concluir-marco

concluir-marco is a command for Claude Code from luanpdd/kit-mcp. It costs 15 tokens per session (3,135 once invoked), scanned A, original, MIT.

A release wrap-up command that archives a completed milestone’s roadmap and requirements, updates the project record, and creates a Git tag. A milestone is a defined piece of planned project work.

In plain words
What is it for?
Use it after finishing a version to archive its planning files, update PROJECT.md, and create a release tag in Git.
Why use it?
It keeps delivered versions documented and prepares the repository for the next version. It also checks whether the milestone passed its required audit before archiving it.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it after finishing a version to archive its planning files, update PROJECT.md, and create a release tag in Git.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/luanpdd/kit-mcp/concluir-marco
Install

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.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for concluir-marco

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/concluir-marco/github.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/concluir-marco)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/concluir-marco"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/concluir-marco/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.

agentmods 80×15 button for concluir-marco

Your own site · 80×15
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/concluir-marco"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/concluir-marco.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.03135
Opus 5 $0.00008 $0.01568
Sonnet 5 $0.00003 $0.00627
Haiku 4.5 $0.00002 $0.00314

Measured 5d ago against content hash bd8c8ad217af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

concluir-marco 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 5d 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.

kit/commands/concluir-marco.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Propósito: Criar registro histórico da versão entregue, arquivar artefatos do milestone (roadmap + requisitos) e preparar para o próximo milestone. Saída: Milestone arquivado (roadmap + requisitos), PROJECT.md evoluído, tag git criado.

<execution_context> Carregar estes arquivos AGORA (antes de prosseguir):

  • @./.claude/framework/workflows/complete-milestone.md (workflow principal)
  • @./.claude/framework/templates/milestone-archive.md (template de arquivo) </execution_context>

Entrada do usuário:

  • Versão: {{version}} (ex: "1.0", "1.1", "2.0")

Seguir o workflow complete-milestone.md:

  1. Verificar auditoria:

    • Procurar .planning/v{{version}}-MILESTONE-AUDIT.md
    • Se ausente ou desatualizado: recomendar /auditar-marco primeiro
    • Se status da auditoria for gaps_found: recomendar /planejar-lacunas primeiro
    • Se status da auditoria for passed: prosseguir para o passo 1
    ## Verificação Pré-voo
    
    {Se não houver v{{version}}-MILESTONE-AUDIT.md:}
    ⚠ Nenhuma auditoria de milestone encontrada. Execute `/auditar-marco` primeiro para verificar
    cobertura de requisitos, integração entre fases e fluxos E2E.
    
    {Se a auditoria tiver lacunas:}
    ⚠ Auditoria de milestone encontrou lacunas. Execute `/planejar-lacunas` para criar
    fases que fechem as lacunas, ou prossiga assim mesmo para aceitar como dívida técnica.
    
    {Se a auditoria passou:}
    ✓ Auditoria de milestone aprovada. Prosseguindo com a conclusão.
    
  2. Verificar prontidão:

    • Checar se todas as fases do milestone têm planos concluídos (SUMMARY.md existe)
    • Apresentar escopo e estatísticas do milestone
    • Aguardar confirmação
  3. Coletar estatísticas:

    • Contar fases, planos, tarefas
    • Calcular intervalo git, alterações de arquivo, LOC
    • Extrair cronograma do git log
    • Apresentar resumo, confirmar
  4. Extrair realizações:

    • Ler todos os arquivos SUMMARY.md das fases no intervalo do milestone
    • Extrair 4-6 realizações principais
    • Apresentar para aprovação
  5. Arquivar milestone:

    • Criar .planning/milestones/v{{version}}-ROADMAP.md
    • Extrair detalhes completos das fases do ROADMAP.md
    • Preencher template milestone-archive.md
    • Atualizar ROADMAP.md para resumo de uma linha com link
  6. Arquivar requisitos:

    • Criar .planning/milestones/v{{version}}-REQUIREMENTS.md
    • Marcar todos os requisitos v1 como completos (checkboxes marcados)
    • Registrar resultados dos requisitos (validado, ajustado, descartado)
    • Deletar .planning/REQUIREMENTS.md (novo será criado para o próximo milestone)
  7. Atualizar PROJECT.md:

    • Adicionar seção "Estado Atual" com versão entregue
    • Adicionar seção "Objetivos do Próximo Milestone"
    • Arquivar conteúdo anterior em <details> (se v1.1+)
  8. Commit e tag:

    • Stagear: MILESTONES.md, PROJECT.md, ROADMAP.md, STATE.md, arquivos de arquivo
    • Commit: chore: archive v{{version}} milestone
    • Tag: git tag -a v{{version}} -m "[resumo do milestone]"
    • Perguntar sobre push da tag
  9. Oferecer próximos passos:

    • /novo-marco — iniciar próximo milestone (questionamento → pesquisa → requisitos → roadmap)

<success_criteria>

  • Milestone arquivado em .planning/milestones/v{{version}}-ROADMAP.md
  • Requisitos arquivados em .planning/milestones/v{{version}}-REQUIREMENTS.md
  • .planning/REQUIREMENTS.md deletado (novo para próximo milestone)
  • ROADMAP.md colapsado para entrada de uma linha
  • PROJECT.md atualizado com estado atual
  • Tag git v{{version}} criado
  • Commit bem-sucedido
  • Usuário conhece os próximos passos (incluindo necessidade de novos requisitos) </success_criteria>

Read the full file on GitHub · 248 lines

Changes

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.

  1. 5d ago First seen · 248 lines · 15 tokens per session scan A bd8c8ad217af

Subscribe to this mod's changes

concluir-marco is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 3,135 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.