adversarial-review

adversarial-review is a plugin for Claude Code from Emlembow/skills. Its manifest loads nothing; the 1 skill it bundles cost 101 tokens per session together, scanned A, original, MIT.

A workflow add-on that requires a task result to pass two consecutive independent adversarial reviews before it is considered complete. An adversarial review deliberately looks for flaws, omissions, or unsafe assumptions.

In plain words
What is it for?
Use it for work where independent scrutiny matters, such as reviewing implementation results, checking evidence, or testing whether a proposed solution withstands criticism.
Why use it?
It adds a repeatable challenge step so errors are more likely to be found before the result is accepted.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add Emlembow/skills
agentmods
npx agentmods add plugins/emlembow/skills/adversarial-review
Clone the repo
git clone --depth 1 https://github.com/Emlembow/skills

Made for: Claude Code.

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/plugins/emlembow/skills/adversarial-review.svg)](https://agentmods.dev/plugins/emlembow/skills/adversarial-review)
Your own site
<a href="https://agentmods.dev/plugins/emlembow/skills/adversarial-review"><img src="https://agentmods.dev/badge/plugins/emlembow/skills/adversarial-review.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 101 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
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 5d 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.

skills/adversarial-review/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "adversarial-review",
  "description": "Requires a task result to survive two consecutive independent adversarial reviews before completion.",
  "version": "1.0.1",
  "author": {
    "name": "Emlembow"
  },
  "repository": "https://github.com/Emlembow/skills",
  "license": "MIT"
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 101 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 5d ago First seen · 11 lines scan A fc6dadca54da

Subscribe to this mod's changes

adversarial-review is a plugin published in the GitHub repository Emlembow/skills (2 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories

adversarial-spec

Iteratively refine product specs through multi-model debate until consensus. Claude actively participates alongside GPT, Gemini, Grok, and other models. Includes interview mode, early agreement verification, and optional Telegram integration.

zscole/adversarial-spec · not measured

csrd

EU CSRD (Corporate Sustainability Reporting Directive, EU 2022/2464) compliance advisor — scope & threshold analysis (large PIEs, other large, listed SMEs, non-EU), double materiality assessment (DMA), ESRS gap assessment, ESRS E1–E5 environmental disclosures, ESRS S1–S4 social disclosures, ESRS G1 governance, Scope…

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance · not measured

eu-cra

Expert EU Cyber Resilience Act (CRA) advisor for Regulation (EU) 2024/2847. Covers product classification (Default/Class I/Class II), Annex I essential requirements gap analysis, conformity assessment (self-assessment vs Notified Body), CE marking, SBOM, vulnerability handling, 24/72-hour ENISA reporting, support…

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance · not measured

dora

DORA (Regulation (EU) 2022/2554) compliance advisor for EU financial entities — ICT risk management framework, incident classification and reporting, TLPT, ICT third-party risk, Register of Information, and all adopted RTS/ITS with article-level citations.

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance · not measured

fedramp

End-to-end FedRAMP authorization guidance under CR26 — Certification Classes A-D, FedRAMP 20x pathway, readiness assessments, SSP narratives, POA&M management, NIST 800-53 Rev 5 control mapping, OSCAL mandate, and ConMon support.

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance · not measured

ism

Expert Australian Information Security Manual (ISM) advisor for Australian government entities, contractors and supply chains. Gap analysis, system authorisation, IRAP preparation, control scoping, and ASD compliance guidance.

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance · not measured