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/loopWrote 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/loop)<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/loop"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/loop/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/loop"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/loop.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 | $0.00030 | $0.02978 |
| Opus 5 | $0.00015 | $0.01489 |
| Sonnet 5 | $0.00006 | $0.00596 |
| Haiku 4.5 | $0.00003 | $0.00298 |
Grade A, and why
loop 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 2d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/loop — Autonomous Loop v2
Invoca scripts/auto-loop.mjs para executar uma task de forma completamente autônoma. Versão 2 adiciona suporte multi-agente (claude + codex), worktree integrado com modo paralelo, passe de qualidade configurável (polishing pass), e quick wins inspirados no gnhf.
Diferença em relação ao /auto:
/auto— prompt-based: Claude lê o protocolo e executa no contexto atual/loop— process-based: Node.js roda o agente como subprocess, iterando até done
Uso
# Task única (default)
node scripts/auto-loop.mjs "sua task aqui"
# Em repos consumidores (instalado em .bot/)
node .bot/scripts/auto-loop.mjs "sua task aqui"
# Multi-task em paralelo (worktrees isolados)
node scripts/auto-loop.mjs --worktree --parallel 3 \
-- "implementar feature A" \
-- "adicionar testes módulo B" \
-- "refatorar API C"
Flags
| Flag | Descrição | Default |
|---|---|---|
--agent claude|codex |
Agente a usar | claude |
--model <name> |
Modelo (apenas para claude) |
$CLAUDE_LOOP_MODEL se definida, senão claude-sonnet-4-5 |
--max-iterations <n> |
Cap de iterações | auto (8/12/15) |
--max-tokens <n> |
Aborta quando tokens cumulativos passam de n |
unlimited |
--stop-when "<cond>" |
Encerra loop quando agente reporta condição satisfeita | — |
--contract <path.json> |
Contrato formal (schemas/task-contract.schema.json) — done_when dirige conclusão, escalate_when para o loop e sinaliza pro usuário em vez do agente decidir sozinho |
— |
--polish none|light|standard|full |
Passe de qualidade após validation | standard |
--worktree |
Roda em git worktree isolado | false |
--parallel <n> |
Roda n tasks em paralelo (requer --worktree, max 8) |
1 |
--no-prevent-sleep |
Não previne sleep do sistema durante a run | false |
--validate |
Validação completa em cada iteração | false |
--no-commit |
Não fazer commit automático ao concluir | false |
--push |
Push após commit | false |
--verbose |
Mostrar output completo do agente | false |
-h, --help |
Mostrar ajuda | — |
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.
- 2d ago Changed · +3 lines ba4986800b6a
- 4d ago Changed 358f7cab164c
- 10d ago First seen · 222 lines · 30 tokens per session scan A 2b0a4b11cdac
loop is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 2,978 once invoked, about $0.0002 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.