code-ai-template: Skill for Claude Code

.claude/skills/fechar-fase/SKILL.md

fechar-fase is a skill for Claude Code from FHDumont/code-ai-template. It costs 48 tokens per session (1,029 once invoked), scanned A, original, MIT.

A close-out checklist for finishing a development phase and preparing its changes for review and merging.

In plain words
What is it for?
Use it to verify a phase against its specification, get a fresh review, update project records, pause for owner approval, and then merge and clean up the branch.
Why use it?
It prevents unfinished tests, missed documentation, and unreviewed differences from being treated as done.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions AGENTS.md.

This is FHDumont/code-ai-template's own configuration. It tells Claude Code how to work on code-ai-template itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything code-ai-template configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FHDumont/code-ai-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FHDumont/code-ai-template/main/.claude/skills/fechar-fase/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/FHDumont/code-ai-template

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 fechar-fase

README.md
[![agentmods](https://agentmods.dev/badge/skills/fhdumont/code-ai-template/fechar-fase/github.svg)](https://agentmods.dev/skills/fhdumont/code-ai-template/fechar-fase)
Your own site
<a href="https://agentmods.dev/skills/fhdumont/code-ai-template/fechar-fase"><img src="https://agentmods.dev/badge/skills/fhdumont/code-ai-template/fechar-fase/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 fechar-fase

Your own site · 80×15
<a href="https://agentmods.dev/skills/fhdumont/code-ai-template/fechar-fase"><img src="https://agentmods.dev/badge/skills/fhdumont/code-ai-template/fechar-fase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,029 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 $0.00048 $0.01029
Opus 5.5 $0.00019 $0.00412
Sonnet 5.5 $0.00010 $0.00206
Haiku 4.5 $0.00005 $0.00103

Measured 5d ago against content hash 644de66472d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fechar-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 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.

.claude/skills/fechar-fase/SKILL.md · 24 lines

What it actually says

Checklist do fecho. As regras vivem em AGENTS.md (§Regra de migração, §Git); aqui está a ordem. O pedido de fecho é a validação: invocar esta skill — ou pedir o fecho em linguagem natural — significa que o dono testou e libera a sequência inteira, sem pausa no meio. Falha ainda para: critério que falha ou revisão que diverge voltam pro código antes de qualquer PR — isso é falha reportada, não pedido de confirmação.

Esta skill duplica de propósito o AGENTS.md §Git como runbook executável. Se um mudar, o outro muda junto.

O ambiente é do dono: não suba nem derrube nada; build, teste e lint rodam sem ele.

A sequência — corre inteira, sem pausar

  1. Rode os critérios de pronto da spec, um por um, com execução real — typecheck, lint, teste dos arquivos tocados. Critério que falhou volta pro código; "feito" só depois de verificado. Teste novo da fase tem que ter falhado no código antigo — se ainda não provou o vermelho (worktree ou patch revertido), prove agora; teste que passa idêntico antes e depois da mudança não é critério. Critério escrito com número absoluto de produção se confere pela estrutura e o número se reconta, reportando os dois.
  2. Revisão de fecho com contexto fresco. Dispare o subagente revisor-fecho (.claude/agents/revisor-fecho.md — o checklist da casa já vem nele) via Task; ele não tem o contexto desta sessão, e você entrega só: a spec da fase e o alvo (git diff main...HEAD). A pergunta dele é uma: o entregue bate com a intenção da spec, item a item? Divergiu → corrija e rode o revisor-fecho de novo tendo o commit de correção como alvo — a correção abre defeito novo com frequência, e só a segunda passada vê. Fase que não tocou código pode pular este passo.
  3. Passada única de docs vivos, tudo antes do commit final: spec inteira de SETUP.md → docs/history/fases/F-xxx.md (arquivo novo) mais uma linha no índice docs/history/SETUP-HISTORICO.md, com o bloco Notas de implementação (desvios, soluções não-óbvias, becos evitados — memória, não log); uma linha em docs/CHANGELOG.md (F-xxx — o que entrou — AAAA-MM-DD); fase removida do ROADMAP.md; DEBITO-TECNICO.md atualizado (débito novo, e o resolvido migrando inteiro pro histórico com nota de como foi); ADR novo se a entrega divergiu por decisão de arquitetura, regra R-NNN em docs/reference/ se o que mudou foi comportamento com exemplo (AGENTS.md §ADR ou regra); CONTEXT.md (e docs/reference/dominio.md) se a fase afiou algum termo.
  4. Commite por caminho explícito — nunca git add -A com subagente rodando: o working tree é compartilhado; confira o git status antes. A passada de docs pode ir junto com a etapa final ou num commit docs: fecho da F-xxx próprio — desde que esse não carregue código (regra canônica em AGENTS.md §Regra de migração).
  5. gh pr create com corpo curto: o que/por quê, os critérios, e a referência à F-xxx.
  6. Confirme os checks verdes. Um CI por fecho: o build que dispara no merge é entrega, não gate — não espere um segundo.
  7. gh pr merge --rebase --delete-branch — os commits da fase entram lineares no main, um por etapa, e a branch some na remota e na local. O hook bloqueia git branch -D; esta é a rota oficial.
  8. Sincronize: git switch main && git pull.
  9. Confirme com git branch: só main, atualizado com o origin/main. O dono não toca no GitHub. Relate ao dono no fim: cada critério com seu resultado, o veredito da revisão de fecho, os docs tocados, e o PR integrado.
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 Changed 644de66472d5
  2. 1mo ago Changed · -1 lines · +5 tokens per session 881d03f8e7bc
  3. 2mo ago First seen · 25 lines · 43 tokens per session scan A 01a5393e2692

Subscribe to this mod's changes

fechar-fase is a skill published in the GitHub repository FHDumont/code-ai-template (2 stars, last pushed 5d ago), licensed MIT. It adds 48 tokens to every session and 1,029 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Related

Other skills, from other repositories

batch

Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.

asgeirtj/system_prompts_leaks · 30 tokens

team-release

Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.

Donchitos/Claude-Code-Game-Studios · 33 tokens

operating-github-cli

Default GitHub skill for the action agent. Use githubcli for any GitHub request — create/list/view/close issues and PRs, assign, labels, repos, releases, checks, github.com/owner/repo URLs, or gh api. Prefer over shellrun/!gh. Run these with githubcli in the current agent turn.

Tracer-Cloud/opensre · 75 tokens

github

Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.

AtomicBot-ai/atomic-agent · 48 tokens

testdino-releases

Use when the user wants to browse, inspect, create, or update releases/milestones in a TestDino project. Covers listreleases, getrelease, createrelease, and updaterelease. Accepts counter-style IDs like MS-12.

anthropics/claude-plugins-community · 56 tokens

create-milestone

Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.

agentic-community/mcp-gateway-registry · 64 tokens