adversarial-reviewer

adversarial-reviewer is a skill for Claude Code, Codex from ricneves-ai/flowgrammers-skills. It costs 97 tokens per session (3,297 once invoked), scanned A, original, MIT.

A deliberately critical code-review skill that examines changes through three reviewer viewpoints: production-breakage, maintainability, and security. It reviews staged changes, unstaged changes, diffs, files, and pull requests before merging.

In plain words
What is it for?
Use it to review recent code changes, pull-request diffs, or individual files for production risks, maintainability problems, and security concerns before a merge.
Why use it?
It reduces the chance that a self-review overlooks a problem or approves changes too easily. Findings are ranked by severity, and issues found by multiple viewpoints receive more weight.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it to review recent code changes, pull-request diffs, or individual files for production risks, maintainability problems, and security concerns before a merge.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ricneves-ai/flowgrammers-skills/adversarial-reviewer
Install

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.

Any agent
npx skills add ricneves-ai/flowgrammers-skills --skill adversarial-reviewer
Clone the repo
git clone --depth 1 https://github.com/ricneves-ai/flowgrammers-skills

Made for: Claude Code, Codex.

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 adversarial-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/adversarial-reviewer/github.svg)](https://agentmods.dev/skills/ricneves-ai/flowgrammers-skills/adversarial-reviewer)
Your own site
<a href="https://agentmods.dev/skills/ricneves-ai/flowgrammers-skills/adversarial-reviewer"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/adversarial-reviewer/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 adversarial-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ricneves-ai/flowgrammers-skills/adversarial-reviewer"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/adversarial-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,297 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 $0.00097 $0.03297
Opus 5 $0.00048 $0.01648
Sonnet 5 $0.00019 $0.00659
Haiku 4.5 $0.00010 $0.00330

Measured 9d ago against content hash 8c25c8f04027, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

adversarial-reviewer 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 9d 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.

engineering-team/adversarial-reviewer/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Revisor de Código Adversarial

Descrição

Skill de revisão de código adversarial que força mudanças genuínas de perspectiva por meio de três personas de revisores hostis (Sabotador, Novo Contratado, Auditor de Segurança). Cada persona DEVE encontrar pelo menos um problema — nenhum "LGTM" passa. Os resultados são classificados por severidade e promovidos quando capturados por múltiplas personas.

Funcionalidades

  • Três personas adversariais — Sabotador (quebras em produção), Novo Contratado (manutenibilidade), Auditor de Segurança (baseado em OWASP)
  • Resultados obrigatórios — Cada persona deve expor pelo menos um problema, eliminando revisões superficiais
  • Promoção de severidade — Problemas capturados por 2+ personas são promovidos um nível de severidade
  • Quebrador de armadilha de auto-revisão — Técnicas concretas para superar pontos cegos de modelo mental compartilhado
  • Veredictos estruturados — BLOQUEAR / PREOCUPAÇÕES / LIMPO com orientação clara para merge

Uso

/adversarial-review              # Revisar mudanças staged/unstaged
/adversarial-review --diff HEAD~3  # Revisar os últimos 3 commits
/adversarial-review --file src/auth.ts  # Revisar um arquivo específico

Exemplos

Exemplo: Revisando um PR Antes do Merge

/adversarial-review --diff main...HEAD

Produz um relatório estruturado com resultados de todas as três personas, deduplicados e classificados por severidade, terminando com um veredicto BLOQUEAR/PREOCUPAÇÕES/LIMPO.

Problema que Esta Skill Resolve

Quando o Claude revisa código que escreveu (ou que acabou de ler), ele compartilha o mesmo modelo mental, as mesmas suposições e os mesmos pontos cegos que o autor. Isso produz revisões do tipo "Parece bom para mim" em código que um revisor humano novo sinalizaria imediatamente. Usuários relatam isso como uma das maiores frustrações no desenvolvimento assistido por IA.

Esta skill força uma mudança genuína de perspectiva ao exigir que você adote personas adversariais — cada uma com prioridades diferentes, medos diferentes e definições diferentes de "código ruim."

Read the full file on GitHub · 249 lines

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. 9d ago First seen · 249 lines · 97 tokens per session scan A 8c25c8f04027

Subscribe to this mod's changes

adversarial-reviewer is a skill published in the GitHub repository ricneves-ai/flowgrammers-skills (112 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 3,297 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 2026-09-03.

Related

Other skills, from other repositories