Plugins for Claude Code

20,861 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

vibe-stack

9049

OneWave-AI/open-agent-stack

Plugin Claude Code

Bundles 14 skills, 1 command, 1 agent · 863 tokens together

The full vibe-coding loop: scaffold an app or marketing site with a real design system, animate it with GSAP and a real motion system, replace the fake data with a real backend, unstick it when it breaks, strip the AI look, ship it, and demo it.

not rated 3 1mo ago A tokens not measured original MIT

loop-contract

9051

hdkhosravian/loop-contract-skill

Plugin Claude Code

Bundles 1 skill · 280 tokens together

Turns a rough, long-running request into a loop-engineered contract and then executes it — frozen scope counted from the source, an achievement oracle written red before the work, a distinct proof per item, and a completion gate that runs the oracle itself so "done" is a fact rather than a claim.

not rated 3 1mo ago A tokens not measured original MIT

demo-video-plugin

9052

lukaskellerstein/claude-my-marketplace

Plugin Claude Code

Bundles 9 skills, 5 agents, 2 hooks · 1,923 tokens together

Turns a project repo into a narrated, edited demo video. Reads the codebase, writes a storyboard with real narrative value, prepares deterministic demo state, drives the UI with Playwright (web, launched Electron, or an attached running app) recording one clip per section with Playwright video or OBS over…

not rated 3 changed 3d ago A tokens not measured

pm-chief-of-staff

9053

pe-menezes/pm-chief-of-staff

Plugin Claude Code

Bundles 10 skills, 1 hook · 1,133 tokens together

Chief of Staff pessoal pra quem trabalha com produto: um segundo cérebro de trabalho que nasce de uma conversa, mora em arquivos markdown seus e se molda a você. Rode /pm-chief-of-staff:setup numa pasta vazia.

not rated 3 +1 1mo ago A tokens not measured original MIT

pasteup

9054

tmoody1973/pasteup

Plugin Claude Code

Bundles 1 skill, 4 commands · 326 tokens together

Halftone paper-collage stop-motion ads: decode a reference into an editable spec, generate cut-out elements on the Gemini image API, and assemble build-from-empty motion with a deterministic local compositor, complete with the handmade stop-motion wobble. No paid video model.

not rated 3 2mo ago A tokens not measured original MIT

branch-guard

9055

karlkfi/claude-bouncer

Plugin Claude Code

Bundles 2 hooks

Cut routine git/gh approval prompts: auto-approve safe commands (read-only, staging, branch/worktree create, feature-branch commits & pushes) and confirm protected-branch or destructive ones.

not rated 3 changed 4d ago A tokens not measured original MIT

c-brain

9056

Yuno15-bb/c-brain

Plugin Claude Code

Bundles 3 skills, 8 agents, 5 hooks · 585 tokens together

A memory that grows. Your agent is brilliant within a session and amnesic between two — this gives it a persistent knowledge trunk on your machine: what you work out once is distilled into a note, filed, linked, and surfaced automatically next time, from any project. It makes no request of its own — no telemetry, no…

not rated 3 +1 23d ago A tokens not measured original Apache-2.0

river-review

9057

s977043/river-review

Plugin Claude Code

Bundles 139 skills, 18 commands, 5 agents, 3 hooks · 8,945 tokens together

Turn review into an organizational judgment asset. Review Judgment as Code for AI-assisted development, delivered as a capability pack for Claude Code: your team's review criteria as versioned, repo-owned skills (a Skill Registry), driven by a review agent that runs perspective-based reviewer roles (code, security…

not rated 3 changed today A tokens not measured original MIT

supervisor

9058

ma-nucho-pro/supervisorLLM-plugin

Plugin Claude Code

Bundles 27 agents, 1 hook · 559 tokens together

Universal Supervisor adapter for Claude Code: web-grounded research, expert code/frontend work, 27 independent specialists, adversarial review, correction loops, and an independent Stop release judge.

not rated 3 +1 1mo ago A tokens not measured

codex-subagents

9060

xuio/claude-code-codex-subagents

Plugin Claude Code

Bundles 1 skill · 88 tokens together

Claude Code plugin for OpenAI Codex subagents, Codex Spark, parallel code review, adversarial review, and native follow-up sessions through a daemonless MCP server with read-only defaults and explicit full-access mode.

not rated 3 2mo ago A tokens not measured original MIT

project-brain

9062

vikasgrac/project-brain

Plugin Claude Code

Bundles 2 skills, 3 hooks · 76 tokens together

Every Claude Code session, in every project, captured into one plain-Markdown brain you own. Index-first recall, automatic redaction, LLM-distilled session notes.

not rated 3 1mo ago A tokens not measured original MIT

vp-beads

9063

voxpelli/claude-beads

Plugin Claude Code

Bundles 8 skills, 1 agent, 3 hooks · 1,562 tokens together

Sprint workflow automation: backlog grooming, retrospectives, upstream vendor tracking, cross-project synergy tracking, swarm wave orchestration, vendor sync, and bilateral sibling reconciliation for projects using beads and Basic Memory.

not rated 3 +1 4d ago A tokens not measured original MIT

scala-lsp

9064

zircote/scala-lsp

Plugin Claude Code

Bundles 1 command · 8 tokens together

Scala language server plugin for Claude Code with Metals LSP integration and automated hooks for formatting, linting, and testing.

not rated 3 1mo ago A tokens not measured original MIT

slop-chop

9065

dcadolph/slop-chop

Plugin Claude Code

Bundles 1 skill, 1 command · 98 tokens together

Chop AI writing tells out of text. Wraps the slop-chop CLI so Claude can strip em-dashes, semicolons, and buzzwords, enforce a spelling dialect, or run the model rewrite pass on a draft.

not rated 3 yesterday A tokens not measured original MIT

mcp-redteam

9066

m0rvayne/mcp-redteam

Plugin Claude Code

Bundles 1 skill · 31 tokens together

Full audit and penetration testing of MCP servers — health, architecture, completeness, security.

not rated 3 changed 9d ago A tokens not measured original MIT

agent-perms

9067

Mearman/agent-permissions

Plugin Claude Code

Bundles 1 MCP server

Cross-agent permission policy sync daemon. Keeps native agent config files (.claude/settings.json, opencode.json, etc.) bidirectionally synced with .agents/permissions.json. No tools exposed — purely a background sync service.

not rated 3 3d ago A tokens not measured original Apache-2.0

trelly

9068

brandonkramer/trelly

Plugin Claude Code

Bundles 2 skills · 174 tokens together

Trello CLI + MCP tools — boards, lists, cards, search, and raw API via trelly-mcp.

not rated 3 2mo ago A tokens not measured

agentic-atlas

9069

aj604/agentic-atlas-plugin

Plugin Claude Code

Bundles 3 skills, 2 agents, 1 MCP server · 707 tokens together

Do design work with Agentic Atlas over hosted MCP at agentic-atlas.dev/mcp/. Three skills — audit an existing agent artifact, design a new agent system, apply one named pattern — over two read-only agents; no SDK, CLI, local server, or content bundle is installed.

not rated 3 changed 10d ago A tokens not measured

bxc

9070

aphrody-code/bxc

Plugin Claude Code

Bundles 22 skills, 3 commands · 1,491 tokens together

Complete cross-platform Claude Code plugin for the bxc stack: Bun runtime + Rust FFI (DOM, lolhtml, X clients, algorithms), native keyless @aphrody/x X/Twitter client, keyless @aphrody/xai Grok client with deep native X tool calling, bxc-native-mcp server, monorepo scraper packages, stealth crawling, autopilot loops.

not rated 3 changed 11d ago A tokens not measured original Apache-2.0

puckapi-skills

9071

PuckAPI/claude-sports-analytics

Plugin Claude Code

Bundles 28 skills · 2,943 tokens together

28 Claude Code skills for hockey analytics with PuckAPI. NHL data exploration, hockey analytics, betting models, and research workflows.

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

groundtruth

9072

veltiq/groundtruth

Plugin Claude Code

Bundles 1 hook

The human-in-the-loop for AI coding: verify every turn against the real diff, then make the agent run/screenshot/test and self-fix before finishing.

not rated 3 +1 1mo 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: