301 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 301 plugins that match these filters.
dotbrainarminzou/dotbrain1
hungry-crabdrevendev/HungryCrab1
one-skill-to-rule-them-allrebelytics/one-skill-to-rule-them-all1
tencent-cloudbaseTencentCloudBase/CloudBase-AI-Toolkit1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceFive-stage, repo-agnostic feature pipeline: grill the decisions, author RFC/PRD, discover per repo, build against named proofs, then one adversarial audit gate. Plus /ef:ready: a deterministic gate that keeps the agent rulebook small and true.
developmentPrivate project context, shared across coding agents and worktrees.
productivityEat a foreign repository, digest it, and extract everything useful for your own repo without violating licenses.
productivityTurn-end guard for task-observer (experimental): notes a turn that used tools and wrote nothing to the observation log or checkpoints.log, and reminds the next turn to flush.
Create, preview, save, deploy, inspect, and roll back Vite web apps hosted on Tencent CloudBase.
MCP tool-catalog compression for Claude Code. Compresses the tool discovery payload from 71,929 to 581 tokens (-99.2%). Auto-installs the zero-dependency mcptoon CLI (/mcptoon-setup), wires the serve bridge, and teaches the agent when to compress. MCP 2026-07-28 stateless-first bridge included.
mcpBundle-plugin engineering toolkit: scaffolding, platform adaptation, version management, and skill lifecycle
Permission-first engineering kit: shared rules, 10 specialist agents, 28 skills, and 10 workflow commands.
Spec-driven development: you decide the Gherkin spec and the C4 design, Claude builds test-first until the spec passes.
Capture and investigate Claude Code agent sessions with local AgentTrace hooks.
Agent Alchemy TDD Tools — Test Driven Development tools for AI agents
Agent Alchemy Plugin Tools — plugin lifecycle tools for AI agents
Git worktrees, branch cleanup, hooks, secret scanning, config hygiene, and guardrails
Eight lean but firm skills, including spec-sync for durable intent and context-hygiene against stale documentation. They trigger only when their conditions match and stay strict once active. Includes a SessionStart discipline primer, passive local usage counting, and first-entry guide-doc seeding for CLAUDE.md / AGENTS.md.
Get screenshots, GIFs, recordings, and files into GitHub PRs and issues via uploads.sh. Bundles the github-screenshots, annotate-screenshots, and uploads-cli skills, the hosted MCP server, and a mod that shows staged screenshots above the prompt and attaches them when gh pr create runs.
Shared debug memory and verified dynamic Skills for Claude Code agents.
Finds vetted agent skills for your task, mid-flow, from a federated catalog — with license/provenance trust metadata. Privacy-preserving: the search backend stays remote and only an abstract wish-list crosses the boundary.
An auditable, on-disk PDLC state machine for AI software engineering: a staged workflow (PRD → design → TDD → implement → review → ship → retro) with hard contracts + objective checks from real exit codes, so an autonomous loop can drive it to convergence unattended (fail-stop / budget guards) — tool-agnostic, richest in Claude Code, plus Codex via adapters.
workflowMarketing OS for developerneurs + solopreneurs — engineers shipping products with zero marketing experience. Spec-driven campaigns with positioning-invariant quality gates.
Codex computer use in Claude Code. Installs LCU from its latest release when it is missing, then registers it with `lcu setup --agent claude-code`.
