Borrowing it
Nothing to install: this file belongs to QuantitativeX/shanghai-social-security-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/QuantitativeX/shanghai-social-security-agent/main/.claude/commands/prd-supplement.mdgit clone --depth 1 https://github.com/QuantitativeX/shanghai-social-security-agentWrote 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/commands/quantitativex/shanghai-social-security-agent/prd-supplement)<a href="https://agentmods.dev/commands/quantitativex/shanghai-social-security-agent/prd-supplement"><img src="https://agentmods.dev/badge/commands/quantitativex/shanghai-social-security-agent/prd-supplement.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 5.1 | $0.00049 | $0.01250 |
| Opus 5 | $0.00024 | $0.00625 |
| Sonnet 5 | $0.00010 | $0.00250 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
prd-supplement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD 文档章节补充
任务目标
根据用户提供的原型图截图，在已有 PRD Word 文档的指定章节内，补充完整的界面要素说明（查询条件、列表、详情、操作四类），并将结果输出为新文件（原文件名 + _new）。
用户额外说明的补充目标：$ARGUMENTS
Step 0 — 确认输入
检查用户是否提供了以下内容，缺少任何一项时停下来询问，不要假设或自行填充：
| 需要的输入 | 说明 |
|---|---|
| PRD Word 文件路径 | 已有的 .docx 文件，补充内容将写入此文件的副本 |
| 原型图文件或截图 | 可以是图片文件路径，也可以是用户直接粘贴的图片 |
| 要补充的章节位置 | 章节名称或编号，例如"3.2 查询列表页"；若未提供则从 $ARGUMENTS 推断，仍不明确时询问 |
确认完毕后，向用户回显：
✅ 输入确认：
PRD 文件：<路径>
原型图：<路径或"已收到截图">
补充章节：<章节名>
额外说明：<$ARGUMENTS 或"无">
Step 1 — 解析原型图
仔细分析原型图中的每一个 UI 元素，按以下四类分组：
- 查询条件区：页面顶部的筛选表单字段（下拉、日期范围、输入框等）
- 查询列表区：表格/列表中展示的数据列
- 详情界面：点击某行后展开或跳转的详情页字段
- 操作说明：按钮、操作项（如"导出"、"审批"、"删除"）
识别规则：
- 下划线字段 = 超链接，备注中注明"点击后跳转至对应功能页面"
- 身份证号、姓名、手机号、银行卡号 等敏感字段 = "是否脱敏展示"列填写是
- 严格按原型图中已有字段定义，不添加原型图中不存在的字段
Step 2 — 复制 PRD 文件
使用 Python 脚本（无需 pandoc / Node.js）复制原始文件：
import shutil, pathlib
src = pathlib.Path("<PRD文件路径>")
dst = src.with_stem(src.stem + "_new")
shutil.copy2(src, dst)
print(f"已生成副本：{dst}")
注意：操作副本，不修改原文件；不要压缩成 zip。
Step 3 — 定位目标章节并写入内容
使用 python-docx 库（pip install python-docx）定位用户指定的章节，在其后追加以下四张表格。
表格格式规范
字体要求（需与原始文档保持一致）：
- 标题：黑体
- 二级标题：楷体
- 正文：Arial
- 表格表头：加粗 + 浅蓝色背景（RGB: 189, 215, 238）
表 1：查询条件要素
| 要素名称 | 输入方式 | 是否必填 | 备注说明 |
|---|---|---|---|
| （示例）申请日期 | 日期范围选择器 | 否 | 默认当月 |
表 2：查询列表要素
| 要素名称 | 显示格式 | 是否脱敏展示 | 备注说明 |
|---|---|---|---|
| （示例）姓名 | 文本 | 是 | 显示为张** |
表 3：详情界面要素
| 要素名称 | 输入方式/显示格式 | 是否脱敏展示 | 备注说明 |
|---|---|---|---|
| （示例）身份证号 | 只读文本 | 是 | 显示为 310********1234 |
表 4：操作说明要素
| 操作按钮 | 备注说明 |
|---|---|
| （示例）导出 | 导出当前查询结果为 Excel |
Step 4 — 输出确认
完成后告知用户：
✅ 已生成：<_new 文件的绝对路径>
补充了以下章节内容：
- 查询条件要素（X 项）
- 查询列表要素（X 项）
- 详情界面要素（X 项）
- 操作说明要素（X 项）
Constraints（硬性约束，不得违反）
- ❌ 不修改
_new文件中除目标章节之外的任何已有内容 - ❌ 不在表格中添加原型图中没有明确显示的字段
- ❌ 不使用 pandoc、Node.js 或任何需要额外安装大型工具的方案
- ❌ 不压缩输出文件（不生成 .zip）
- ✅ 所有脚本用 Python 实现；若
python-docx未安装，先运行pip install python-docx - ✅ 超链接字段在备注中注明跳转行为
- ✅ 敏感字段（身份证、姓名、手机号、银行卡等）的"是否脱敏展示"列统一填写是
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.
- 7d ago First seen · 130 lines · 49 tokens per session scan A 86577a468b50
prd-supplement is a command published in the GitHub repository QuantitativeX/shanghai-social-security-agent (5 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 1,250 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.
Other commands, from other repositories
latex-posters
Create a large-format academic poster in LaTeX using beamerposter, tikzposter, or baposter. Use when the requested deliverable is a conference or research poster rather than sequential presentation slides. For slide decks, use $beamer-deck.
brand-extract
Extract a Brand Profile from an Office template.
report
Generate a publication-grade HTML report from a markdown source using the TRAID Design System catalog (5 templates). Agy matches content to template, you confirm, agy produces final branded HTML.
maket
Design a visual document with Maket.
print-export-designer
Use when something has to leave the screen. PDF generation, print stylesheets, receipts and invoices, exported reports, or a download that gives the user no feedback.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.