adversarial-reviewer

adversarial-reviewer is a skill for Codex from bestagentkits/agency-skills. It costs 69 tokens per session (2,675 once invoked), scanned A, original, MIT.

A code-review process that examines changes through three deliberately critical viewpoints: production failure, maintainability, and security.

In plain words
What is it for?
Use it to review staged changes, recent commits, a branch difference, or a specific file before merging.
Why use it?
It is designed to find problems that a familiar author or reviewer may overlook, and to give clear guidance about whether changes should merge.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions CLAUDE.md.

Good fit Use it to review staged changes, recent commits, a branch difference, or a specific file before merging.

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

Made for: 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/bestagentkits/agency-skills/adversarial-reviewer/github.svg)](https://agentmods.dev/skills/bestagentkits/agency-skills/adversarial-reviewer)
Your own site
<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/adversarial-reviewer"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-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/bestagentkits/agency-skills/adversarial-reviewer"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/adversarial-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,675 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 $0.00069 $0.02675
Opus 5 $0.00034 $0.01337
Sonnet 5 $0.00014 $0.00535
Haiku 4.5 $0.00007 $0.00267

Measured 12d ago against content hash 391c6565078c, 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 12d 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/claude-skills/adversarial-reviewer/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Code Reviewer

Description

Adversarial code review skill that forces genuine perspective shifts through three hostile reviewer personas (Saboteur, New Hire, Security Auditor). Each persona MUST find at least one issue — no "LGTM" escapes. Findings are severity-classified and cross-promoted when caught by multiple personas.

Features

  • Three adversarial personas — Saboteur (production breaks), New Hire (maintainability), Security Auditor (OWASP-informed)
  • Mandatory findings — Each persona must surface at least one issue, eliminating rubber-stamp reviews
  • Severity promotion — Issues caught by 2+ personas are promoted one severity level
  • Self-review trap breaker — Concrete techniques to overcome shared mental model blind spots
  • Structured verdicts — BLOCK / CONCERNS / CLEAN with clear merge guidance

Usage

/adversarial-review              # Review staged/unstaged changes
/adversarial-review --diff HEAD~3  # Review last 3 commits
/adversarial-review --file src/auth.ts  # Review a specific file

Examples

Example: Reviewing a PR Before Merge

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

Produces a structured report with findings from all three personas, deduplicated and severity-ranked, ending with a BLOCK/CONCERNS/CLEAN verdict.

Problem This Solves

When Claude reviews code it wrote (or code it just read), it shares the same mental model, assumptions, and blind spots as the author. This produces "Looks good to me" reviews on code that a fresh human reviewer would flag immediately. Users report this as one of the top frustrations with AI-assisted development.

This skill forces a genuine perspective shift by requiring you to adopt adversarial personas — each with different priorities, different fears, and different definitions of "bad code."

Table of Contents

  1. Quick Start
  2. Review Workflow
  3. The Three Personas
  4. Severity Classification
  5. Output Format
  6. Anti-Patterns
  7. When to Use This

Read the full file on GitHub · 248 lines

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. 12d ago First seen · 248 lines · 69 tokens per session scan A 391c6565078c

Subscribe to this mod's changes

adversarial-reviewer is a skill published in the GitHub repository bestagentkits/agency-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 2,675 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

vanity-engineering-review

Reviews codebases, architectures, PRs, and technical plans for vanity engineering — code and systems built for the developer's ego, resume, or intellectual pleasure rather than delivering user or business value. Triggers on: "review this code", "is this over-engineered", "code review", "architecture review"…

bencium/bencium-marketplace · 181 tokens

argumentation

Construct well-structured arguments using the hypothesis-argument-example triad. Covers formulating falsifiable hypotheses, building logical arguments (deductive, inductive, analogical, evidential), providing concrete examples, and steelmanning counterarguments. Use when writing or reviewing PR descriptions that…

pjt222/agent-almanac · 86 tokens

cross-review-project

Conduct a structured cross-project code review between two Claude Code instances via the cross-review-mcp broker. Each agent reads its own codebase, reviews the peer's code, and engages in evidence-backed dialogue — with QSG scaling laws enforcing review quality through minimum bandwidth constraints and phase-gated…

pjt222/agent-almanac · 63 tokens

create-pull-request

Create and manage pull requests using GitHub CLI. Covers branch preparation, writing PR titles and descriptions, creating PRs, handling review feedback, and merge/cleanup workflows. Use when proposing changes from a feature or fix branch for review, merging completed work into the main branch, requesting code review…

pjt222/agent-almanac · 78 tokens

audit-pr

Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".

gtrabanco/agentic-workflow · 71 tokens

fold-findings

Repair persisted fix-now findings in compatible atomic batches: root-cause fixes, green gate, commit/push, and per-row folded: yes updates. Never reclassify or substitute backlog notes. Triggers: "fold-findings", "fix the review findings", "repair audit blockers".

gtrabanco/agentic-workflow · 65 tokens