Claude Code plugins

Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.

until

claude

The outer loop for coding agents. No code until the Plan is agreed — Until moves peer review onto the Plan and checks every Pull request against it.

6 skills · 1 MCP server · hooks

until-dev/plugins 32

Lets Claude read your REAPER session, set FX, write automation and measure mix moves. Runs on your computer next to REAPER and needs a one-time local install.

7 skills · 1 MCP server

wretcher207/reaper-daemon 32

Verified P0-A MCP delegation with macOS arm64 certified; eligible Linux Codex editing is tested; native Windows Codex editing is unsupported. Codex edit eligibility requires its proven native sandbox.

3 skills · 4 agents · 1 MCP server

PyModel/claude-architect 32

软考(计算机技术与软件专业技术资格考试)备考工具 - 自动生成选择题、问答题、论文题并提供智能评分

2 commands · 5 agents

coldingcode/ruankao-agent 32

airlayer

claude

Semantic SQL compiler — compile .view.yml schema definitions into dialect-specific SQL. Unix-philosophy CLI designed as a tool-use interface for LLMs.

6 skills · 1 command

oxy-hq/airlayer 32

EUMETSAT agent skills: eumdac, ewccli, firecube, esf-satellite-data, feature-db-client, ewc-community-hub, ml-menu

7 skills

eumetsat/skills 32

peekie

claude

Teaches the agent when and how to reach for the peekie CLI for Xcode .xcresult bundles. Ships as an umbrella skill plus one dedicated sub-skill per subcommand (peekie-tests, peekie-warnings, peekie-errors, peekie-coverage, peekie-attachments) — fully-qualified test names, attachment extraction, JSON output for jq pipelines, SonarQube reports

6 skills

dodobrands/Peekie 32

pendle-v2

claude

Pendle V2 DeFi protocol — 25 semantic tools for trading yield tokens, managing LP positions, placing limit orders, and querying market data

4 skills · 1 agent · 1 MCP server

pendle-finance/pendle-ai 32

autopilot

claude

AI 自动驾驶工程套件:从目标描述到代码合并的全流程闭环。AI 自适应 fast/standard 档位;design 阶段 brainstorm 交互式需求探索 + plan-reviewer 计划审查;implement 阶段红蓝对抗分层验收;QA 谓词闸门 + 端到端执行面验证把守 merge 门;知识工程自动沉淀跨任务经验。含需求管理(项目任务 DAG)、智能提交、工程健康度诊断(doctor)、worktree 自动初始化。版本演进史见插件 README 与 git log。

5 skills · hooks

strzhao/autopilot 32

Run opencode inside claude code

4 skills · 1 command · 1 agent

apoapps/swarm-code-plugin 32

sciwrite

claude

Six skills for scientific writing: edit research prose, structure an IMRaD manuscript, run the writing process, handle peer review and publication ethics, draft grants and letters, and write for general audiences.

6 skills

dvdsosa/scientific-writing-skills 32

Discipline de développement TricorderKit : cadrage (interview-me), protocole spec→plan→sous-agents→tests→ship (dev-protocol), revue adverse (doubt-driven-development), débogage par cause racine, correction/durcissement web OWASP (code-corrector), observabilité des automatisations.

6 skills

GeekFamilyCorp/TricorderKit 32

بلقن الفيديو: 6 سكلات — ريل من فيديو كلام، ريل مراجعة منتج بتعليق صوتي، موشن 3D، بودكاست (مع صفحة مراجعة)، مونتاج على الإيقاع، أغلفة وثمبنيل. يشتغل بأي بيئة (لابتوب/جوال/سحابة).

6 skills

majedphotos/majed-plugins 32

Multi-agent deliberation for Claude Code - council, debate, and consensus workflows

1 skill · 4 commands

BayramAnnakov/agent-tower-plugin 32

Boros — Pendle's interest-rate-derivatives platform on Arbitrum. 44 semantic tools for trading funding-rate swaps, managing cross/isolated margin, and providing AMM liquidity.

3 skills · 1 agent · 1 MCP server

pendle-finance/pendle-ai 32

文章内容分析与结构化摘要生成工具

1 skill · 1 command · 3 MCP servers

strzhao/autopilot 32

写作技能包。包含博客向、技术文档向、专业技术博客向、阮一峰风格四种写作风格,以及专业技术文章评价工具

5 skills

strzhao/autopilot 32

cotask

claude

Cotask — task management with TASKS.md kanban dashboard

4 skills · hooks

wbopan/cotask 32

Five authorized Telegram workflows

5 skills

KiaroSama/Telegram-mcp 32

dr-ralph

claude

Implementation of the Dr. Ralph technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.

3 commands · hooks

blencorp/dr-ralph 32

warden

claude

Auto-approves safe commands, blocks dangerous ones, prompts for the rest

1 skill · 2 commands · hooks

banyudu/claude-warden 32

Données et graphe TricorderKit : accès normé à Neo4j (MCP officiel, lecture seule par défaut), recherche hybride Qdrant+Neo4j (graphrag-hybrid), scraping adaptatif (Scrapling), veille de changements (changedetection.io + RSSHub).

4 skills

GeekFamilyCorp/TricorderKit 32

Skills for Django development: fix type errors, upgrade JavaScript and Python dependencies

3 skills

saaspegasus/django-skills 32

graqle

claudecodex

Graph-powered codebase reasoning, impact analysis, and governed edits via the GraQle MCP server, plus governed-workflow skills and an optional governance gate hook.

2 skills · hooks

quantamixsol/graqle 32

castra

claude

Evidence-backed execution, session continuity, and context controls for Claude Code.

2 skills · hooks

beyondworks/castra 32

rive-mcp

claude

Create, edit, lint, render and preview Rive (.riv) animations without the Rive editor — 35 MCP tools plus the design workflow that makes generated motion look professional

1 skill · 1 agent · 1 MCP server

ODU33104/rive-mcp 32

drex

claude

Integrate Drex with coding agents. Select make_default at installation to prefer Drex over other decision models.

2 skills · hooks

nace-ai/drex-agent-skills 32

tokdiet

claude

Token/cost meter + context-compaction proxy companion. Ships a lightweight metering hook (logs tool I/O sizes to ~/.tokdiet); the full token-saving proxy runs via `npx tokdiet start` + ANTHROPIC_BASE_URL.

1 command · hooks

agiwhitelist/tokdiet 32

evals

claude

Create fine-tuned LLM-as-a-judge evaluators on the Plurai platform

1 skill · 1 MCP server

plurai-ai/plurai-plugins 32

Design skill for Claude Code. Iterative design document production with research, divergent thinking, and fresh evaluator agents.

2 skills

arkbriar/sisyphus-design 32