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.

cache-tax

claude

cache-tax, the Mod. Stops a cold send once with its price, keeps the 1-hour prompt cache warm for a window you set (/keepwarm 6h), arms that for you after a paid cold write, and keeps score. Reach L2, one $.model.fork per idle stretch, its own store, a status slot; sees prompt length only.

karanb192/claude-code-mods 47

43 finance skills for AI agents — accounting operations, financial analysis, tax, audit and SOX, risk, treasury, and corporate finance.

GAJETOso/financeskills 47

408 Claude skills for TV producers, journalists, podcasters, YouTubers and media professionals

200 skills · 10 agents

ur-grue/autopunk-media-skills 46

pstack

claudecodex

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.

61 skills · 2 agents

minghinmatthewlam/agent-guards 46

iris-dev

claude

Execute ObjectScript, query globals and SQL, inspect productions, run unit tests and read class source on a live IRIS instance. Needs the iris-agentic-dev binary on PATH.

40 skills · 1 MCP server · hooks

intersystems-community/iris-agentic-dev 46

protean

claude

Teaching skills for the Protean DDD framework, matched to the installed framework version.

39 skills

proteanhq/protean 46

swarmesh

claudecodex

Multi-CLI swarm in tmux with discuss / vote (v0.6: LLM-first, multi-round, files injection, auto-promote) / execute modes.

13 skills · 13 commands

Soein/swarmesh 46

harness

claude

Specification-first AI harness with 11 gates, 12 commands, 11 agents, and 3-tier architecture enforcement

2 skills · 13 commands · 11 agents

studioKjm/ai-harness-template 46

aurakit

claude

All-in-one Claude Code skill: build, fix, review, deploy with one /aura command. 46 modes, 23 agents, 6-layer security (OWASP+), 10 hooks, 8 languages, ~55% token savings.

3 skills · 23 agents

smorky850612/Aurakit 46

DataHub development and interaction toolkit with connector planning, PR review, catalog search, metadata enrichment, lineage tracing, data quality management, and connection setup skills

13 skills · 8 commands · 4 agents

datahub-project/datahub-skills 46

19 Claude Code skills + a pre-configured Obsidian vault that run a complete content engine. LinkedIn / X / YouTube (script, description, thumbnail, publish) / long-form / newsletters / lead magnets / graphics / motion video / short-form video editing (cut, audio, captions, motion graphics, QA gate). Personalize once, draft forever. Content tracked in a native Obsidian Base, searchable with qmd. Built by Oxygen, free under MIT.

20 skills

timscheuerai/content-vault 46

tares

claude

Open-source platform for always-on AI agents: a software factory for Claude Code that takes your projects from tickets to merged pull requests, or an AI SRE that watches your systems. The plugin connects Claude Code to Tares over MCP, streams sessions in, specs projects with /tares:spec, and runs the tares-factory crew and challenger sessions.

9 skills · 5 commands · 1 MCP server · hooks

glassflow/tares 46

Generate and validate PHPUnit tests for Shopware 6. Unit tests: analyzes source classes to detect category (DTO, Service, Flow/Event, DAL, Exception) and applies category-specific templates. Migration tests: analyzes SQL operations to generate pattern-appropriate migration tests with 8 migration-specific rules. Integration tests: generates wired-up tests via phpunit-integration-test-generation for controller, message-handler, indexer, DAL-flow, and multi-service patterns (defers to unit generation when the SUT is unit-shape); 8 quality rules plus a placement smoke check via phpunit-integration-test-reviewing; a separate user-invoked phpunit-integration-to-unit-migrating skill audits placement with 8 deep-reasoning rules and migrates load-bearing-free tests to the unit suite. Workflow-based team review: wave-orchestrated agents coordinated through a shared blackboard (no agent-to-agent messaging), with adversarial red team and defense rounds. Bundles test-rules MCP server for Shopware compliance rules. Orchestrator runs inline fix loop (max 4 iterations) with oscillation detection. Optional dev-tooling plugin enables PHPStan/PHPUnit/ECS validation in the fix loop.

11 skills · 3 agents · 1 MCP server

shopwareLabs/ai-coding-tools 46

Launch a team of AI agents to implement features with code review gates

3 skills · 11 agents

izmailovilya/ilia-izmailov-plugins 46

gemini

claude

Use Gemini CLI from Claude Code for code reviews and task delegation.

3 skills · 8 commands · 1 agent · hooks

bonboncinnabon/gemini-plugin-cc 46

Multi-agent /workflow development pipeline (planner → plan-review → coder → code-review).

9 skills · 3 MCP servers

hex0xdeadbeef/claude-kit 46

Content generation and publishing skills

12 skills

xuanxuan1983/baoyu-xuanyi-skills 46

AI-powered generation backends

12 skills

xuanxuan1983/baoyu-xuanyi-skills 46

Utility tools for content processing

12 skills

xuanxuan1983/baoyu-xuanyi-skills 46

randroid

claude

Focused Randroid skills for bounded development loops, PR feedback, VibeReview evidence, visual cleanup, and gameplay interaction and feedback. Legacy slash-command aliases remain available.

6 skills · 4 commands · hooks

Randroids-Dojo/skills 46

Interactive feature audit for vibe-coded projects - finds dead code through conversation

1 skill · 7 agents

izmailovilya/ilia-izmailov-plugins 46

tap-python-sdk

claudecodex

Skills for building Python apps with Tap Strap, TapXR, and TapBand: connect, taps, air gestures, vision models, IMU motion, raw sensors, and knob / D-Pad gesture recipes.

8 skills

TapWithUs/tap-python-sdk 46

legal-research

claudecodex

Cite-check drafts against real sources, find verified authorities, proofread, build Zotero libraries, write research memos, and prep Supreme Court cases.

7 skills · hooks

danepps/legal-research-skills 46

lastlight

claude

Install, configure and operate Last Light (server, client, overlay) and Last Light Evals — driven through the lastlight / lastlight-evals CLIs.

7 skills

nearform/lastlight 46

Reports and memos bury the answer under background, so readers must reconstruct the argument and decisions stall. This plugin applies Barbara Minto's Pyramid Principle (answer first, MECE-grouped support) and keeps a separate source-integrity layer that requires a specific source, locator, and confidence for every fact. Your reader gets the decision in the first sentence and can trust every number under it.

6 skills · 1 command

tyroneross/pyramid-principle 46

Launch a team of AI agents for deep parallel codebase research — causal understanding, not just coverage

1 skill · 5 agents

izmailovilya/ilia-izmailov-plugins 46

Autonomous coding using the Ralph Wiggum technique - simple loops, persistent memory, one task at a time

2 skills · 4 commands

mj-meyer/choo-choo-ralph 46

Turn any video into a Chinese-narration recap (understanding -> narration -> cut -> voiceover -> assemble) on ffmpeg + one Xiaomi MiMo API key. A bundle of independent skills + a thin orchestrator. macOS / Linux / Windows.

6 skills

ops120/video-recap-skills-plus 46

Integrated Rust development skills for multiple domains (UI, Robotics, etc.)

6 skills

ZhangHanDong/cowork-skills 46

Sipcode

claudecodex

Token-economy observatory for Claude Code: forensic per-session audit, A/B savings verifier, reproducible benchmark, and cost prediction — directly in Claude chat. Auto-installs via npx on first use.

4 skills · 1 MCP server

Anuj7411/sipcode 46