v9.2.6 · MIT
Tribunal Kit is the governance layer for AI coding agents that stops AI hallucinations and npm ghost packages before they hit disk. Works with Cursor, Windsurf, Claude Code, and Aider.
v0.8.0 · MIT
Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as markdown files you own.
v0.3.1 · MIT
An agentic development harness for Claude Code, Codex & Cursor: gated pipeline from spec to green checks.
v1.2.0 · MIT
50+ consulting frameworks used by McKinsey, BCG, Bain, and Accenture — packaged as a Claude Code plugin
v1.1.66 · no license
Official PostHog plugin for Claude Code, Cursor, Gemini, Codex and other AI coding tools
— · MIT
Claude Code plugin for people who describe what they want and let Claude build it: brand identity, product planning, plain-language build/ship/debug workflows, and a creator toolkit.
v0.3.2 · MIT
Claude Code plugin that transforms vague requirements into detailed implementation plans via research, interviews, and multi-LLM review.
v0.10.2 · MIT
Comprehensive multi-agent code review for Claude Code
— · MIT
Public adapters and discovery catalog for Triptych OS (Agent OS): agent frameworks, MCP/A2A/x402 protocols, workflows, wallets, SDKs, and examples for execute-first routing, governed handoffs, and receipt-aware agent commerce.
v3.7.5 · MIT
Compound V — a multi-model orchestrator for Claude Code, layered on Superpowers: a deterministic router (Opus for risky work, Sonnet for the mechanical), cross-model review (Claude + Codex), 3 scouts (code · docs · domain), semantic memory, and Epic/Marathon autonomous loop mode. The pill that turns one freelancer into a squad.
v1.4.0 · MIT
Hand off tasks to Devin — a plugin/skill for Claude Code, Codex, Cursor, and any coding agent
— · MIT
RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet), so it builds with the stack instead of drifting off it.
v0.8.0 · MIT
Claude Code plugin for EODHD financial data — 150k+ tickers, 70+ exchanges, OAuth MCP server with 80 tools, 7 workflow skills, financial-analyst agent, 5 slash commands. MIT.
— · MIT
Skills & plugins for agentic commerce : UCP, ACP, AP2, A2A, WebMCP, Magento 2, BigCommerce, WooCommerce
— · MIT
A multi-agent application-security review harness for Claude Code (and, later, other AI agents). One router skill dispatches to a full offensive-security pipeline that maps a codebase, hunts vulnerabilities with a per-class knowledge base, chains findings into escalations, verifies real impact, and reports to README/JSON/SARIF/doc/PDF.
v2.0.7 · Apache-2.0
Kimi for Claude Code and Codex: code questions, reviews, fixes, and parallel tasks through your local Kimi Code CLI. Available through GitHub marketplaces and npm.
v0.6.0 · MIT
Procedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, STE-100, developer docs) + character voices. Agent Plugins 1.0.0, works in opencode, Claude Code, Codex.
— · MIT
23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex desktop edition tuned for Astra. Source for clickai.dev.
— · MIT
Audit and fix your Mac's security in one command. No agent, no signup, open source.
v2.0.0 · MIT
Markdown and HTML renderer for Svelte 5 — built for rendering streaming AI agent output from Claude Code, ChatGPT, and agentic workflows. XSS-safe defaults, streaming-aware sanitization, token caching, TypeScript types, and Svelte 5 runes.
v2.0.3 · Apache-2.0
Local-first memory & context harness for coding agents
v0.1.16 · MIT
Spawn the Claude Code CLI with a chosen plugin directory, skill, and prompt
— · Apache-2.0
Outline-Driven Development for Claude Code - 46 agents, 25+ skills, diagram-first methodology, AST-based editing, atomic commits.
— · Apache-2.0
Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.