Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/felvieira/claude-skills-fvnpx agentmods add commands/felvieira/claude-skills-fv/factoryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/felvieira/claude-skills-fv/factory)<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/factory"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/factory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/factory"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.01708 |
| Opus 5.5 | $0.00019 | $0.00683 |
| Sonnet 5.5 | $0.00009 | $0.00342 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
factory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/factory — Software Factory Autônoma
Linha de montagem industrial multi-agente para desenvolvimento de features. Transforma um pedido em especificação formal, implementação isolada em git worktree com porta dedicada, banca de 4 revisores paralelos com contrato de veredito estrito e gatekeeper de risco que decide entre auto-merge para a branch principal ou escalonamento para humano.
Diferença Fundamental: /factory vs /loop vs /auto
| Dimensão | /auto |
/loop (Auto-Loop v2) |
/factory (Software Factory) |
|---|---|---|---|
| Paradigma | Prompt-based | Process-based CLI runner | Linha de montagem multi-agente |
| Execução | Contexto atual da conversa | Subprocesso Node iterativo (auto-loop.mjs) |
Orquestrador de sessão + 7 subagentes especializados |
| Papéis | Agente único faz tudo | Agente único iterando em loop de turnos | Separação estrita de funções (Spec, Build, 4 Reviewers, Approver) |
| Isolamento | Branch atual / local | --worktree opcional |
Worktree obrigatório + portas dedicadas (5100 + 10n) |
| Revisão de Código | Review pontual final | Polishing pass configurável | Banca 4D paralela (Security, Code, UI, UX) com veredito PASS/CHANGES |
| Gate de Merge | Agente decide ou pergunta | Commit automático se testes passarem | Approver autônomo com taxonomia de risco (merge vs escalate) |
| Fila e Monitoramento | Conversacional | Argumentos CLI | Backlog Markdown atômico (/factory next) + Dashboard HTML local |
O Ciclo da Fábrica (The Assembly Line)
feature → spec-writer → builder → [security, code, ui, ux] (PARALELO)
▲ │
│ ▼
└── any CHANGES: ◄── WAIT FOR ALL
(máx 2 reaberturas) │
▼ all PASS
merge to main ◄── APPROVE ── approver ── ESCALATE ──► needs-human
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 130 lines · 47 tokens per session scan A c279200dee4f
factory is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,708 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other commands, from other repositories
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
release-tag
Create and push a version tag after a release PR has been merged.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.