38,360 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 when designing or reviewing AI agents that must assess their own output quality — covers confidence scoring and calibration, chain-of-thought reflection, LLM-as-judge, hallucination self-detection, output quality verification, eval-driven development, and self-evaluation anti-patterns with examples in TypeScript…
Skill Claude CodeCodex
Skill "code-analysis" from madhurprash/AutoEvals, covering code analysis skill, agent architecture detection, 1. subagents architecture (centralized orchestration), 2. skills architecture (progressive disclosure) and 3. handoffs architecture (state-driven transitions).
Plugin Claude Code
Bundles 13 commands, 1 MCP server · 194 tokens together
Multi-server MCP proxy with AI context provenance tracking and quality feedback loop. Enables self-aware, self-improving AI through automatic lineage tracking.
GongLingRui/agent-skills-factory
Skill Claude Code
An automatic selector that chooses the most suitable item from a list of tasks based on the user's original request. It limits how many items it returns to a fixed fraction of the available choices.
Skill Codex
Use when developing cmux-home, explaining its cmux event-driven Rust TUI, or adapting it into a custom cmux launcher for parallel agent workflows across worktrees, multiple checkouts, SSH hosts, VMs, browsers, or review dashboards.
HaodiFan/engineering-everything
Skill Claude CodeCodex
Use when a wrapped Skill entry activates the canonical EvoZeus-CoEvolve Harness contract before its business flow.
JularDepick/AGENTS.md-Best-Practices
Skill Claude CodeCodex
A collection of guidance documents for agents working with AGENTS.md, a file that tells coding agents how to work in a project.
Plugin Claude Code
Bundles 1 skill · 97 tokens together
Operate the Herdr-to-Telegram bridge: per-agent topics, send/interrupt/queue, status, managed bots, cockpit, maintenance.
Skill Claude CodeCodex
Autonomous agent loop design in 10 steps.
Skill Claude CodeCodex
Validate a Loooom/Agent Skills SKILL.md against the official Anthropic spec using skills-ref. Checks frontmatter structure, required fields, naming rules, and directory conventions. Use when building or publishing a new skill.
Skill Claude Code
Meta-skill that generates project-specific scaffold skills by reading your repo conventions.
produckyou-design/agent-director-protocol
Plugin Claude Code
Bundles 1 skill · 56 tokens together
A platform-neutral director/implementer operating protocol for AI coding agents. One high-capability director plans, decomposes, delegates, and reviews; implementer subagents write the actual code. Includes a defined escalation path (Rescue Agent promotion, then takeover) instead of leaving stuck implementers to…
Skill Claude CodeCodex needs its repo
Create, test, and optimize Grok skills. Use when creating a skill from scratch, editing one, testing if a skill works, optimizing skill triggering, benchmarking performance, or packaging a .skill file. Triggers: "create skill", "new skill", "edit skill", "test skill", "skill not triggering", "optimize description"…
dungnotnull/mountain-landslide-early-warning-agent-skill
Skill Claude CodeCodex
The skill system follows a skill-registry pattern with a chain-of-thought router. Skills are declarative descriptors (metadata + I/O schemas + optional handler) registered in a single registry. The router scores skills against an intent, emits a rationale, and returns an ordered dispatch plan. The orchestrator…
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
heymitch/claude-cowork-bootcamp
Plugin Claude Code
Bundles 1 skill · 112 tokens together
Dispatch Chain — template for building chain skills that invoke other skills in a named order via Dispatch. Runs without stopping mid-sequence. Customize the ordered list and handoff rules for your chain; leave the never-stop contract as-is. Includes build-time local-file discovery and preflight skill mapping.
Plugin Claude Code
Bundles 15 skills, 1 command, 1 hook · 1,759 tokens together
Interactive architecture advisor for multi-agent LLM systems. Guides through structured discovery, tension resolution, requirements stress testing, and architecture proposal. Generates C4 diagram, ADR, decision matrix, and NFR checklist. Supports post-artifact deepening on domain-specific topics.
Skill Codex
An orchestrator for composing and evolving multiple Agent Skills. Use when users ask to mix, combine, stitch, or assemble Skills, or describe a new Skill that needs several capabilities. Discover candidates from public GitHub Skills, inspect interfaces, licenses, and security boundaries, generate multiple…
Skill Claude CodeCodex
Use when someone wants to ship one set of agent skills/plugins to multiple AI apps (Claude Code, Cursor, Antigravity CLI, GitHub Copilot, OpenAI Codex CLI) from a single source, and needs to create or update a pluginpack.config.ts — choosing targets, source layout, MCP servers, and output directories.
Parth3930/recursive-thinking-mcp
MCP server Claude CodeCodexCursor +2
MCP server "recursive-thinking" as configured in Parth3930/recursive-thinking-mcp. Launched with recursive-thinking-mcp.
Plugin Claude Code
Bundles 4 skills, 10 agents, 1 hook · 725 tokens together
Meet your new sous chef, Jeff: a model-native quality control plane and cooperative workflow protocol for trusted operators and friendly agents, not a security sandbox.
Skill Claude CodeCodex
Use when named delegation is a genuine option for current work, when preparing or reviewing a handoff, or when continuing delegated work to a verified outcome. It supplies context recovery, deliberate skill selection, necessary-only delegation, evidence requirements, and continuation discipline. Do not use for…
Plugin Claude Code
Bundles 32 skills · 1,916 tokens together
briefbound-skills. Chinese-first Codex skill pack for intent alignment, dynamic routing, lightweight development, code review, UI design, and AI research workflows.
Skill Claude CodeCodex
A review and cleanup method for instructions stored in files such as CLAUDE.md, AGENTS.md, skills, context, and memory.
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: