2,669 tagged claude-code-plugin, measured the same way as everything else here.
Browse within: claude-code-skills 169claude-code-skill 163claude-code-marketplace 134claude-code-plugins 119claude-plugin 94ai-tools 90ai-coding 81claude-ai 81cli 72agentic-ai 71claude-code-hooks 64codex-plugin 56code-quality 54claude-code-commands 51
Plugin Claude Code
Bundles 1 skill, 2 commands, 2 hooks · 125 tokens together
Gates code changes behind an interactive quiz: Claude investigates, tests your understanding of root cause and fix, and only implements once you pass.
Plugin Claude Code
Bundles 10 skills · 658 tokens together
Agentic software-delivery loop: turn specs into a dependency-ordered GitHub Issues backlog, then let agents claim, implement, adversarially review, patch, and merge tasks in isolated git worktrees behind a single correctness gate.
byjunyoung/claude-product-skills
Plugin Claude Code
Bundles 6 skills · 952 tokens together
A bundle for product docs and the tasks that come out of them. Write a spec against a format and verify it before it ships; turn a request thread into a task's context table; file that task in your engineering tracker and keep the two sides reconciled. Where things are stored is decided by config.
zircote-plugins/documentation-review
Plugin Claude Code
Bundles 4 skills, 6 commands, 2 agents · 875 tokens together
Comprehensive documentation management: review, create, update, and maintain high-quality documentation with Diataxis framework support.
Plugin Claude Code
Bundles 3 skills, 6 hooks · 216 tokens together
Session-state handoff for Claude Code: hooks auto-snapshot at SessionEnd/PreCompact and auto-load at SessionStart. Rebuilds lost handoffs from per-turn backups, keeps rotating history, nudges at 40% context, and HMAC-signs handoffs so cloned repos can't inject trusted rules.
AshtonYoon/claude-config-dashboard
Plugin Claude Code
Bundles 2 commands · 118 tokens together
Local web dashboard and CLI for /.claude config visualization — measured per-session token cost, install-vs-used gaps, and a review-first cleanup script for plugins, agents, skills, hooks, and MCP servers.
Plugin Claude Code
Bundles 1 skill · 58 tokens together
Profile your Claude Code transcripts: context budget report, skill-promotion candidates, and a skill regression test harness. Local-only, stdlib-only.
Plugin Claude Code
Bundles 9 commands, 1 hook · 305 tokens together
A read-only plugin that maps the locations, progress stages, and dependencies of seven related projects. A dependency is a link showing that work in one project affects or precedes work in another.
Plugin Claude Code
Bundles 3 skills, 7 commands, 2 hooks · 286 tokens together
A safety add-on for people who are new to coding agents, with guidance in simple Korean. It can guard risky work with confirmation, backups, and undo support.
Plugin Claude Code
Bundles 6 skills, 7 commands, 1 hook · 694 tokens together
A Korean-language Claude Code plugin for defensive and educational reverse engineering, which means examining how software works.
Plugin Claude Code
Bundles 4 skills, 5 commands, 1 agent, 1 hook · 1,058 tokens together
A plugin for beginner “vibe coders”—people who build software by directing an AI with natural-language prompts. It provides a plan-first workflow, simple review, and safety defaults for Claude Code and Codex.
Plugin Claude Code
Bundles 11 skills, 11 commands · 728 tokens together
A Claude Code plugin containing ten Korean-language writing skills for beginners. It supports both slash commands and ordinary natural-language requests for tasks such as summaries, messages, study plans, introductions, captions, translations, and speeches.
Plugin Claude Code
Bundles 1 skill, 2 commands · 88 tokens together
Essential commands, skills, and workflows for everyday development.
Plugin Claude Code
Bundles 5 skills · 317 tokens together
Ultra-compressed Ukrainian mode for Claude Code. −65-90% tokens, 0% accuracy loss. Auto-detect language, custom abbreviations, token counter, context-aware compression.
Plugin Claude Code
Bundles 1 skill, 2 hooks, 1 MCP server · 82 tokens together
Standalone visualization MCP for Cortex — a live neural-graph galaxy of every project, file, symbol, memory, discussion and wiki page, plus a per-session execution trace. Read-only bridge over Cortex's shared PostgreSQL and the /.claude artifacts.
cdeust/ai-architect-mcp-codebase
Plugin Claude Code
Bundles 3 skills, 24 commands, 18 agents, 6 hooks, 2 MCP servers · 597 tokens together
Rust MCP server that indexes ANY codebase into a LadybugDB property graph — source in 11 languages with full AST, plus docs/config/binaries as File nodes (.js→Imports, Markdown→References). Resolves imports and call chains, detects communities via Leiden, traces execution flows from entry points, and exposes 26 MCP…
Plugin Claude Code
Bundles 1 skill · 138 tokens together
Multi-agent codebase audit skill for Claude Code — spawns parallel subagents (security, performance, tests, architecture, dead-code) and synthesizes their findings into a prioritized action plan.
Plugin Claude Code
Bundles 6 skills, 6 commands · 493 tokens together
Automate your project's documentation lifecycle — ADR, CHANGELOG, releases, devlog, index, and CLAUDE.md — as 6 skills with zero-dependency helpers.
Plugin Claude Code
Bundles 7 commands, 1 hook · 123 tokens together
Umbrella plugin: dispatch /ai:review|rescue|gater across configured providers, plus /ai:compare for fan-out.
Plugin Claude Code
Bundles 3 skills, 5 commands · 635 tokens together
Turnkey docs review: set up notabene on any repo — write the config, create the .notabene store, and start the review server via npx (no toolchain to install) — then run the human↔agent loop: process browser comments on your docs, apply the feedback, mark resolved, write the journal, and verify.
Plugin Claude Code
Bundles 8 skills, 2 agents, 5 hooks · 406 tokens together
Makes a repository know itself and preserve the engineering context built while you work with it, so an agent stops rediscovering both. An architecture index and an impact map instead of scanning files; work state, session records and the decisions behind them instead of losing context between sessions; the procedures.
Plugin Claude Code
Bundles 5 skills · 183 tokens together
plumb-line provenance: epistemic honesty enforced by tooling. Five skills give any repository a clear source-truth layer, visible uncertainty, quarantined fakery, reproducible outputs, and rules enforced by machines rather than goodwill. New here? Run plumb-line-adopt first — it looks at your repo and tells you which…
Plugin Claude Code
Bundles 17 skills · 2,250 tokens together
Skills for code you'll have to live with. Two collections: craft (code that's understandable, named well, lean, loud about failure, and testable — without turning every edit into a rewrite) and rigor (claims you can believe — adversarial testing, full-suite banking, cited numbers, population sweeps, evidence-backed…
Plugin Claude Code
Bundles 2 skills · 222 tokens together
Write prose that reads as though a person wrote it, then prove it mechanically. A rewrite pass, a reporting gate, and a composition read.