Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/felvieira/claude-skills-fvWrote 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/auto)<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/auto"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/auto/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/auto"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/auto.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 | $0.00021 | $0.02747 |
| Opus 5 | $0.00010 | $0.01373 |
| Sonnet 5 | $0.00004 | $0.00549 |
| Haiku 4.5 | $0.00002 | $0.00275 |
Grade A, and why
auto 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 11d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/auto — Agente Autônomo
Início imediato: Ao receber este comando, leia o guia completo antes de qualquer outra ação:
- Se instalado como plugin global:
docs/skill-guides/autonomous-loop.md - Se instalado em
.bot/:.bot/docs/skill-guides/autonomous-loop.md
Leia o guia com o Read tool agora. Depois execute o loop completo sem parar para perguntar.
Regras Invioláveis
- Nunca perguntar ao usuário — decidir com base no kit, codebase e policies
- Nunca entregar código sem testes passando — se não testa, não está pronto
- Nunca pular security review — todo código passa por OWASP checklist
- Nunca expandir scope — implementar exatamente o que foi pedido, nada mais
- Parar se estiver stuck — após 3 tentativas no mesmo erro, declarar bloqueio com diagnóstico
- Manter progresso visível — escrever
.auto/progress.mdapós cada fase
Loop Autônomo
PLAN → [UI-DESIGN] → BUILD → TEST → FIX → VALIDATE → REVIEW → COMMIT
↑ |
└──────────────── se falhar ──────────────┘
UI-DESIGN só roda quando o escopo inclui frontend (ver Fase 1). É um gate: o BUILD de qualquer arquivo visual não começa antes de a âncora estética estar escolhida e os tokens definidos.
Fase 0 — Setup
- Criar diretório
.auto/para tracking de progresso - Roteamento estruturado obrigatório: rodar
node scripts/route-task.mjs --json --out .auto/route.json "<task>"; carregar as skills/policies retornadas antes de planejar. Recomendações externas são apenas informativas: não instalar nem executar sem opt-in explícito e, se alto risco, revisão humana. - Pesquisar o codebase — usar política de search-first (arquivo em
policies/search-first.mdou.bot/policies/search-first.md) - Ler
docs/repo-audit/current.mdou.bot/docs/repo-audit/current.mdse existir - Detectar ferramentas disponíveis: test framework, lint, typecheck, build (verificar
package.json,pyproject.toml,Makefile, etc.) - Registrar ferramentas detectadas em
.auto/env.md - Snapshot inicial: rodar
git diff --statpara baseline
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.
- 11d ago First seen · 191 lines · 21 tokens per session scan A da96fe6b844d
auto is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 2,747 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.