adversarial-review-quick

adversarial-review-quick is a skill for Claude Code from patrickdappollonio/claude-plugins. It costs 210 tokens per session (8,404 once invoked), scanned A, original, MIT.

A smaller panel-based review process that checks a code change from eight independent, hostile viewpoints.

In plain words
What is it for?
Quick reviews of a pull request, commit, or local change, especially for design fit, tests, assumptions, observability, incomplete fixes, data integrity, and API contracts.
Why use it?
It looks for problems the author or main agent may overlook while using fewer reviewers than a full adversarial review. It does not cover areas such as input attacks, authorisation, concurrency, or state changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Claude Code.

Part of the adversarial-review plugin — 2 skills shipped together

Good fit Quick reviews of a pull request, commit, or local change, especially for…

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

Made for: Claude Code.

Or install adversarial-review, the plugin that ships this one along with the rest of its 2 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-quick

README.md
[![agentmods](https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/adversarial-review-quick.svg)](https://agentmods.dev/skills/patrickdappollonio/claude-plugins/adversarial-review-quick)
Your own site
<a href="https://agentmods.dev/skills/patrickdappollonio/claude-plugins/adversarial-review-quick"><img src="https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/adversarial-review-quick.svg" alt="Measured on agentmods" height="20"></a>
Per session 210 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,404 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 $0.00210 $0.08404
Opus 5 $0.00105 $0.04202
Sonnet 5 $0.00042 $0.01681
Haiku 4.5 $0.00021 $0.00840

Measured 7d ago against content hash 6080cca599be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

adversarial-review-quick 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/adversarial-review/skills/adversarial-review-quick/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Review — Quick Panel

Overview

The same hostile review as the full adversarial-review skill, on an 8-reviewer panel instead of 18. Each reviewer runs as a fresh subagent that assumes the code is broken and tries to prove it, from one narrow angle. Because they are fresh, none of them inherit the main session's reasoning or the author's rationalizations — that is the whole point.

The panel is the two charters that check the design itself, plus the six bug-hunting angles that historically produced the most confirmed high- and medium-severity findings. The verifier and the fix validator are not cut — they are what makes the output trustworthy, and they cost two agents.

Claude: do not use dynamic workflows. That means more token consumption for no functional gain. Dispatch plain subagents in parallel.

Say what this panel does not cover

This is a narrower net, and the user must know which way it is narrow. Ten angles are not on this panel:

Not covered Escalate to the full adversarial-review when
Input Attacker, Authorization Attacker the change touches untrusted input, authentication, or permissions
Concurrency & State Saboteur the change touches shared state, locking, or parallelism
Failure Injection Adversary the change talks to networks, disks, databases, or third-party services that can fail mid-operation
Resource Exhaustion Adversary the change touches unbounded collections, loops over user data, or hot paths
Rollback & Change-Safety Adversary the change includes migrations, rollouts, or anything that must be reversible under pressure
Maintainability Cynic, Karpathy Minimalist the change is large, or you suspect scope creep
AI Anti-Slop Critic, Fact-Checker the code is AI-generated, or leans on claims about libraries, versions, or standards

If the change touches any of those, stop and ask before dispatching anyone. Use AskUserQuestion (multi-select): one option per missing angle the change actually touches — named for the risk, not the charter ("it calls services that can fail mid-operation", not "Failure Injection Adversary") — plus a "quick panel as-is" option. Do not ask about angles the change doesn't touch.

Read the full file on GitHub · 382 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. 7d ago First seen · 382 lines · 210 tokens per session scan A 6080cca599be

Subscribe to this mod's changes

adversarial-review-quick is a skill published in the GitHub repository patrickdappollonio/claude-plugins (8 stars, last pushed today), licensed MIT. It adds 210 tokens to every session and 8,404 once invoked, about $0.0011 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.