claude-code-plugin plugins

2,642 tagged claude-code-plugin, measured the same way as everything else here.

Browse within: claude-code-skills 170claude-code-skill 148claude-code-marketplace 113claude-plugin 86claude-code-plugins 84claude-ai 81ai-coding 76code-quality 56codex-plugin 47claude-code-hooks 45hooks 41claude-skill 38Multi-Agent 36agent-orchestration 30

Agentic-Assets/corbis-literature-starter-kit

Plugin Claude Code

Bundles 6 skills, 6 commands, 1 agent, 1 hook, 1 MCP server · 726 tokens together

Literature review and idea-screening starter kit for Claude Code, powered by the Corbis MCP. Bundles the repo's six research skills — literature review, positioning, landscape figures, idea generation, idea screening, and citation verification — alongside six slash commands and a paper-reader subagent.

not rated 11 4mo ago A tokens not measured original MIT

development-skills

435

reidemeister94/development-skills

Plugin Claude Code

Bundles 16 skills, 1 agent, 2 hooks · 529 tokens together

Use when any coding, development, analysis, debugging, or code-related task is detected. Triggers on: writing code, fixing bugs, adding features, refactoring, architecture decisions, requirements analysis, code review, diff analysis, error investigation, debugging failures, and evaluating approaches. A disciplined…

not rated 11 1mo ago A tokens not measured original MIT

micro-skill-pipeline

437

stevesolun/micro-skills

Plugin Claude Code

Bundles 1 skill, 7 commands, 1 agent, 2 hooks · 250 tokens together

Gated micro-skill pipeline system. Converts monolithic skills into small, sequenced steps with YES/NO gates and a compounding failure log. Use /skill-convert to convert, /skill-use to activate a pipeline, /skill-check to run gates, /skill-list to see conversions, /skill-new to scaffold, /skill-fail to log patterns…

not rated 11 5mo ago A tokens not measured original MIT

vstack

438

Cavalry-Collective/visual-stack

Plugin Claude Code

Bundles 8 skills, 1 hook · 719 tokens together

Stop prompting. Start pointing. Visual Stack adds a Figma-like feedback layer to Claude Code. Create a new screen from a prompt, screenshot, reference site, or design system, or open an app you already have running. Click any element and leave feedback exactly where the problem is hiding, and Claude publishes the next.

not rated 11 yesterday A tokens not measured original MIT

fullstack-dev-kit

440

theam/claude-dev-kit

Plugin Claude Code

Bundles 10 skills, 2 commands, 6 agents, 3 hooks, 3 MCP servers · 945 tokens together

Issue-to-PR workflow kit for any tech stack. Fetch a user story from your tracker (Jira, Linear, GitHub Issues, Azure DevOps) and any linked Figma designs, implement with plan approval, enforce >95% coverage and a security pass, generate e2e tests, open the PR, fix review findings, and move the ticket to review.

not rated 11 changed today A tokens not measured original Apache-2.0

tokendiet

443

Fortytude/TokenDiet

Plugin Claude Code

Bundles 1 skill, 1 command · 138 tokens together

Audit your codebase for wasteful, expensive LLM API usage and get a concrete plan to cut the cost — cache, batching, model routing, retry caps, prompt bloat. Runs on your own agent, in your own repo. Free & open source. TokenDiet by Fortytude.

not rated 11 1mo ago A tokens not measured original MIT

qq

444

tykisgod/quick-question

Plugin Claude Code

Bundles 27 skills, 4 hooks · 821 tokens together

The control plane for game-dev agents — close the loop with verified compile, test, and cross-model review across Unity, Godot, Unreal, and S&box. Lifecycle-aware /qq:go routing, structured runtime state in .qq/, 26 /qq: slash commands. Claude Code-first, agent-agnostic via HTTP and MCP.

not rated 11 9d ago A tokens not measured original MIT

design-with-claude

445

imsaif/design-with-claude

Plugin Claude Code

Bundles 1 skill, 48 commands · 1,863 tokens together

A product designer inside your terminal: 48 specialized design skills as slash commands, covering accessibility, motion, color, checkout, dashboards, and more.

not rated 11 13d ago A tokens not measured original MIT

whisperx-transcribe

447

abubakarsiddik31/whisperx-transcribe

Plugin Claude Code

Bundles 1 skill · 194 tokens together

Transcribe audio/video into a clean, speaker-labeled Markdown transcript using WhisperX, so an LLM can read a long meeting or recording without processing raw audio.

not rated 11 1mo ago A tokens not measured original MIT

wire-memory

448

usewire/wire-memory

Plugin Claude Code

Bundles 6 skills, 4 hooks · 145 tokens together

Persistent memory for AI agents. Connect to a Wire container to remember decisions, patterns, and context across sessions.

not rated 11 +1 3mo ago A tokens not measured original MIT

docflow

449

EvolveHQ/docflow

Plugin Claude Code

Bundles 9 skills · 1,075 tokens together

ADR-driven documentation workflow: a bootstrap skill that scaffolds an Architecture Decision Record (ADR) catalogue, a plan/ queue, AGENTS.md conventions, and agent/ coordination — plus lifecycle skills to author ADRs, queue and ship work, add conventions, audit consistency, brainstorm decisions, run agent waves, and.

not rated 11 +1 29d ago A tokens not measured original MIT

polygraph

450

cognitive-fab/polygraph

Plugin Claude Code

Bundles 6 skills, 5 commands, 4 agents, 1 plugin · 1,805 tokens together

A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…

not rated 11 7d ago A tokens not measured original Apache-2.0

review

453

harnessprotocol/harness-kit

Plugin Claude Code

Bundles 1 skill, 1 agent · 137 tokens together

Code review for a branch, PR, or path — structured output with severity labels and cross-file analysis.

not rated 10 today A tokens not measured original Apache-2.0

humanizer-kr

454

hjongc/humanizer-kr

Plugin Claude Code

Bundles 1 skill · 85 tokens together

Korean-specialized writing skill for rewriting AI-sounding Korean into natural, source-grounded Korean.

not rated 13 2mo 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: