agents plugins

by vikash ruhil

Loomwright is a plan-first, multi-agent development system for Claude Code. Launch Pad turns a goal into a reviewed brief; Supervisor executes it autonomously across parallel git worktrees with self-heal; dedicated agents cover code review, red-teaming, QA, and standalone PR review-and-heal. 14 agent roles, 24 slash commands, 42 skills, 39 quality gate hooks. Full history in CHANGELOG.md.

by BugBug.io

BugBug workflows for AI agents workflows for AI agents

by DataRecce

Agnostic agent cartography and visualization — a live local dashboard mapping coding-agent sessions across Claude Code, Codex, Pi, Gemini, Antigravity, Copilot, OpenCode, Cursor, Goose, and Droid

by Allyson Bruno Campos Barros Vilela

Fábrica de software autônoma como plugin Codex CLI: 71 agentes em 21 times — 40 core (liderança, produto, arquitetura, frontend, mobile, backend, dados, ciência de dados, qualidade, plataforma, documentação) coordenados por Laura, e 31 de apoio em 10 squads (microcopy, narrativa, naming, valor, observabilidade, DX, revisão arquitetural, requisitos, gestão de entregas, governança). 18 skills: onboardar, especificar, mapear-arquitetura, mapear-conhecimento, diagnosticar, analisar-ameacas, desenhar, validar, rodar, mobilizar, entregar, revisar, avaliar, lancar, otimizar, migrar, auditar, evoluir. Grafo de conhecimento com proveniência como memória compartilhada da fábrica (Graph Engineering). Versão MIT/genérica — para domínios regulados use kairos-ai.

by Allyson Bruno Campos Barros Vilela

Fábrica de software autônoma como plugin Codex CLI: 71 agentes em 21 times — 40 core (liderança, produto, arquitetura, frontend, mobile, backend, dados, ciência de dados, qualidade, plataforma, documentação) coordenados por Laura, e 31 de apoio em 10 squads (microcopy, narrativa, naming, valor, observabilidade, DX, revisão arquitetural, requisitos, gestão de entregas, governança). 18 skills: onboardar, especificar, mapear-arquitetura, mapear-conhecimento, diagnosticar, analisar-ameacas, desenhar, validar, rodar, mobilizar, entregar, revisar, avaliar, lancar, otimizar, migrar, auditar, evoluir. Grafo de conhecimento com proveniência como memória compartilhada da fábrica (Graph Engineering). Versão MIT/genérica — para domínios regulados use kairos-ai.

by OmniNode

Unified ONEX architecture plugin with intelligent agent routing, manifest injection, quality enforcement, 53 polymorphic YAML agents, and 100+ reusable skills (invoked as /onex:<skill-name>) for comprehensive workflow automation and observability

by karlorz

Project-aware Karpathy-style knowledge base for agentic coding tools: 21 prompt-only skills (wiki-*, proj-*, using-skillwiki, skillwiki-mcp) backed by the deterministic skillwiki CLI.

by Martin Eserios

AI development system — skills, agents, and hooks for systematic software engineering with Claude Code

by YPY

Claude is the architect: it writes specs and verdicts and picks a reasoning effort per task. The relay model (follows your codex config) on an OpenAI-compatible relay does all the implementation — agentically through the Codex CLI by default, or as chat completions applied verbatim as the fallback — and a clean-context Claude advisor reviews every deliverable before it ships.

by wasikarn

A Claude Code harness that composes mattpocock-skills instead of duplicating it. Seven computational deny/ask gates (irrecoverable commands, subagent git guard, subagent spawn guard, task-complete separation, test integrity, config-write guard, codex-setup guard) plus a SubagentStop verdict-check gate, a 4 KB METHODOLOGY injected at SessionStart, and memory-lint for the auto-memory store.

by nuttaruj

Coordinated software-house team for AI coding CLIs — 15 specialist agents, Core 10 phase skills (1 router + 9 phase), 6-phase lifecycle. Pre-commit gates (S1-S5 simplicity / T1-T6 testing / F1-F5 failure-mode) catch bugs before ship. On Claude Code, ships as a pure marketplace plugin (agents / skills / commands / hooks) — the always-on judgment core is delivered by a SessionStart hook, so install and uninstall touch no global config. See https://github.com/nuttaruj/rolepod.

by nuttaruj

Coordinated software-house team for AI coding CLIs — 15 specialist agents, Core 10 phase skills (1 router + 9 phase), 6-phase lifecycle. Pre-commit gates (S1-S5 simplicity / T1-T6 testing / F1-F5 failure-mode) catch bugs before ship. On Claude Code, ships as a pure marketplace plugin (agents / skills / commands / hooks) — the always-on judgment core is delivered by a SessionStart hook, so install and uninstall touch no global config. See https://github.com/nuttaruj/rolepod.

by Allen Eubank

Reusable planning, handoff, verification, and workflow skills for agents.

by Daniel Luca

Orchestrator skills for PR review, design review, issue triage, simplification, batch merging, codebase mapping, and installing periodic maintenance agents.

by Aviv Sinai

Agent Message Queue - file-based inter-agent messaging with co-op mode, cross-project federation, and orchestrator integrations

by Christopher Boone

Review and reorganize AI coding agent configuration and instruction files across Claude Code, Codex, Copilot, and OpenCode.

by Christopher Boone

Review and reorganize AI coding agent configuration and instruction files across Claude Code, Codex, Copilot, and OpenCode.

by donald2028

A reusable skill collection for Claude Code, Codex, Cursor, Gemini CLI, Kimi Code, OpenCode, WorkBuddy, and compatible agents.

by Antonio Junior

Production-grade agent skills and custom agents for AI coding assistants.

by Eliott Jacopin

Creates, executes, and amends graph-based campaign roadmaps.

by antonygiomarxdev

Skill plus policy directory: role definitions and gate scripts that turn one AI session into a coordinator dispatching specialised workers through Orca

by snwlee

개인 개발 하네스: intake → spec → build(TDD) → review → finish 워크플로, 전문가 에이전트, Baton 컨텍스트 핸드오프

by Roman

Multi-repo agent orchestration with ownership enforcement, structured communication, and compliance-ready audit trails

by Francisco Perez-Sorrosal

Skills, commands, and agents for AI coding workflows — Claude Code authoring, Python development, project management, and domain-specific tools