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.
npx agentmods add skills/xrensiu/claude-code-forge/adversarial-designnpx skills add XRenSiu/claude-code-forge --skill adversarial-designgit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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.
[](https://agentmods.dev/skills/xrensiu/claude-code-forge/adversarial-design)<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>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 | $0.00101 | $0.04439 |
| Opus 5 | $0.00051 | $0.02219 |
| Sonnet 5 | $0.00020 | $0.00888 |
| Haiku 4.5 | $0.00010 | $0.00444 |
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.
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:
- PRD 文档已就绪(Phase 1 产出)
- 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 │
│ │
└──────────────────────────────────────────────────────────────────────┘
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.
- 4d ago First seen · 502 lines · 101 tokens per session scan A c9253c9781fa
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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.
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…