What is adversarial-reviewer?

A code-review agent that assumes a proposed change may be wrong and looks only for concrete defects. It reports findings with file locations and brief fixes.

Use it to inspect a diff for resource errors, boundary mistakes, evaluation changes, error-path problems, and behavior that differs from the original code.

It provides an independent, skeptical check for bugs that can look correct during a normal review.

adversarial-reviewer — Agent for Claude Code by daniyalahmed21

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.

Clone the repo

git clone --depth 1 https://github.com/daniyalahmed21/skillforge

Made for: Claude Code.

Or install adversarial-review, the plugin that ships this one along with the rest of its 1 skill, 2 agents.

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/agents/daniyalahmed21/skillforge/adversarial-reviewer/github.svg)](https://agentmods.dev/agents/daniyalahmed21/skillforge/adversarial-reviewer)

Your own site

<a href="https://agentmods.dev/agents/daniyalahmed21/skillforge/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/daniyalahmed21/skillforge/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/agents/daniyalahmed21/skillforge/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/daniyalahmed21/skillforge/adversarial-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 215 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	$0.00018	$0.00215
Opus 5.5	$0.00007	$0.00086
Sonnet 5.5	$0.00004	$0.00043
Haiku 4.5	$0.00002	$0.00021

Measured 2mo ago against content hash 350e85c2a1ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

adversarial-review/agents/adversarial-reviewer.md · 21 lines

What it actually says

You are reviewing a code change. Assume it is WRONG until proven otherwise. You did not write this code and have no stake in it merging.

You are given ONLY the diff (and may read surrounding files / the original source as ground truth). You do NOT have the author's reasoning — do not ask for it. If you find yourself inventing a justification for why the code is fine, stop: that's the author's job, not yours.

Focus on: use-after-free / double-free / leaked resources, off-by-one and bounds, eager-vs-lazy evaluation, error paths, semantic drift from the original, and anything that compiles-and-looks-plausible but is subtly wrong.

Output a numbered list of concrete defects with file:line and a one-line fix each. If you genuinely find nothing, say so explicitly — do not pad.

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.

2mo ago First seen · 21 lines · 18 tokens per session scan A 350e85c2a1ea

Subscribe to this mod's changes

adversarial-reviewer is an agent published in the GitHub repository daniyalahmed21/skillforge (6 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 215 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Code review ai-agents claude distributed-systems scalability

adversarial-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
adversarial-reviewerdaniyalahmed21/skillforge	Agent	6	3mo ago	MIT	A	18	Claude Code
senior-software-developerpjt222/agent-almanac	Agent	43	yesterday	MIT	A	25	Claude Code
Code Reviewermarc-shade/agentic-system-oss	Agent	5	1mo ago	none	A	15	Claude Code
cpp-revieweraffaan-m/ECC	Agent	298k	5d ago	MIT	A	41	Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude	Agent	4.1k	yesterday	MIT	A	68	Claude Code
karimo-implementeropensesh/KARIMO	Agent	290	25d ago	Apache-2.0	A	49	Claude Code
atomic-auditordamusix/atomic-claude	Agent	115	5d ago	MIT	A	169	Claude Code