adversarial-requirements

adversarial-requirements is a skill for Claude Code from XRenSiu/claude-code-forge. It costs 116 tokens per session (3,744 once invoked), scanned A, original, MIT.

A requirements-writing process in which a product-focused agent and a technically skeptical agent debate a proposed feature for two rounds. It produces a requirements document after checking both the desired outcome and the codebase's technical limits.

In plain words
What is it for?
Use it for complex new features, detailed product requirements documents, and requests that need evidence-based technical feasibility checks.
Why use it?
It exposes unclear requirements and feasibility problems before implementation begins. The process requires Claude Code's experimental Agent Teams feature to be enabled.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

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

Made for: Claude Code.

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-requirements

README.md
[![agentmods](https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/adversarial-requirements.svg)](https://agentmods.dev/skills/xrensiu/claude-code-forge/adversarial-requirements)
Your own site
<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/adversarial-requirements"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/adversarial-requirements.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,744 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 5.1 $0.00116 $0.03744
Opus 5 $0.00058 $0.01872
Sonnet 5 $0.00023 $0.00749
Haiku 4.5 $0.00012 $0.00374

Measured 5d ago against content hash a2294ee2ed68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

adversarial-requirements 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 5d 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-requirements/SKILL.md · 456 lines

How it starts

The opening of the file, as written. The whole thing — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Requirements

用两个 agent 的对抗辩论替代单人闭门造车的需求文档。

实测数据:单人撰写的 PRD 平均有 3-5 个技术可行性盲点。对抗式需求通过产品倡导者 + 技术怀疑者的结构化辩论,将需求文档的技术可行性问题提前暴露,减少 60%+ 的实现阶段返工。

Announce at start: "I'm using the adversarial-requirements skill to create a battle-tested PRD through product-technical debate."

前置条件: 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="新功能需求" shape=oval];
    q1 [label="需求复杂度?" shape=diamond];
    q2 [label="技术风险?" shape=diamond];
    simple_prd [label="单 agent PRD\n(常规流程)" shape=box];
    adversarial [label="adversarial-requirements\n(本 Skill)" shape=box style=filled fillcolor=lightgreen];

    start -> q1;
    q1 -> simple_prd [label="低\n明确的需求"];
    q1 -> q2 [label="中/高"];
    q2 -> simple_prd [label="低"];
    q2 -> adversarial [label="中/高"];
}

The 7-Step Protocol

┌─────────────────────────────────────────────────────────────────┐
│                   ADVERSARIAL REQUIREMENTS                       │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  Step 1: INTAKE             收集用户需求描述                       │
│          ↓                                                       │
│                                                                  │
│  Step 2: TEAM CREATE        创建 Agent Team                      │
│          ↓                  Product Advocate + Technical Skeptic  │
│                                                                  │
│  Step 3: ADVOCATE DRAFT     产品倡导者分析代码库 + 撰写 PRD 草案   │
│          ↓                                                       │
│                                                                  │
│  Step 4: SKEPTIC CHALLENGE  技术怀疑者分析代码库 + 挑战 PRD        │
│          ↓                                                       │
│                                                                  │
│  Step 5: DEBATE             倡导者回应 + 怀疑者再挑战 (2 轮)       │
│          ↓                                                       │
│                                                                  │
│  Step 6: SYNTHESIS          Lead 综合产出 battle-tested PRD       │
│          ↓                                                       │
│                                                                  │
│  Step 7: CLEANUP            Shutdown Team + 输出最终文档           │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 456 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. 5d ago First seen · 456 lines · 116 tokens per session scan A a2294ee2ed68

Subscribe to this mod's changes

adversarial-requirements is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 3,744 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.

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

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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens