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/run-programWrote 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/run-program)<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/run-program"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/run-program/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/run-program"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/run-program.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 | $0.00027 | $0.01407 |
| Opus 5 | $0.00014 | $0.00704 |
| Sonnet 5 | $0.00005 | $0.00281 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
run-program 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 10d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/run-program — Executable YAML Pipelines
Objetivo: parsear e executar programs/<nome>.yml como pipeline declarativo. Cada step pode ser um command, gate humano, bloco paralelo, ou conditional. Variable substitution via ${inputs.X} e ${steps.X.output}.
Inspiração: github/spec-kit workflows/ + extensões nossas (when, parallel, conditional, vars).
Quando usar
- pipelines repetidos que mereçam consistência (spec-driven, pipeline-discovery, loop-polishing, detective-spec)
- fluxos com múltiplos review gates onde "humano decide entre passos"
- equipes que precisam de mesmo pipeline executado igual por agentes diferentes
Quando NÃO usar
- task de 1 ou 2 steps — overhead desproporcional
- exploração sem fluxo definido
- iteração ad-hoc onde o próximo passo depende de algo dinâmico não modelável
Pré-requisitos
- arquivo
programs/<nome>.ymlexiste - todos os commands referenciados estão disponíveis (
/spec,/plan, etc) - inputs do programa serão pedidos via
AskUserQuestionse obrigatórios
Processo
Passo 1 — Validar o program
node scripts/validate-program.mjs programs/<nome>.yml
Se inválido: abort com lista de erros.
Passo 2 — Resolver inputs
Para cada input em inputs: do YAML:
- Se passado via
--input <key>=<value>, usar - Se obrigatório e ausente, usar
AskUserQuestioncom opromptdo schema - Se opcional, usar
default(ou pedir confirmação se--ask-all)
Passo 3 — Resolver variable substitution
Antes de executar cada step:
- Substituir
${inputs.X}por valor real - Substituir
${steps.Y.output}ou${steps.Y.capture.Z}por output capturado anteriormente - Substituir
${date},${env.X}, etc.
Referências a steps que ainda não rodaram → erro de runtime.
Passo 4 — Executar steps em ordem
Para cada step do array steps[]:
- Avaliar
when— se false, skip (warning no log) - Despachar pelo tipo:
command→ invocar slash command via Task ou diretogate→AskUserQuestioncom options; respeitaron_rejectparallel→ despachar todos via Task em 1 mensagem; aguardar todosconditional→ avaliarif; rodarthen[]ouelse[]
- Capturar output se
capture: <name>declarado - Tratar erros conforme
on_error(abort/continue/retry)
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.
- 10d ago First seen · 140 lines · 27 tokens per session scan A c900c2e3265a
run-program is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,407 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.