Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Software Factory Orchestrator

ASecurity

Run a 24/7 AI software factory on a VPS with Archon YAML workflows - GitHub issue in, validated merged PR out. Triage, implement, holdout validate, auto-merge or escalate. Hostinger KVM2 reference, provider MCP, model routing per node. Use quando operar factory autonoma, deploy remoto 24/7, ou pipeline issue-to-PR com Archon.

2 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentsgonodegit

Works with

claude codemcp

Security Analysis

A100/100

Scanned 9/24/2026

$npx -y skills add majinmagros/magros.ai-skills --skill software-factory-orchestrator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Software Factory Orchestrator?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Software Factory Orchestrator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-software-factory-orchestrator/badge)](https://www.skillsdirectory.com/skills/majinmagros-software-factory-orchestrator)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: software-factory-orchestrator
description: Run a 24/7 AI software factory on a VPS with Archon YAML workflows - GitHub issue in, validated merged PR out. Triage, implement, holdout validate, auto-merge or escalate. Hostinger KVM2 reference, provider MCP, model routing per node. Use quando operar factory autonoma, deploy remoto 24/7, ou pipeline issue-to-PR com Archon.
---

# Software Factory Orchestrator

Issue entra, PR validado e mergeado sai (padrao ColeMedin dark-factory + Archon https://github.com/coleam00/Archon, experimento publico em https://github.com/coleam00/dark-factory-experiment). Motor: workflows YAML do Archon (`.archon/workflows/`: triage, fix-github-issue, validate-pr); orquestrador cron; coding agent (Claude Code/Codex) executa os nos.

## Quando usar

Quando precisa operar (nao so construir) uma factory: VPS 24/7 aceitando GitHub issues, com triagem, implementacao, validacao independente e merge automatico ou escalacao humana. NAO use para one-shot de codigo - isso e `orch-build-mvp`; NAO use para VPS generico sem factory - isso e `vps-guided-install`.

## Passos

1. **Interview (fixe o escopo)** - provider VPS (default Hostinger; qualquer Ubuntu serve), repo novo (PRD) vs existente, coding agent (Claude Code/Codex, testados), app funcional vs so PRD. O agente de setup pergunta e escreve os arquivos de contexto da factory.
2. **Provisione a VPS** - referencia KVM2 (suficiente); SSH + firewall. Crie a instancia VOCE (o plugin nao tem esse poder - de proposito).
3. **Plugins + auth manual** - instale o plugin do provider no coding agent, autentique; GitHub via device-code; Codex com `device-auth` habilitado no dashboard ChatGPT. Credenciais NUNCA vao para o agente - esses 2 logins sao manuais.
4. **Instale a factory** - Archon + workflows (`.archon/workflows/`), repo-alvo clonado, coding agent live na VPS. Escreva `MISSION.md` + `FACTORY_RULES.md`: o que a factory aceita/rejeita e por que.
5. **Teste end-to-end** - crie UMA issue simples (ou PRD fatiado em issues), acompanhe: triage classifica e prioriza (`archon ready`?) -> implementa -> PR draft -> `validate-pr` holdout (checks + review paralela: comportamento, code review, erros, seguranca) -> merge automatico OU escalacao humana. DNS via plugin se o dominio estiver no provider.
6. **Opere 24/7** - orquestrador cron despacha (ex. a cada 30min, paralelo limitado); cada ciclo: triage em lote -> implementacao por issue -> validacao independente com contexto fresco (segunda passada nao pode ser o mesmo contexto da primeira) -> merge ou fix-and-retry.
7. **Roteie modelo por no** - reasoning em modelo forte, extracao barata em modelo leve (ex. sonnet/haiku); provider trocavel sem mudar o design. Factory cara e factory morta.

## Regras

- EARLY ALPHA: nao prometa 100% de confiabilidade para qualquer codigo - experimente e refine (e o que o proprio autor diz).
- Triage REJEITA o que foge da missao; validate-pr e HOLDOUT (contexto independente) - validador que viu o build nao valida.
- Merge automatico SO com gate verde completo; duvida = escala para humano.
- Issues sao a UNICA entrada; PR mergeado e a UNICA saida. Nada fora desse contrato.
- Token efficiency e feature, nao otimizacao tardia: meça por workflow desde o dia 1.

## Related skills

- `autonomous-agent-harness` - loop autonomo generico com memoria e schedules.
- `agentic-os` - agentes persistentes multi-sessao.
- `vps-guided-install` - VPS bare-metal sem factory em cima.
- `fusion-harness` - multi-modelo como architect + builders.
- `eval-harness` - rigor do gate de validacao.

Attribution

majinmagrosmajinmagros
View sourceSee grades on GitHubMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →