What is adverse-review?

A code-review process that asks three different reviewer roles—an auditor, an adversary, and a pragmatist—to examine the same change, question one another, and produce one ranked report.

It is intended for substantial pull requests, security-sensitive changes, broad refactors, or code about to be merged or shipped.

It exposes security risks, correctness problems, and practical concerns that a single review perspective might miss.

adverse-review — Skill for Codex by addyosmani

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 addyosmani/adverse --skill adverse-review

Clone the repo

git clone --depth 1 https://github.com/addyosmani/adverse

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/addyosmani/adverse/adverse-review/github.svg)](https://agentmods.dev/skills/addyosmani/adverse/adverse-review)

Your own site

<a href="https://agentmods.dev/skills/addyosmani/adverse/adverse-review"><img src="https://agentmods.dev/badge/skills/addyosmani/adverse/adverse-review/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/addyosmani/adverse/adverse-review"><img src="https://agentmods.dev/badge/skills/addyosmani/adverse/adverse-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,151 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	$0.00129	$0.02151
Opus 5	$0.00064	$0.01076
Sonnet 5	$0.00026	$0.00430
Haiku 4.5	$0.00013	$0.00215

Measured 10d ago against content hash 6ed9907252c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

adverse-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 10d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/collect.mjs, scripts/combine.mjs, scripts/dump-prompts.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/adverse-review/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adverse — Multi-Agent Adversarial Code Review

This skill is the Claude Code-native side of the adverse project. The same logic is also available as a standalone CLI (adverse review …). When you run inside Claude Code, prefer this skill — it uses Claude Code's native Agent tool to spawn reviewers (no subprocess auth issues, faster) and calls Node helpers only for the deterministic source-collection and synthesis steps.

When to use this skill

The user explicitly asked for an adversarial / multi-perspective / panel review of their code, OR they're about to merge / land / ship a non-trivial change and asked for one more pass. If the diff is trivially mechanical (formatting, dependency bumps, typos), do NOT invoke this — say so and stop.

Prerequisites

node (>= 20) on PATH. Verify with node --version. The skill scripts live under ${SKILL_DIR}/scripts/ and are stdlib-only (no npm install needed).

If node is missing, tell the user: install Node 20+ from nodejs.org (or their package manager) and re-invoke. Do not fall back to a different implementation; the deterministic synthesizer is the contract.

Phase 0 — decide what to review

Pick scope before spending tokens:

If the user named a path, that's the scope.
Else if git status --porcelain reports uncommitted changes, review those (diff mode against HEAD).
Else if the current branch is ahead of main (or master / the configured upstream), review the diff since the merge base.
Else review the whole working directory.

State the scope you picked in one sentence so the user can redirect.

Phase 1 — collect source

Run the Node helper that walks the target and produces a single prompt-ready text block:

node ${SKILL_DIR}/scripts/collect.mjs --target <path> [--diff [base]] --out /tmp/adverse-source.txt --files-out /tmp/adverse-files.json

/tmp/adverse-source.txt is what you'll embed in the reviewer prompts. /tmp/adverse-files.json is the file list (use it to confirm scope to the user). The helper enforces the same source-size caps as the CLI.

Read the full file on GitHub · 217 lines

Files

What ships with it

9 files 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.

10d ago First seen · 217 lines · 129 tokens per session scan A 6ed9907252c4

Subscribe to this mod's changes

adverse-review is a skill published in the GitHub repository addyosmani/adverse (55 stars, last pushed 2mo ago), licensed MIT. It adds 129 tokens to every session and 2,151 once invoked, about $0.0006 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.

Code review

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens