fg-adversarial-review

fg-adversarial-review is a skill for Claude Code from gyuha/forge. It costs 129 tokens per session (3,911 once invoked), scanned A, original, no licence file.

An optional review step in the Forge workflow where reviewers assume the result is wrong and look for evidence of problems.

In plain words
What is it for?
Use it to challenge results from `fg-run` and `fg-learn` and identify findings that may need fixes.
Why use it?
It can expose failures, hidden assumptions, misunderstood requirements, security or performance risks, data loss, misuse, and weak decisions before work is accepted.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the forge plugin — 23 skills, 3 agents, 2 hooks shipped together

Good fit Use it to challenge results from fg-run and fg-learn and identify findings that may need fixes.

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

Made for: Claude Code.

Or install forge, the plugin that ships this one along with the rest of its 23 skills, 3 agents, 2 hooks.

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 fg-adversarial-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/gyuha/forge/fg-adversarial-review/github.svg)](https://agentmods.dev/skills/gyuha/forge/fg-adversarial-review)
Your own site
<a href="https://agentmods.dev/skills/gyuha/forge/fg-adversarial-review"><img src="https://agentmods.dev/badge/skills/gyuha/forge/fg-adversarial-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.

agentmods 80×15 button for fg-adversarial-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/gyuha/forge/fg-adversarial-review"><img src="https://agentmods.dev/badge/skills/gyuha/forge/fg-adversarial-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 3,911 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 unknown 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 $0.00129 $0.03911
Opus 5 $0.00064 $0.01956
Sonnet 5 $0.00026 $0.00782
Haiku 4.5 $0.00013 $0.00391

Measured 4d ago against content hash f535a01e985b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fg-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 4d 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/fg-adversarial-review/SKILL.md · 132 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 4d ago Changed f535a01e985b
  2. 5d ago Changed afbb7f597109
  3. 7d ago Changed · +2 lines e6742220f8fe
  4. 10d ago First seen · 130 lines · 129 tokens per session scan A 2c883226d381

Subscribe to this mod's changes

fg-adversarial-review is a skill published in the GitHub repository gyuha/forge (4 stars, last pushed yesterday), with no licence file. It adds 129 tokens to every session and 3,911 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 2026-08-31.