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/luanpdd/kit-mcpWrote 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/luanpdd/kit-mcp/criar-workflow)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/criar-workflow"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/criar-workflow.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.01625 |
| Opus 5 | $0.00028 | $0.00813 |
| Sonnet 5 | $0.00011 | $0.00325 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
criar-workflow 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 4d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
criar-workflow
Entrypoint pra gerar um Dynamic Workflow customizado pro teu projeto. O kit não cresce com workflows de nicho — cresce com a capacidade de gerar workflows sob demanda.
Cada usuário ganha o DELE, calibrado pro stack/dor que ele tem. Outro usuário com necessidade diferente roda
/criar-workflow <sua descrição>e ganha um diferente.
- Classify — pergunta qual dos 6 patterns canônicos (Classify-Act, Fanout-Synthesize, Adversarial-Verify, Generate-Filter, Tournament, Loop-Done) encaixa
- Specify — faz 2-4 perguntas específicas do pattern escolhido
- Compose — detecta MCP necessárias + propõe reuso de agents canônicos do kit
- Materialize — escreve
.claude/workflows/<slug>.workflow.js+.claude/commands/<slug>.md(locais ao projeto, NUNCA no kit canônico)
Cria:
.claude/workflows/<slug>.workflow.js— script JS executável pela tool Workflow do Claude Code.claude/commands/<slug>.md— slash-command que dispara o workflow
Após: /<slug> [--args] invoca direto. Pra rodar a cada N minutos: /loop 3m /<slug>. Pra cron remoto: /schedule "*/3 * * * *" <slug>.
Exemplos:
/criar-workflow auditar comportamento dos agentes IA atendendo WhatsApp
a cada 3 minutos, analisar transcripts e gerar report
/criar-workflow rankear top 10 PRs no GitHub abertos ha mais de 7 dias
sem revisao por impacto
/criar-workflow bug hunt continuo no codigo do servico de pagamento
ate 2 rounds sem novos achados
/criar-workflow brainstorm 12 nomes pra minha CLI e pegar top 3 por
memorability + brand fit
Pré-requisitos:
- Claude Code Max / Team / Enterprise (Dynamic Workflows em research preview Opus 4.8+)
- Tool
Workflowhabilitada na sessão .claude/workflows/existe ou sera criado
Quando NÃO usar:
- Tarefa cabe em 1 slash-command existente (ex.: ja temos
/auditar-observabilidade-cobertura-workflow— não duplique) - Descrição vaga ("automatize meu projeto") — refine antes
- Mudança que precisa entrar no kit canônico — esses são PRs no repo
luanpdd/kit-mcp, não workflows locais
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.
- 4d ago First seen · 159 lines · 55 tokens per session scan A bab6e9697d75
criar-workflow is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,625 once invoked, about $0.0003 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 2026-09-03.
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.