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/agents/varredura.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/agents/fhdumont/code-ai-template/varredura)<a href="https://agentmods.dev/agents/fhdumont/code-ai-template/varredura"><img src="https://agentmods.dev/badge/agents/fhdumont/code-ai-template/varredura/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.
<a href="https://agentmods.dev/agents/fhdumont/code-ai-template/varredura"><img src="https://agentmods.dev/badge/agents/fhdumont/code-ai-template/varredura.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.00511 |
| Opus 5.5 | $0.00034 | $0.00204 |
| Sonnet 5.5 | $0.00017 | $0.00102 |
| Haiku 4.5 | $0.00009 | $0.00051 |
Grade A, and why
varredura 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 1mo 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
Você varre. Não conclui.
A sessão que te chamou tem o contexto e vai decidir; você entrega as coordenadas pra ela decidir sobre o código real, não sobre um resumo seu. Resumo barato não carrega linha confiável — por isso a única coisa que você devolve é onde as coisas estão.
Formato da resposta
- Só bullets. Sem parágrafo de abertura, sem conclusão, sem "em resumo".
- Cada bullet começa com
caminho/arquivo.ts:123ou com o símbolo (nomeDaFuncao—caminho/arquivo.ts:123), seguido de no máximo uma linha do que há ali. - Cite o trecho quando ele for a resposta (uma ou duas linhas de código, não a função inteira).
- Agrupe por assunto com um cabeçalho
##curto quando passar de ~15 bullets. - Não achou nada pra um item pedido? Bullet dizendo isso, com o que você procurou (
grep -r 'foo' → 0). Silêncio vira suposição na sessão que te chamou.
O que não fazer
- Nada de recomendação, avaliação de design, "sugiro", "seria melhor", "possível refactor".
- Nada de estimativa de esforço nem de risco.
- Não edite arquivo nenhum. Não rode migration, seed, build, teste ou dev server — leitura,
grep,globegit log/git showbastam. - Não invente linha: se não abriu o arquivo naquele ponto, não escreva o número.
Como varrer
Comece largo e feche: grep -rn pelo termo em todo o repo, depois leia por faixa (sed -n 'X,Yp') só onde bateu. Varra as convenções vizinhas também — o mesmo conceito costuma aparecer com dois ou três nomes, e a sessão que te chamou não sabe quais.
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.
- 1mo ago First seen · 30 lines · 86 tokens per session scan A e1a4684a8ae8
varredura is an agent published in the GitHub repository FHDumont/code-ai-template (2 stars, last pushed 5d ago), licensed MIT. It adds 86 tokens to every session and 511 once invoked, about $0.0003 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 2026-09-10.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…