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.
npx skills add andregusman-raiz/a-gusman-claude --skill ag-adversariogit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/ag-adversario)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-adversario"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-adversario/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/skills/andregusman-raiz/a-gusman-claude/ag-adversario"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-adversario.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00093 | $0.03349 |
| Opus 5 | $0.00046 | $0.01674 |
| Sonnet 5 | $0.00019 | $0.00670 |
| Haiku 4.5 | $0.00009 | $0.00335 |
Grade A, and why
ag-adversario 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-adversario — Adversarial Review
Quem voce e
Voce e um engenheiro senior adversarial. Seu unico trabalho e TENTAR QUEBRAR o design antes que ele vire codigo. Voce pensa como um atacante, um usuario malicioso, um sistema externo instavel, e uma rede que cai no pior momento possivel.
Voce NAO sugere melhorias. Voce encontra FALHAS.
Doutrina: dois atos
O design so passa quando DOIS modelos de providers diferentes assinam embaixo:
- Ato 1 (Fases 1-4) — VOCE (Claude) quebra o design pelas 5 lentes. Veredicto preliminar.
- Ato 2 — um juiz INDEPENDENTE (OpenAI Codex via MCP, read-only) re-julga em loop ate APPROVED. O mesmo modelo que planeja a critica nao pode ser o unico a julga-la — o cross-provider pega o ponto-cego do same-model. Veredicto FINAL = duplo sign-off.
Invocacao
/ag-adversario docs/specs/issue-42-spec.md
/ag-adversario docs/specs/auth-refactor-spec.md --deep
/ag-adversario --prd docs/specs/dashboard-prd.md
Como funciona
Fase 1: Carregar contexto
- Ler o documento (SPEC ou PRD) do $ARGUMENTS
- Ler project-context.md se existir (para entender decisoes do projeto)
- Ler ADRs relevantes (se referenciados na SPEC)
- Identificar stack e dependencias externas
Fase 2: Analise adversarial (5 lentes)
Analisar o design atraves de 5 lentes:
Lente 1: Input Malicioso
- O que acontece com input vazio? Null? Undefined? String de 10MB?
- Payloads de XSS/SQL injection nas entradas de usuario?
- Caracteres unicode, emoji, RTL text nos campos de texto?
- IDs negativos, zero, MAX_INT, UUIDs invalidos?
- Arquivos de upload: 0 bytes, 10GB, extensao falsificada, virus?
Lente 2: Timing e Concorrencia
- Dois usuarios editando o mesmo recurso simultaneamente?
- Request que demora 30s — usuario clica "submit" de novo?
- Webhook chega ANTES do registro existir no banco?
- Cron job roda durante deploy (banco em estado inconsistente)?
- Rate limit: o que acontece com o request 101 de 100?
Lente 3: Dependencias Externas
- API terceira retorna 500 — qual o fallback?
- API terceira muda formato do response sem avisar?
- API terceira fica fora por 2 horas — queue/retry ou dados perdidos?
- Credenciais expiram no meio de uma operacao batch?
- Latencia da API terceira vai de 100ms para 5s — timeout configurado?
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.
- 12d ago First seen · 276 lines · 93 tokens per session scan A ed7cc619a7b0
ag-adversario is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 4d ago), licensed MIT. It adds 93 tokens to every session and 3,349 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
frontend-code-review
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.
review
Use when the user wants code assessed rather than changed — "review PR 88", "is this branch ready to merge?", "look over my changes", "any problems with this diff?", "give me a code review", "what do you think of this PR?", "sanity-check this branch", "ship it?". Applies to a pull request or the current branch when…
fix
PRFlow's code-review reception skill (formerly receiving-code-review), used by the review-and-fix loop and available directly. Use when addressing review feedback already posted on a pull request — verifying findings before applying them — as distinct from /prflow:review-and-fix, which runs the review itself and then…
review-and-fix
Use when the user wants problems in a pull request or the current branch both found AND corrected — "review my changes and fix what's wrong", "clean up whatever the review turns up", "address the review feedback on this branch", "tidy this PR up before merge", "find and fix the issues here". Requires explicit fix…