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/executar-fase)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/executar-fase"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/executar-fase.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 | $0.00019 | $0.00806 |
| Opus 5 | $0.00010 | $0.00403 |
| Sonnet 5 | $0.00004 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
executar-fase 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.
What it actually says
O orquestrador se mantém enxuto: descobrir planos, analisar dependências, agrupar em ondas, invocar subagentes, coletar resultados. Cada subagente carrega o contexto completo de execute-plan e cuida do seu próprio plano.
Filtro de onda opcional:
--wave Nexecuta apenas a OndaNpara controle de ritmo, gestão de cota ou lançamento em etapas- verificação/conclusão da fase ainda ocorre apenas quando não há planos incompletos restantes após a onda selecionada terminar
Regra de tratamento de flags:
- As flags opcionais documentadas abaixo são comportamentos disponíveis, não comportamentos ativos implícitos
- Uma flag está ativa apenas quando seu token literal aparece em
$ARGUMENTS - Se uma flag documentada estiver ausente de
$ARGUMENTS, trate-a como inativa
Orçamento de contexto: ~15% orquestrador, 100% fresco por subagente.
<execution_context> @./.claude/framework/workflows/execute-phase.md @./.claude/framework/references/ui-brand.md </execution_context>
Flags opcionais disponíveis (somente documentação — não automaticamente ativas):
--wave N— Executar apenas a OndaNna fase. Use quando quiser controlar o ritmo da execução ou ficar dentro dos limites de uso.--gaps-only— Executar apenas planos de fechamento de lacunas (planos comgap_closure: trueno frontmatter). Use após verify-work criar planos de correção.--interactive— Executar planos sequencialmente inline (sem subagentes) com checkpoints de usuário entre tarefas. Menor uso de tokens, estilo programação em par. Melhor para fases pequenas, correções de bugs e lacunas de verificação.[modelo]— token de modelo no fim (opus|sonnet|haiku|inheritou id do runtime, ex.:/executar-fase 3 --wave 1 haiku). Força o modelo do executor só nesta execução — override de prioridade máxima sobre o perfil. Absorvido doexecute <plano> <modelo>doimprove.
Flags ativas devem ser derivadas de $ARGUMENTS:
--wave Nestá ativa somente se o token literal--waveestiver presente em$ARGUMENTS--gaps-onlyestá ativa somente se o token literal--gaps-onlyestiver presente em$ARGUMENTS--interactiveestá ativa somente se o token literal--interactiveestiver presente em$ARGUMENTS- Se nenhum desses tokens aparecer, executar o fluxo padrão de execução completa da fase sem filtragem específica de flag
- Não inferir que uma flag está ativa apenas porque está documentada neste prompt
Arquivos de contexto são resolvidos dentro do workflow via tools init execute-phase e blocos <files_to_read> por subagente.
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 · 60 lines · 19 tokens per session scan A ff01e6b58a58
executar-fase is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 806 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 2026-09-03.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.