Claude Code

81,493 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.

claude-hook-advisor

3097

sirmews/claude-hook-advisor

Plugin Claude Code

Bundles 5 commands, 3 hooks · 27 tokens together

Intelligent command history tracking with automatic failure detection. Tracks all bash commands Claude runs (successful and failed) with semantic directory aliasing and command mapping.

not rated 24 11mo ago A tokens not measured

fp

3098

vynazevedo/first-plan

Plugin Claude Code

Bundles 19 skills, 19 commands, 4 agents, 1 hook · 2,190 tokens together

Camada compilada de contexto para qualquer AI coding tool. Compila projetos em estrutura .first-plan/ com 15 camadas (discovery, conventions, reuse, features, quality, contracts, evolution, runtime) e gera arquivos de instrução tool-specific (AGENTS.md para Codex, .cursorrules para Cursor, .github/copilot-instructions.

not rated 24 changed 1mo ago A tokens not measured original MIT

worker-relay

3099

VsevolodUstinov/openclaw-worker-relay

Skill Claude CodeCodex

Run Codex CLI, Claude Code, or another supported external agent as a supervised asynchronous worker with strict OpenClaw routing, progress notifications, result delivery, session resume, optional provider fallback, and multi-turn supervisor ownership. Always use whenever the user asks to call, run, invoke, use, ask…

not rated 24 3mo ago A 132 tokens original MIT

skill-atlas

3100

danielLublinsky/Skill-Atlas

Plugin Claude Code

Bundles 2 skills, 1 command, 2 hooks · 231 tokens together

Graph, categorize and search your installed Claude Code skill collection: what is loadable, what is disabled, what points at things that no longer exist — plus a zero-token searchable tier for dormant skills.

not rated 24 2mo ago A tokens not measured original Apache-2.0

prompt-optimizer

3101

ckanner/agent-skills

Skill Claude CodeCodex

This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured prompts and need assistance transforming them into clear, effective, and well-structured instructions that AI models…

not rated 24 +1 1mo ago A 83 tokens original Apache-2.0

rudder

3102

RudderCode/Rudder

Plugin Claude Code

Bundles 6 skills, 2 hooks · 491 tokens together

Maintain a device-local spec from coding-session intent, then generate focused unit tests with your existing coding agent.

not rated 24 1mo ago A tokens not measured original Apache-2.0

lofn-music

3104

LocalSymmetry/lofn

Skill Claude CodeCodex

Run Lofn music/audio pipeline, Suno-ready prompts, lyrics, song guides, and music production briefs. Do NOT use for static image prompts, QA audit, or final ranking.

not rated 24 2mo ago A 43 tokens

skill-grep

3105

LittleDinoC/skill-grep

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.

not rated 24 7mo ago A 46 tokens original Apache-2.0

eva-galperin

3106

dtannen/icon-agents

Agent Claude Code

Eva Galperin, cybersecurity activist and Director of Cybersecurity at Electronic Frontier Foundation (EFF). Expert in digital rights, surveillance, stalkerware, and protecting vulnerable populations from cyber threats. Focuses on making cybersecurity accessible to journalists, activists, and marginalized communities…

not rated 24 1y ago A 63 tokens

jasoseo

3107

KangRyun/jasoseo-plugin

Plugin Claude Code

Bundles 1 skill, 2 agents · 404 tokens together

A workflow for writing Korean job-application personal statements, known as self-introduction letters. It covers company research, drafting, length adjustment, expert review, editing, and final checks for applications to multiple employers.

not rated 24 changed 1mo ago A tokens not measured original MIT

vibe-testing

3108

knot0-com/vibe-testing

Skill Claude CodeCodex

This skill should be used when the user asks to "test my specs", "validate my design docs", "find gaps in my architecture", "stress-test the spec", "vibe test", "pressure test the docs", or mentions spec validation before implementation begins.

not rated 24 7mo ago A 57 tokens original MIT

whatsup

3109

sshh12/claude-plugins

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 116 tokens together

WhatsApp MCP server for Claude Code via Baileys — bidirectional channel with allowlist gating, push notifications, and the reply/react/edit/download tool surface.

not rated 24 4mo ago A tokens not measured original MIT

pragma

3110

peteski22/agent-pragma

Plugin Claude Code

Bundles 12 skills, 2 agents · 237 tokens together

Deterministic linting hooks, semantic code validators, and a multi-LLM advisory council. Enforces coding rules mechanically — not by suggestion.

not rated 24 changed 8d ago A tokens not measured original Apache-2.0

world-model-mcp

3113

SaravananJaichandar/world-model-mcp

Settings file Claude Code

One of 5 in settings.json

Agent settings declaring 4 hook events (PostToolUse, PreToolUse, SessionStart, SessionEnd).

not rated 24 1mo ago A tokens not measured original MIT

design-to-code

3115

ursazoo/lanhu-to-code

Skill Claude CodeCodex

Lanhu to Code workflow for Claude Code. Convert Lanhu design URLs into Vue/React frontend code with component reuse, design token mapping, TODO-safe business logic, and optional code review.

not rated 24 6mo ago A 42 tokens

repl-scratchpad

3116

knot0-com/repl-scratchpad

Skill Claude CodeCodex

Use instead of chaining 3+ Bash calls, grep/cat/find pipelines, or any multi-step data processing. This skill should be used when the user asks to "start a scratchpad", "use the REPL", "scratchpad mode", "persistent Python session", or when a task involves exploration, analysis, or file processing that would benefit…

not rated 24 7mo ago A 122 tokens original MIT

forge-cli

3118

LinekForge/forge-hub

Skill Claude CodeCodex

A command-line management tool for Forge Hub, a service that connects agent instances to chat channels and routes messages between them.

not rated 24 5mo ago A 0 tokens original MIT

bar-observatory

3119

bar181/bar-observatory

Plugin Claude Code

Bundles 5 commands, 21 hooks · 104 tokens together

Local-only, deterministic flight recorder for Claude Code agent sessions. Five-channel effort ledger (T/R/L/Δ/E), report generation, and a read-only MCP query surface. Pure Rust + SQLite; nothing leaves your machine.

not rated 24 2mo ago A tokens not measured original MIT

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: