What is adversarial-reviewer?

A deliberately critical code review using three viewpoints: someone trying to break the system, a new developer checking clarity, and a security reviewer checking common risks.

Use it before merging a pull request, after a sprint, or when checking for production failures, confusing code, input-validation issues, injection risks, leaked secrets, and dependency problems.

It exposes assumptions and blind spots that can make a self-review too agreeable.

adversarial-reviewer — Skill for Claude Code and Codex by tmj-90

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 tmj-90/gaffer --skill adversarial-reviewer

Clone the repo

git clone --depth 1 https://github.com/tmj-90/gaffer

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tmj-90/gaffer/adversarial-reviewer/github.svg)](https://agentmods.dev/skills/tmj-90/gaffer/adversarial-reviewer)

Your own site

<a href="https://agentmods.dev/skills/tmj-90/gaffer/adversarial-reviewer"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tmj-90/gaffer/adversarial-reviewer"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/adversarial-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 971 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.

Model	Per session	Once invoked
Fable 5.1	$0.00093	$0.00971
Opus 5	$0.00046	$0.00485
Sonnet 5	$0.00019	$0.00194
Haiku 4.5	$0.00009	$0.00097

Measured 10d ago against content hash b40ca88ad667, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

runner/skills/adversarial-reviewer/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Break the self-review monoculture

When an agent reviews code it just wrote, it shares the author's assumptions and blind spots. This produces "Looks good to me" on code a fresh reviewer would flag immediately. Three hostile personas; each must find at least one issue.

The three personas

Saboteur — wants to break this in production. Asks: what input crashes this? What race condition emerges under load? What happens when a dependency is down? What deploy order causes data corruption?

New Hire — joined last week. Asks: what does this variable name actually mean? Why was this chosen over the obvious alternative? Where does this function get called? Could I maintain this at 2 AM?

Security Auditor — OWASP Top 10 + supply chain. Asks: where is user input validated? Where could injection occur? What happens if this secret leaks? Are dependencies pinned and scanned?

Severity classification

Level	Meaning	Action
BLOCK	Production break, data loss, security vulnerability	Must fix before merge
CONCERN	Quality, maintainability, or performance issue	Should fix before merge
NOTE	Suggestion, style, minor smell	Optional; document if skipping

Severity promotion: a finding caught by 2+ personas is promoted one level (CONCERN → BLOCK; NOTE → CONCERN). Cross-persona findings reveal a systemic blind spot.

Steps

Read the diff. git diff against the merge target. If the diff is large, read the most critical files first: auth, payments, data mutations, API boundaries.
Adopt the Saboteur. Look for: unhandled error paths, race conditions, wrong assumptions about input range, missing retries, state corruption, resource leaks. The Saboteur must find at least one finding.
Adopt the New Hire. Look for: unclear names, missing context, surprising behaviour, missing tests, no docstring on a complex function, a choice that needs explanation. The New Hire must find at least one finding.
Adopt the Security Auditor. Look for: unvalidated input, SQL/command injection, hardcoded secrets, insecure defaults, over-permissive access, dependency risks. The Auditor must find at least one finding.
Deduplicate and promote. Merge findings; promote cross-persona findings one severity level.
Emit the verdict. BLOCK (any BLOCK finding) / CONCERNS (CONCERN only) / CLEAN (notes only). Include the evidence: file, line, description, and suggested fix for every BLOCK/CONCERN.

Read the full file on GitHub · 70 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.

10d ago First seen · 70 lines · 93 tokens per session scan A b40ca88ad667

Subscribe to this mod's changes

adversarial-reviewer is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 93 tokens to every session and 971 once invoked, about $0.0005 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.

Autonomous Agents Code review Security ai-agents ai-coding-assistant ai-governance anthropic claude

test-audit

Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.

QBall-Inc/the-bulwark · 0 tokens

code-review

Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.

QBall-Inc/the-bulwark · 61 tokens

adversarial-reviewer