code-ai-template: Skill for Claude Code

.claude/skills/verificar-referencia/SKILL.md

verificar-referencia is a skill for Claude Code from FHDumont/code-ai-template. It costs 45 tokens per session (665 once invoked), scanned A, original, MIT.

A maintenance routine for checking registered reference repositories for new commits since the last reviewed version.

In plain words
What is it for?
Pulling updates, comparing them with the last reviewed commit, classifying each change as adopt, adapt, or ignore, and opening issues for findings.
Why use it?
It prevents useful changes in external sources from being missed or copied without review. It also keeps a recorded point showing what was checked.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

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/verificar-referencia/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 verificar-referencia

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/fhdumont/code-ai-template/verificar-referencia"><img src="https://agentmods.dev/badge/skills/fhdumont/code-ai-template/verificar-referencia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 665 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 $0.00045 $0.00665
Opus 5.5 $0.00018 $0.00266
Sonnet 5.5 $0.00009 $0.00133
Haiku 4.5 $0.00005 $0.00067

Measured 5d ago against content hash c27eea895e34, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verificar-referencia 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/verificar-referencia/SKILL.md · 23 lines

What it actually says

O método deste repo bebe de fontes externas. Elas continuam evoluindo depois que copiamos delas — esta é a passada que fecha o loop. Entrada e saída são fixas: lê docs/reference/referencias.md, escreve issues achado e o SHA novo. Nada de mudança de método aqui; a triagem é do plan mode.

Rode uma entrada de cada vez. Para cada repo vigiado em docs/reference/referencias.md — a seção Fontes avulsas fica de fora: são post e palestra, sem SHA pra avançar e sem novidade pra puxar:

  1. Atualize o clone. git -C <clone local> pull. Sem clone na máquina? Diga ao dono onde clonar e siga pra próxima entrada.
  2. Levante o que entrou desde o SHA revisado da entrada: git -C <clone> log --oneline <sha>..HEAD e git -C <clone> diff --stat <sha>..HEAD. Se a fonte tem CHANGELOG, git -C <clone> diff <sha>..HEAD -- CHANGELOG.md costuma ser o resumo mais barato. Zero commits → registre "sem novidades" e vá pra próxima.
  3. Leia o que parece relevante — skill nova, mudança em skill que já adaptamos, princípio de método novo. Volume grande: dispare subagentes, um por área, e junte os relatos.
  4. Classifique cada novidade em uma de três:
    • adotar — cabe no método como está, ou com ajuste cosmético.
    • adaptar — a ideia serve, a forma não; vale portar em pt-BR/no formato daqui.
    • ignorar — fora do escopo do template (versionamento, marketplace, stack específica). Ignorado é decisão: diga o porquê em uma linha no relato, e não abra issue.
  5. Abra uma issue achado por item de adotar/adaptar — gh issue create --label achado —, cada uma com: o que é, o caminho do arquivo na fonte, o SHA em que apareceu, e por que vale aqui. Uma issue por item; item grande vira issue própria, não bullet dentro de outra.
  6. Avance o SHA. Atualize SHA revisado e a data da entrada em docs/reference/referencias.md pro HEAD do clone, mesmo quando tudo foi ignorado — o SHA marca "revisado até aqui", não "adotado até aqui".
  7. Relate ao dono: por entrada, quantos commits desde o SHA anterior, o que virou issue, e o que foi ignorado com o porquê.

As issues abertas aqui são matéria-prima solta. Quem decide o que vira fase é o próximo plan mode, pelo /planejar-fase.

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 c27eea895e34
  2. 2mo ago First seen · 23 lines · 45 tokens per session scan A edde49264bd3

Subscribe to this mod's changes

verificar-referencia is a skill published in the GitHub repository FHDumont/code-ai-template (2 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 665 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.