Pipeline de skills e subagentes que conduz qualquer projeto de software (fullstack, API, CLI, biblioteca, dados/IA) do brainstorming ao código executável: analista e desenvolvedor de ideias, escritor de plano, designer, devs backend/banco/frontend/IA, analista de infra e analista de segurança — todos seniores, com…
★not rated 2 2mo agoA
tokens not measured
AGPL-3.0
Dispatch tasks to cursor-agent from Claude Code. In-place by default; --isolated opts into a sandbox worktree. Background jobs, session boundary safety, structured policy refusals.
★not rated 2 4mo agoA
tokens not measured
originalMIT
General-purpose spec-driven development plugin. /dev:spec creates specs via AI interview + research. /dev:work executes specs using adaptive agent teams.
Model-tier router: on agent spawns, an LLM classifies the brief and injects a cost-appropriate Claude model (Haiku/Sonnet/Opus) via a PreToolUse hook (Anthropic API, or claude -p fallback). Also ships a model-router skill.
Guided Claude Code profile creation plus multi-account switching. Bundles the /cc-loadout:init skill; the cc-loadout CLI does the discovery and writing.
★not rated 2
changed 7d agoA
tokens not measured
originalMIT
Multi-agent development crew: 14 specialized agents, 93 skills (including caveman token-compression suite), studio templates, and companion plugins (LSP, Trail of Bits security, playground). Full-stack TypeScript, Python, and Swift with DDD patterns, CI/CD pipelines, design extraction, and cross-session memory.
★not rated 2 5mo agoA
tokens not measured
originalMIT
Comprehensive centralized repository of Claude Code configurations including agents, skills, commands, hooks, and MCP servers optimized for full-stack development.
Observe, debug, cost-manage, and evaluate AI systems from the Progress Observability Platform: an instrumenter that retrofits observability onto an existing Python, TypeScript, or .NET agent and verifies traces arrive, a scaffolder for new instrumented .NET agents, a setup health check, then trace triage, cost/usage…
★not rated 2 2d agoA
tokens not measured
originalMIT
Multi-model fusion for Claude Code + Codex: a parallel panel (1x Claude Fable 5 via claude -p locked at --effort max + 1x GPT-5.6 Sol via codex locked at ultra; /fusion-max adds a 2nd Fable 5 panelist) answers a task independently and blind, then GPT-5.6 Sol (codex, ultra) judges and a Claude Fable 5 synthesizer (via.
★not rated 2 2mo agoA
tokens not measured
originalMIT
An agent-driven software factory: GitHub issues carry pipeline state, OpenSpec change folders carry spec content, ten agent roles move work between them behind four approval gates, with releases gated on GitHub milestones.
★not rated 2 4d agoA
tokens not measured
originalMIT
MindrianOS -- Your AI innovation co-founder. Larry thinks with you through PWS methodology, builds your Data Room as you explore, and chains frameworks intelligently. Install and go.
Skills for COMP4020/COMP8020 Agentic Coding Studio students: setting up the course environment, tracking budget and deadlines, and getting each week's deliverable started, checked and shipped. Ships no hooks; the optional status line lives in the companion comp4020-statusline plugin.
★not rated 2 25d agoA
tokens not measured
originalApache-2.0
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: