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.
curl -O https://raw.githubusercontent.com/FHDumont/code-ai-template/main/.claude/skills/verificar-referencia/SKILL.mdgit clone --depth 1 https://github.com/FHDumont/code-ai-templateWrote 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/skills/fhdumont/code-ai-template/verificar-referencia)<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="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 | $0.00045 | $0.00630 |
| Opus 5 | $0.00023 | $0.00315 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
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 8d 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 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 uma em docs/reference/referencias.md:
- Atualize o clone.
git -C <clone local> pull. Sem clone na máquina? Diga ao dono onde clonar e siga pra próxima entrada. - Levante o que entrou desde o SHA revisado da entrada:
git -C <clone> log --oneline <sha>..HEADegit -C <clone> diff --stat <sha>..HEAD. Se a fonte tem CHANGELOG,git -C <clone> diff <sha>..HEAD -- CHANGELOG.mdcostuma ser o resumo mais barato. Zero commits → registre "sem novidades" e vá pra próxima. - 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.
- 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.
- Abra uma issue
achadopor 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. - Avance o SHA. Atualize
SHA revisadoe a data da entrada emdocs/reference/referencias.mdproHEADdo clone, mesmo quando tudo foi ignorado — o SHA marca "revisado até aqui", não "adotado até aqui". - 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.
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.
- 8d ago First seen · 23 lines · 45 tokens per session scan A edde49264bd3
verificar-referencia is a skill published in the GitHub repository FHDumont/code-ai-template (2 stars, last pushed 27d ago), licensed MIT. It adds 45 tokens to every session and 630 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…