adversarial-review

adversarial-review is a skill for Claude Code, Codex from gabonio/agent-operator-toolkit. It costs 68 tokens per session (328 once invoked), scanned A, original, MIT.

A read-only review process that deliberately tests a specification, plan, architecture, code change, or readiness claim for hidden problems. It checks assumptions, risks, failure cases, and missing verification.

In plain words
What is it for?
Pressure-testing designs, reviewing implementation diffs, challenging readiness claims, and identifying security, compatibility, operational, or testing gaps.
Why use it?
It helps expose important flaws before work is approved or shipped. Findings are tied to available evidence instead of being presented as guesses.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the builder-kit plugin — 5 skills shipped together

Good fit Pressure-testing designs, reviewing implementation diffs, challenging readiness claims, and identifying security, compatibility, operational, or testing gaps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gabonio/agent-operator-toolkit/adversarial-review
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 gabonio/agent-operator-toolkit --skill adversarial-review
Clone the repo
git clone --depth 1 https://github.com/gabonio/agent-operator-toolkit

Made for: Claude Code, Codex.

Or install builder-kit, the plugin that ships this one along with the rest of its 5 skills.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabonio/agent-operator-toolkit/adversarial-review.svg)](https://agentmods.dev/skills/gabonio/agent-operator-toolkit/adversarial-review)
Your own site
<a href="https://agentmods.dev/skills/gabonio/agent-operator-toolkit/adversarial-review"><img src="https://agentmods.dev/badge/skills/gabonio/agent-operator-toolkit/adversarial-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 328 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 $0.00068 $0.00328
Opus 5 $0.00034 $0.00164
Sonnet 5 $0.00014 $0.00066
Haiku 4.5 $0.00007 $0.00033

Measured 7d ago against content hash decae18b6cd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

adversarial-review 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 7d 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.

plugins/builder-kit/skills/adversarial-review/SKILL.md · 20 lines

What it actually says

Adversarial Review

Read the adversarial lens, lens routing, and only the domain lenses relevant to the target.

Procedure

  1. Identify the artifact, approved objective, relevant constraints, and evidence available.
  2. State the review boundary and whether this is a same-context pass, fresh-context pass, automated evidence, or human review. Do not imply independence that did not occur.
  3. Challenge material assumptions, decision tradeoffs, failure modes, scale, trust boundaries, operability, and verification gaps.
  4. Verify claims against repository evidence where possible. Label observation, inference, hypothesis, and unanswered question distinctly.
  5. Report the three or four most material findings by default. Report fewer when fewer are real; do not fill the batch with style preferences or speculative criticism. For code, anchor each finding to the tightest useful path and line range.
  6. Include overlooked strengths, residual risks, and one verdict: ready, ready with accepted risks, revise, or blocked on decision.

Remain read-only unless the user separately authorizes changes. A finding does not overrule repository evidence or user authority; document accepted risks clearly.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 20 lines · 68 tokens per session scan A decae18b6cd4

Subscribe to this mod's changes

adversarial-review is a skill published in the GitHub repository gabonio/agent-operator-toolkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 328 once invoked, about $0.0003 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.

Related

Other skills, from other repositories