Claude Code

81,561 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.

brewpage

6697

kochetkov-ma/brewpage-openapi

Plugin Gemini CLI

Publish HTML, Markdown, sites, KV, JSON and files on BrewPage; get a shareable link.

not rated 5 changed today A tokens not measured original Apache-2.0

crg

6698

n24q02m/claude-plugins

Plugin Claude Code

Bundles 6 skills, 3 hooks · 184 tokens together

Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

not rated 5 +1 changed today A tokens not measured original Apache-2.0

broomva-skills

6699

broomva/skills

Plugin Claude Code

Bundles 119 skills, 6 agents · 25,846 tokens together

All 112 broomva/skills agent skills (23 category buckets) as one plugin. Generated by scripts/buildpluginmarketplace.py.

not rated 5 changed 3d ago A tokens not measured original MIT

cursorrules

6701

syf2211/ruledoctor

Cursor rule Cursor

A collection of project rules for Cursor, an AI coding editor. The rules cover money and date formats, error handling, types, comments, linting, and safe Git use.

not rated 4 4mo ago A 111 tokens original MIT

My Commit Wizard

6702

kainulla/skillfire

Skill Claude CodeCodex needs its repo

Write a polished git commit message from my staged changes following Conventional Commits, with an optional emoji and the related issue key.

not rated 4 4mo ago A 29 tokens original MIT

skala-review

6703

yongchane/skala-review-skill

Skill Claude Code

A Korean-language study and review assistant for SKALA trainees. It uses lectures, PDFs, notes, and keywords for question-based review, summaries, and drafts for learning platforms or personal Markdown notes.

not rated 4 3mo ago A 88 tokens original MIT

madrox

6706

barkain/madrox

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 11 tokens together

MCP server that orchestrates multiple Claude CLI instances as parallel workers with a real-time dashboard.

not rated 4 3mo ago A tokens not measured original MIT

claude-pty-agents

6707

coredo-eu/codex-claude-orchestrator

Skill Claude CodeCodex

Launch and safely retire one bounded Claude Code stage per owned session, with a Sonnet 5.5 parent by default, role-routed Haiku 5.5/Sonnet 5.5/Opus 5.5/Fable 5.1 subagents, and GPT-5.6 native Codex fallback. Use when Claude is requested or a bounded repository stage benefits from context isolation. Do not use for…

not rated 4 changed 18d ago A SkillSpector: pass 113 tokens original MIT

better-skills

6708

psylch/better-skills

Plugin Claude Code

Bundles 3 skills · 347 tokens together

Skill development toolkit for AI coding agents: create, review, and publish skills with runtime UX best practices.

not rated 4 8mo ago A tokens not measured original MIT

ctf

6709

zebbern/termstack

Agent Claude Code

CTF Coordinator — Triages CTF challenges by category and delegates to specialized agents (web, crypto, forensics, binary, reversing, misc, bonus). user-invocable: true argument-hint: 'Challenge info — e.g.

not rated 4 7mo ago A 53 tokens

swift-networking

6710

jeremieb/swift-unit-test-instructions

Skill Claude CodeCodex

Builds a protocol-based async/await networking layer with URLSession, testable abstractions, error handling, and mock support for Swift projects. Use when user says "add networking", "create an API layer", "fetch data from API", "build a network service", "add URLSession", "implement HTTP requests", "create a REST…

not rated 4 8mo ago A 82 tokens original MIT

cavemenko

6711

ruslanlap/cavemenko

Plugin Claude Code

Bundles 5 skills · 256 tokens together

Ultra-compressed Ukrainian mode for Claude Code. −49% output tokens on top of a terse control, measured. Auto-detect language, native Ukrainian pro-drop, real token stats.

not rated 4 changed 1mo ago A tokens not measured

devkit

6712

5uck1ess/devkit

Plugin Claude Code

Bundles 39 skills, 6 agents, 4 hooks · 4,351 tokens together

A deterministic development harness for AI agents — YAML workflow engine, self-learning hooks, and multi-agent consensus.

not rated 4 +1 changed 2d ago A tokens not measured original MIT

dev-task

6713

yunsii/wezdeck

Skill Claude CodeCodex needs its repo

A set of rules for handling development work in approved repositories, including when to use the main branch or a separate worktree, which is an isolated copy of a repository.

not rated 4 changed 28d ago A 69 tokens original MIT

fable-mode

6714

lucianlamp/fable-mode

Skill Claude CodeCodex

A set of working rules for smaller AI coding sessions, based on a discipline called Fable mode. It emphasizes clarifying the task, breaking it into parts, checking results, and reporting evidence.

not rated 4 4mo ago A 74 tokens original MIT

ab

6715

zapgun-ai/clawback

Skill Claude CodeCodex

Run a counterbalanced A/B knob block end to end and produce a report. Orchestrates the whole validation loop the other skills do piecemeal — for each arm it starts a clawback proxy with that arm's knobs and its OWN --state file (fresh SESSION KEY, no clawback-side carry-over), drives N turns of load through it (pty or…

not rated 4 5mo ago A 0 tokens

architect

6716

vignesh2027/claude-best-practice

Agent Claude Code

Use for system design, architecture decisions, database schema design, API design, technical planning. Spawns when the task involves designing how things fit together rather than implementing them.

not rated 4 2mo ago A 36 tokens

agent-mcp-cli

6718

anilcancakir/laravel-agent-mcp

Skill Claude CodeCodex

Call the agent-mcp read-only tools from the shell with php artisan agent-mcp:call, locally or against a remote app. Use when the agent-mcp MCP server is not registered in the client, or for a one-off call, a script or CI. Not for writes; no tool writes to the database.

not rated 4 changed 5d ago A 70 tokens original MIT

searching-with-serpapi

6719

aryrabelo/serpapi-agent-toolkit

Skill Claude CodeCodex

Use when an agent needs live, structured search-engine data through SerpApi (web results, news, shopping, local, jobs, flights, scholar, images, video). Covers picking the right engine for the intent, choosing compact vs complete output, query operators, pagination, deduping and citing results, and when NOT to search.…

not rated 4 5mo ago A 104 tokens original MIT

toolshedlabs-hash/nightshift

Skill Claude CodeCodex

Run a coding agent unattended overnight, long running agent safety, stop a runaway loop, cap agent token spend. Sets up four guardrails around an agent loop you already have: a resumable handoff file so an interrupted run continues, a verification gate that fails closed so unchecked work is never accepted, a runaway…

not rated 4 3mo ago A 146 tokens 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: