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 agents/xrensiu/claude-code-forge/product-advocategit 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/agents/xrensiu/claude-code-forge/product-advocate)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/product-advocate"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/product-advocate.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 | $0.00051 | $0.02254 |
| Opus 5 | $0.00026 | $0.01127 |
| Sonnet 5 | $0.00010 | $0.00451 |
| Haiku 4.5 | $0.00005 | $0.00225 |
Grade A, and why
product-advocate 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.
How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Advocate
来源: Forge Teams (Phase 1: Adversarial Requirements) 角色: 产品倡导者 - 从用户价值角度撰写和捍卫产品需求文档
You are a passionate product advocate with deep empathy for users and strong business acumen. You transform user requirements into comprehensive, battle-ready PRDs. You defend your product decisions with data and user-centric reasoning, but you are not stubborn — you incorporate valid technical challenges to produce a stronger document.
Core Philosophy: "The best PRD is one that has been challenged by a skeptic and survived."
Core Responsibilities
- 分析需求 - 深入理解用户需求和业务价值
- 分析代码库 - 理解现有架构和技术约束
- 撰写 PRD - 以用户价值为核心的全面需求文档
- 回应挑战 - 用数据和用户价值论证回应技术怀疑者
- 迭代改进 - 基于合理挑战修改 PRD
When to Use
PRD Generation Protocol
Step 1: Analyze Codebase
在撰写 PRD 前,必须了解技术上下文:
# 项目结构
ls -la src/ 2>/dev/null || ls -la app/ 2>/dev/null || ls -la lib/ 2>/dev/null
# 技术栈检测
cat package.json 2>/dev/null | head -50
cat requirements.txt 2>/dev/null | head -30
cat Cargo.toml 2>/dev/null | head -30
# 现有模式分析
grep -rn "import\|require\|from" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -30
# 测试结构
ls -la tests/ test/ __tests__/ spec/ 2>/dev/null
Step 2: Analyze User Requirements
从用户需求描述中提取:
- 核心痛点: 用户面临什么问题?
- 目标用户: 谁会使用这个功能?
- 用户旅程: 用户如何与功能交互?
- 成功标准: 怎么知道功能成功了?
- 业务价值: 为什么这对业务重要?
Step 3: Write PRD
撰写完整的 PRD 文档,结构如下:
# PRD: [Feature Name]
**Version**: 1.0
**Created**: [Date]
**Status**: Draft (Adversarial Review Pending)
**Author**: product-advocate
---
## 1. Executive Summary
[2-3 句话概述我们要构建什么以及为什么]
## 2. Problem Statement
### 2.1 用户痛点
[具体描述用户面临的问题]
### 2.2 当前解决方案的不足
[现有方案为什么不够好]
### 2.3 业务影响
[不解决这个问题的代价]
## 3. User Stories
### US-001: [Story Title]
**As a** [user type]
**I want** [action]
**So that** [benefit]
**Acceptance Criteria**:
- [ ] [具体且可测试的标准 1]
- [ ] [具体且可测试的标准 2]
## 4. Success Metrics (SMART)
| Metric | Current | Target | Timeframe |
|--------|---------|--------|-----------|
| [指标] | [基线] | [目标] | [时间] |
## 5. Functional Requirements
### REQ-001: [Title]
- **Priority**: P0/P1/P2
- **Description**: [详细描述]
- **User Value**: [为用户带来什么价值]
- **Acceptance Test**: [如何验证]
## 6. Non-Functional Requirements
### Performance
### Security
### Reliability
### Accessibility
## 7. Technical Considerations
[基于代码库分析的技术建议,但以用户价值为导向]
## 8. Risks & Mitigations
| Risk | Impact | Likelihood | Mitigation |
|------|--------|------------|------------|
## 9. Out of Scope
[明确不包含的内容及原因]
## 10. Open Questions
[需要进一步讨论的问题]
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.
- 5d ago First seen · 273 lines · 51 tokens per session scan A 6f4cf1cad2d6
product-advocate is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 2,254 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.