adversarial-design

adversarial-design is a skill for Claude Code, Codex from XRenSiu/claude-code-forge. It costs 101 tokens per session (4,439 once invoked), scanned A, original, MIT.

A team-based architecture design process in which several architects propose solutions, a critic challenges them, and an arbiter combines the results. An architecture is the high-level structure and technical choices of a system.

In plain words
What is it for?
Use it for major system designs, high-risk architecture changes, or decisions that need a written Architecture Decision Record. It examines competing proposals and their trade-offs.
Why use it?
It reveals weaknesses in important design decisions before they are built, especially when several plausible solutions exist.

Skill for Claude CodeCodex

Part of the forge-teams plugin — 7 skills, 20 agents shipped together

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.

agentmods
npx agentmods add skills/xrensiu/claude-code-forge/adversarial-design
Any agent
npx skills add XRenSiu/claude-code-forge --skill adversarial-design
Clone the repo
git clone --depth 1 https://github.com/XRenSiu/claude-code-forge

Made for: Claude Code, Codex.

Or install forge-teams, the plugin that ships this one along with the rest of its 7 skills, 20 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.

agentmods badge for adversarial-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/adversarial-design.svg)](https://agentmods.dev/skills/xrensiu/claude-code-forge/adversarial-design)
Your own site
<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/adversarial-design"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/adversarial-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00101 $0.04439
Opus 5 $0.00051 $0.02219
Sonnet 5 $0.00020 $0.00888
Haiku 4.5 $0.00010 $0.00444

Measured 4d ago against content hash c9253c9781fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adversarial-design 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.

plugins/forge-teams/skills/adversarial-design/SKILL.md · 502 lines

How it starts

The opening of the file, as written. The whole thing — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Design

用多个架构师的竞争对抗替代单人设计的盲点。

实测数据:单人架构设计的关键缺陷遗漏率约 30-50%。对抗式设计通过竞争提案 + 专职批评 + 中立仲裁,将架构缺陷在设计阶段暴露率提升到 80%+。

Announce at start: "I'm using the adversarial-design skill to create an agent team where multiple architects compete and a critic challenges their designs."

前置条件:

  1. PRD 文档已就绪(Phase 1 产出)
  2. 需要启用 Agent Teams 实验性功能。 在 settings.json 中添加: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }

When to Use

digraph {
    rankdir=TB;
    start [label="需要系统设计" shape=oval];
    q1 [label="设计复杂度\n高?" shape=diamond];
    q2 [label="多个可行\n方案?" shape=diamond];
    q3 [label="需要严格\n论证?" shape=diamond];
    single [label="单人设计" shape=box];
    adversarial [label="adversarial-design\n(本 Skill)" shape=box style=filled fillcolor=lightgreen];
    simple [label="直接实现" shape=box];

    start -> q1;
    q1 -> simple [label="低"];
    q1 -> q2 [label="高"];
    q2 -> single [label="否"];
    q2 -> q3 [label="是"];
    q3 -> adversarial [label="是"];
    q3 -> single [label="否\n(但建议用)"];
}

The 5-Phase Protocol

┌──────────────────────────────────────────────────────────────────────┐
│                      ADVERSARIAL DESIGN                              │
├──────────────────────────────────────────────────────────────────────┤
│                                                                      │
│  Phase 0: INTAKE               读取 PRD,理解需求和约束              │
│           ↓                                                          │
│                                                                      │
│  Phase 1: TEAM ASSEMBLY        创建 Agent Team                       │
│           ↓                    2 × solution-architect                │
│                                1 × technical-critic                  │
│                                1 × design-arbiter                   │
│                                                                      │
│  Phase 2: INDEPENDENT DESIGN   架构师独立设计 (并行)                 │
│           ↓                    不交流,各自产出完整方案               │
│                                                                      │
│  Phase 3: ADVERSARIAL DEBATE   2-3 轮对抗辩论                        │
│           ↓                    展示 → 挑战 → 回应 → 迭代             │
│                                                                      │
│  Phase 4: ARBITRATION          仲裁者评分裁决                         │
│                                获胜方案 + 合并改进 + 淘汰记录        │
│                                                                      │
└──────────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 502 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. 4d ago First seen · 502 lines · 101 tokens per session scan A c9253c9781fa

Subscribe to this mod's changes

adversarial-design is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 4,439 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens