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.

threnody

9458

timjensgrossinger/threnody

Plugin Claude Code

Bundles 10 skills, 3 agents · 650 tokens together

Local-first MCP meta-harness: routes, plans, and swarms multi-agent coding work — emitting tier-aware Dynamic Workflows on Claude Code — while the host shell executes via Agent/Task subagents.

not rated 2 21d ago A tokens not measured original Apache-2.0

ljucask/pureinn-product-development

Plugin Claude Code

Bundles 51 skills, 1 command · 4,013 tokens together

AI-native product development framework. 51 active skills covering the full product lifecycle. FDD+SDD hybrid: 4 living registers, JIT design per feature, atomic commit protocol. Three playbooks: Greenfield, Feature Implementation, Rebuild. From zero to launch.

not rated 2 changed 3d ago A tokens not measured original MIT

claudeshot

9460

MarcoGarofalo94/claudeshot

Plugin Claude Code

Bundles 1 skill · 52 tokens together

Cross-platform screenshot tool for Claude Code. Capture your screen and drop it straight into your prompt — no copy-paste required.

not rated 2 5mo ago A tokens not measured original MIT

check-my-skills

9461

tonyfadel23/skill-inspector

Plugin Claude Code

Bundles 3 skills · 256 tokens together

Parse, visualize, and audit SKILL.md files as interactive DAGs with quality scoring and structural diagnostics.

not rated 2 5mo ago A tokens not measured original MIT

sysadmin-skills

9464

bouob/sysadmin-skills

Plugin Claude Code

Bundles 9 skills · 1,173 tokens together

ITIL 4-based IT operations skills for system administrators — incident response, change management with CAB review, and status communication.

not rated 2 4mo ago A tokens not measured original MIT

garage

9465

alifanov/ai-garage-launch

Plugin Claude Code

Bundles 4 skills, 12 commands, 2 agents · 703 tokens together

A workflow plugin for launching a product with the AI Garage method, from an initial idea through payments. Each team reads project documents, completes one step, records the result, and suggests the next command.

not rated 2 1mo ago A tokens not measured original MIT

research-poster

9466

adamjali/research-poster-skill

Plugin Claude Code

Bundles 1 skill · 166 tokens together

Turn a PDF abstract into a polished, fully-editable scientific conference poster (.pptx + PDF + preview) with native editable PowerPoint charts, verified citations, big readable typography, and a render-and-QA loop.

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

palas-basic

9468

Jacopalas/agentic-ai-palas

Plugin Claude Code

Bundles 2 skills · 104 tokens together

AI skills for your business and projects: basic common tools that can be re-used in business or anything. Includes markdown linting and notebook watermark removal.

not rated 2 6mo ago A tokens not measured original MIT

spring-fleet

9470

talayash/spring-fleet

Plugin Claude Code

Bundles 4 skills, 6 commands, 3 agents, 1 MCP server · 555 tokens together

OpenTelemetry-native, MCP-first debugging layer for multi-repo Spring Boot microservice fleets. Cross-repo call-chain tracing, traceid-correlated log timelines with code-grounded root-cause hypothesis, and a stdlib MCP server exposing fleet operations as typed tools.

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

sutra

9472

avmnu-sng/sutra

Plugin Claude Code

Bundles 19 skills, 4 agents, 2 hooks · 1,168 tokens together

A senior-engineer operating system for Claude Code -- architecture review, verification discipline, multi-session build orchestration, doc sanitization, and commit craft, delivered as skills, subagents, and layered lite/standard/strict profiles.

not rated 2 1mo ago A tokens not measured original MIT

dev-agent

9474

Surjal/dev-agent

Plugin Claude Code

Bundles 4 commands, 16 agents, 1 hook · 932 tokens together

Deep autonomous AI developer agent: idea -> architecture spec -> UX design -> implement -> test -> optional browser-based visual QA -> security/performance/final review -> Definition of Done, with automatic retry loops and persistent resumable execution state. Framework-agnostic -- inspects the target project to…

not rated 2 1mo ago A tokens not measured original MIT

studiomeyer-academy

9475

studiomeyer-io/studiomeyer-marketplace

Plugin Claude Code

Bundles 5 commands, 1 MCP server · 69 tokens together

Memory-First AI Operator School. 12 tools open to everyone, 21 once you add an Academy API key at install time. Lessons, quizzes, recipes, knowledge graph, certificates, AI tutor. Open source MCP server (npm mcp-academy, MIT). Free.

not rated 2 changed 13d ago A tokens not measured original MIT

fable-flow

9476

jjilli/fable-flow

Plugin Claude Code

Bundles 4 skills, 6 commands, 4 agents · 860 tokens together

Multi-agent shipping pipeline tuned for Claude Fable 5: parallel Sonnet 5 scouts, an xhigh-effort Fable 5 architect, Fable 5 implementers in isolated git worktrees, merge, an Opus 4.8 adversarial review loop, a post-implementation bug-iteration flow, per-repo pipeline memory, a card-based direction-brainstorm before…

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

companion-pet

9479

OvOhao/companion-pet

Plugin Claude Code

Bundles 1 skill, 5 hooks · 144 tokens together

A desktop companion that greets you on startup and pings you (work done / errors / waiting) with a cute mascot. Bring your own character images.

not rated 2 2mo ago A tokens not measured

heading-core

9480

mishahanin/heading-os-marketplace

Plugin Claude Code

Bundles 3 skills, 2 commands · 276 tokens together

Sovereignty and session core: the prime/state-check/checkpoint skills, the standalone sovereignty guard hooks, and the session checkpoint system - a context-usage sensor, a threshold offer, a pre-compaction brief that states what the summary must keep verbatim, a redacted post-compact save, and a resume injector, all…

not rated 2 11d ago A tokens not measured original Apache-2.0

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: