adversarial-review

adversarial-review is a skill for Claude Code from laurigates/claude-plugins. It costs 37 tokens per session (2,332 once invoked), scanned A, original, MIT.

A second review that deliberately tries to find failures in code, designs, plans, or architecture decisions after a normal review has passed. An architecture decision record, or ADR, is a written explanation of an important technical choice.

In plain words
What is it for?
It helps red-team high-stakes changes, migration plans, ADRs, and other work where hidden mistakes could be costly.
Why use it?
It looks for risks that a first review may have overlooked, while filtering out faults that are merely invented or irrelevant.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Part of the agent-patterns-plugin plugin — 22 skills shipped together

Good fit It helps red-team high-stakes changes, migration plans, ADRs, and other work where hidden mistakes could be costly.

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

Made for: Claude Code.

Or install agent-patterns-plugin, the plugin that ships this one along with the rest of its 22 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/laurigates/claude-plugins/adversarial-review.svg)](https://agentmods.dev/skills/laurigates/claude-plugins/adversarial-review)
Your own site
<a href="https://agentmods.dev/skills/laurigates/claude-plugins/adversarial-review"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/adversarial-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,332 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 7
    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.
How audits are shown
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 $0.00037 $0.02332
Opus 5 $0.00018 $0.01166
Sonnet 5 $0.00007 $0.00466
Haiku 4.5 $0.00004 $0.00233

Measured 4d ago against content hash 133317d97947, 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 4d 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.

agent-patterns-plugin/skills/adversarial-review/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Review

A normal review asks "is this right?" and confirms intent. Adversarial review asks "how could this be wrong?" and hunts for the fault the first pass rationalised away. It is a second pass for residual risk on high-stakes work — not a replacement for the first pass, and not for low-stakes or reversible changes where it only manufactures busywork.

This is a thin posture, not a new checklist. It layers four moves — isolation, inverted objective, a triage gate, and a bounded loop — on top of the domain checklists that already live in code-review, security-audit, verify-before-plan, and cold-read-gate. It dispatches an isolated reviewer with the matching lens and then triages what comes back, because an agent told to find faults will invent them.

When to Use This Skill

Use this skill when... Use something else instead when...
Stakes are high and a normal review already passed, but residual risk remains First-pass review of a diff/PR → code-quality-plugin:code-review
Red-teaming an architecture decision, ADR, or migration plan before commit Verifying plan facts (counts, paths, build state) → agent-patterns-plugin:verify-before-plan
Stress-testing a design's failure modes and invariants Pure security audit → agents-plugin security-audit / /security-review
Probing whether outward text survives a reader → wrap cold-read-gate Legibility of outward text on its own → agent-patterns-plugin:cold-read-gate
The change is hard to reverse and a missed fault is expensive The change is low-stakes, reversible, or throwaway — skip; it wastes tokens

The Four Moves

Move What it means Borrowed from
Isolation The reviewer gets the artifact with no author context — bias can't leak in cold-read-gate
Inverted objective Brief says "enumerate failure modes," never "confirm it works" this skill
Triage gate Separate genuine faults from manufactured objections before acting cold-read-gate Step 3
Bounded loop One revise round; a third means a structural problem the gate can't fix cold-read-gate Step 4

Read the full file on GitHub · 179 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. 4d ago Changed · +5 lines 133317d97947
  2. 8d ago First seen · 174 lines · 37 tokens per session scan A 729d2e0b5f70

Subscribe to this mod's changes

adversarial-review is a skill published in the GitHub repository laurigates/claude-plugins (58 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,332 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 2026-08-30.

Related

Other skills, from other repositories

phpunit-test-team-reviewing

Use this skill when the user asks for a team-based, consensus, multi-reviewer, or red-team review of Shopware PHPUnit tests — trigger phrases like "team review these tests", "consensus review the tests in PR.

shopwareLabs/ai-coding-tools · 52 tokens

phpunit-test-reconciling

Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.

shopwareLabs/ai-coding-tools · 32 tokens

continuous-improvement

Orchestrate a continuous improvement cycle: spawn rust-live-tester for live testing, rust-researcher for dependency monitoring and research, rust-arch-analyst for code quality and architecture review, and rust-security-analyst for vulnerability scanning. Aggregates findings and produces a cycle summary.

bug-ops/claude-plugins · 63 tokens

specification-compliance-review

Use this skill when an implementation is described as partial, passing, or complete and the task is to determine whether it actually satisfies an explicit specification. This is not a generic code review and not a re-run of the test suite. The central question is: does every normative requirement have both a correct…

AtlasOmnia/hermes-custom-pack · 35 tokens

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai · 26 tokens