Organization engineering context for Claude. Connects the hosted ctx| MCP so Claude can call ctxadvisor for standards, ADRs, architecture, and likely source areas before planning.
Your AI development team. 36 agents and 32 skills for building, reviewing, debugging, and shipping production code. Supports Vue, React, Next.js, SvelteKit, Angular, Astro, and Nuxt.
★not rated 21 14d agoA
tokens not measured
originalMIT
Autonomous AI research harness for Claude Code. Plan -> Research -> Build -> Audit -> Run -> Assess -> Codify, with adversarial subagent review, a taste corpus, a [LEARN] memory system over SQLite/FTS5, and a spot-first GPU procurement router.
★not rated 21 1mo agoA
tokens not measured
originalApache-2.0
Two-way voice phone calls plus tiered alerts for your AI agent, over free self-hosted SIP. The agent rings your phone and talks to you when it needs a decision, and it is presence-aware so it only calls when you are away from the keyboard. Runs the engine in Docker, so there is no local build.
★not rated 21 2mo agoA
tokens not measured
originalApache-2.0
A plugin builder for DMAP, a declarative system for describing workflows that use multiple AI agents. It is identified as version 1.4.0 and is published under the MIT license.
★not rated 21 4mo agoA
tokens not measured
originalMIT
Professional Agentic Product Engineering — two skills for operating a coding agent well. /pape:agentic-coach catches teachable moments while you work and surfaces the single most relevant tip from the guide. /pape:harness-audit reads the harness checked into your repo — guidelines, autotests, guardrails — and reports…
★not rated 21▲
+1
changed yesterdayA
tokens not measured
Michael Hanko's portable Claude Code kit: curated skills, slash commands, and subagents kept in one place so every machine (and the mph server) runs the same setup.
★not rated 21▲
+2 13d agoA
tokens not measured
originalMIT
Sync: Claude and Codex council orchestration. Routes work by role across declared pools, requires current headroom before any capacity claim, coordinates through run directories, gates on executed commands, and evolves policy from recorded outcomes.
Professional-grade multi-LLM agent coordination with comprehensive registry system, mandatory orchestration protocol, and production-ready DevOps workflows. Portable and customizable for any project.
★not rated 21 2d agoA
tokens not measured
originalMIT
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: