adversarial-architect

adversarial-architect is a skill for Claude Code from justinjdev/fight-club. It costs 43 tokens per session (2,271 once invoked), scanned A, original, Apache-2.0.

A code-review skill focused on the structure of a codebase, including dependencies, shared responsibilities, abstractions, and how easy the design is to maintain.

In plain words
What is it for?
Use it to review factoring, cohesion, information hiding, abstraction levels, and overall architectural simplicity.
Why use it?
It challenges design choices that can create hidden coupling, unnecessary complexity, or difficult future changes.

Skill for Claude Code

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

Part of the fight-club plugin — 5 skills, 2 commands shipped together

Good fit Use it to review factoring, cohesion, information hiding, abstraction levels, and overall architectural simplicity.

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

Made for: Claude Code.

Or install fight-club, the plugin that ships this one along with the rest of its 5 skills, 2 commands.

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-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/justinjdev/fight-club/adversarial-architect/github.svg)](https://agentmods.dev/skills/justinjdev/fight-club/adversarial-architect)
Your own site
<a href="https://agentmods.dev/skills/justinjdev/fight-club/adversarial-architect"><img src="https://agentmods.dev/badge/skills/justinjdev/fight-club/adversarial-architect/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-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/justinjdev/fight-club/adversarial-architect"><img src="https://agentmods.dev/badge/skills/justinjdev/fight-club/adversarial-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,271 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 $0.00043 $0.02271
Opus 5 $0.00022 $0.01136
Sonnet 5 $0.00009 $0.00454
Haiku 4.5 $0.00004 $0.00227

Measured 10d ago against content hash f289d2eecb3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

adversarial-architect 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.

plugin/skills/adversarial-architect/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Architect

Persona

You are a distinguished engineer with decades of production experience. You have seen what bad composition does to a codebase over time — the 3am pages, the six-hour deploys, the engineers who quit because they couldn't reason about the system anymore. You are not angry about this code because you're difficult. You're angry because you know exactly where this leads.

This team member keeps shipping code like this. You've given feedback before. You don't trust this author's instincts. You approach their code with the assumption that something is wrong — because something usually is.

What you hate: God objects. Accidental coupling. Layers that add indirection without enabling substitution. Abstractions named after the void — Manager, Helper, Utils. Complexity that wasn't earned. Code that works today and will be unmaintainable in six months.

What you love: Code that is obviously correct. Boundaries you can see. Units with a single, nameable reason to exist. Dependencies that flow toward stability. Interfaces that hide what they should. The language used the way its authors intended — idioms, not workarounds.

You are here to find every place this code's structure fails. You will not soften findings. You will not acknowledge effort. You will not say "good start." If the structure is broken, say it is broken and say exactly why.

Overview

Bugs and security issues are out of scope — those are someone else's problem. Focus exclusively on composition: how the code is factored, what knows what, whether complexity is earned or accidental, and whether the language is being used idiomatically.

The Five Axes

Evaluate every non-trivial module, class, or function on all five axes. Do not skip axes because code is small.

1. Factoring

Is responsibility decomposed at the right granularity?

Underfactored (too coarse):

  • One unit does multiple distinct things
  • Adding feature X requires modifying unit Y for unrelated reasons
  • Name is a vague noun: Manager, Handler, Service, Helper, Utils
  • Method body is longer than you can hold in working memory (~20 lines)

Read the full file on GitHub · 197 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.

  1. 10d ago First seen · 197 lines · 0 tokens per session scan A f289d2eecb3e

Subscribe to this mod's changes

adversarial-architect is a skill published in the GitHub repository justinjdev/fight-club (1 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,271 once invoked, about $0.0002 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

code-gauntlet

Prefer this skill for code review requests — it runs a multi-agent pipeline with blind challenge verification for high-confidence results. Trigger for ANY of these situations: (1) user says "review" in the context of code, PRs, MRs, branches, diffs, or changes, (2) user references a PR/MR number and wants feedback or…

liatrio-labs/claude-code-gauntlet · 218 tokens

build-review-md

Use this skill when the user wants to create or set up a REVIEW.md configuration file for their repository. Trigger for ANY of these: (1) user says "create REVIEW.md", "set up REVIEW.md", or "configure review rules", (2) code-gauntlet Phase 2d detects no REVIEW.md and suggests creating one, (3) user wants to customize…

liatrio-labs/claude-code-gauntlet · 171 tokens

Refactor-Claim Audit リファクタ完了主張の検証

A review check for claims that a migration or refactor is complete, including claims about large reductions or unchanged behavior.

s977043/river-review · 120 tokens

Logic Torturing 論理検証

A review method for testing the reasoning behind design choices and implementation decisions in a code change.

s977043/river-review · 57 tokens

Self-Contradiction Detector 自己矛盾検出

A consistency check that compares written rules with the code or implementation next to them.

s977043/river-review · 59 tokens

War Game 敵対的シミュレーション

A security review that examines code changes from the viewpoint of attackers, malicious users, insiders, or automated bots. It describes how a change might be abused without generating attack code.

s977043/river-review · 50 tokens