AI-readiness. Run /guardian plan, review, audit, improve, or docs to keep it in basis-form (a basis of decisions, not a list of cases) — compressible, contractual, verifiable, safe — and to migrate rules from prose into deterministic enforcement.
ashaykubal/essential-agents-skills
Skill Claude Code
Generates Claude Code skills from requirements using adaptive interview, complexity classification, and iterative validation. Use when creating new skills, scaffolding skill structure, or generating skills with sub-agent orchestration.
Skill Claude CodeCodex needs its repo
Build TypeScript MCP clients with composable code snippets. Includes agentic pattern with LLM integration, server-initiated requests (sampling, elicitation), and dynamic discovery. Use when creating applications that connect to MCP servers.
Skill Claude CodeCodex
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.
kirill-sviridov/agent-dev-skills
Plugin Claude Code
Bundles 4 skills · 299 tokens together
Opinionated skills for building and debugging LangGraph agents and for prompt engineering: pick a stack, write a spec, debug a broken graph, and write better prompts.
DerekYRC/agent-thinking-skills
Plugin Claude Code
Bundles 2 skills · 284 tokens together
First Principles thinking mode. Forces AI to break out of analogical reasoning and re-derive solutions from fundamental truths. Five-step framework: identify assumptions, strip them, return to ground truths, derive from scratch, compare.
bnb-attestation-service/agent_scan_skills
Skill Claude CodeCodex
An agent-search skill for discovering ERC-8004 agents by name, skill, or a natural-language request. ERC-8004 is a standard for registering and identifying agents on a blockchain network.
ltczding-gif/agent-supervision-skills
Skill Claude Code needs its repo
Use when the user wants to delegate work to the local Claude Code CLI (claude --print, claude --bg, claude ultrareview) — substantive tasks, multi-turn resume, structured output, multi-agent code review, background sessions — and then independently verify what Claude did. Useful from Codex / Kimi / any agent that…
Plugin Claude Code
Bundles 29 skills, 12 commands, 9 agents, 1 hook · 1,702 tokens together
Full-lifecycle engineering skills for AI coding agents — orchestration chain from brainstorm to ship, with production-grade engineering standards at every step.
DESONGs/agent-skill-Self-evolution
Skill Claude CodeCodex
Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.
Skill Claude CodeCodex
A security service that decides whether an AI agent may call a tool. It uses user roles, task details, signed permissions, data labels, approvals, and audit records; risky requests can be stopped for human review.
Plugin Claude Code
Bundles 6 skills, 3 agents · 1,111 tokens together
The autonomous engineering system for repository portfolios — engineer, read-only surveyor, and meta-engineer agents; portfolio, product, spend, and improvement workflows; cross-tool instruction architecture and skill discovery; configured by the consumer AGENTS.md.
254095728-bit/agent-skill-menu
Skill Codex
Discover, search, understand, organize, and inspect locally installed Agent Skills across Codex, Claude Code, GitHub Copilot, Cursor, Gemini CLI, OpenClaw, and custom roots. Use when the user asks what skills are installed, which skill fits a task, wants relevant skill options from the current conversation, searches…
Skill Claude Code
Manage AI agent skills - download from GitHub, discover skills in repositories, deploy to multiple agents with symlink support, update, uninstall with safe deletion, and track versions. Use when users want to install, manage, or update skills for AI coding assistants like Claude Code, Cursor, Windsurf, etc.
Plugin Claude Code
Bundles 15 skills, 2 hooks · 1,107 tokens together
Source-first AI-agent toolkit with native Claude Code plugin metadata, English setup routing, Windows-safe hook repair, opt-in repo auto-update, and local bridge adapters.
Plugin Claude Code
Bundles 2 skills · 68 tokens together
Developer tools for building with the Gravity Rail SDK and CLI — guides, patterns, and recipes for workspace automation, AI assistants, and multi-channel communication.
Plugin Claude Code
Bundles 1 skill, 7 commands · 0 tokens together
Enterprise-grade AI workflow orchestration system with multi-agent task decomposition, context isolation, and autonomous execution loops.
Plugin Claude Code
Bundles 13 commands, 5 agents · 377 tokens together
Fully Agentic Multi-Agent Orchestration Framework for Claude Code - Autonomous dev → UAT → QA pipeline with 150k token-budgeted tasks, parallel-first execution, retry limits, and enforcing quality gates.
Plugin Claude Code
Bundles 4 skills · 233 tokens together
Scheduler/launcher for Claude Code headless runs. Cron-scheduled jobs launch claude -p in a folder, with per-job model, reasoning effort, timeout, duplicate guard, missed-tick catch-up, log rotation, a process-level circuit breaker that treats a Claude usage-limit / transient API overload as a skip (not a failure) so.
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: