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 commands/yezannnnn/agentgroup/specgit clone --depth 1 https://github.com/yezannnnn/agentGroupWrote 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/yezannnnn/agentgroup/spec)<a href="https://agentmods.dev/commands/yezannnnn/agentgroup/spec"><img src="https://agentmods.dev/badge/commands/yezannnnn/agentgroup/spec.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 | $0.00000 | $0.01251 |
| Opus 5 | $0.00000 | $0.00626 |
| Sonnet 5 | $0.00000 | $0.00250 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
spec 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec - 设计规范
输出完整的设计规范文档
使用方式
/spec # 输出当前项目设计规范
/spec create # 创建新的设计规范
/spec update # 更新现有规范
设计规范模板
# 设计规范 - [项目名称]
## 基础信息
设计师: 艾拉
创建日期: YYYY-MM-DD
更新日期: YYYY-MM-DD
---
## 1. 颜色系统
### 品牌色
| 名称 | 色值 | 使用场景 |
|------|------|----------|
| 主色 | #1890FF | 按钮、链接、强调 |
| 主色-浅 | #E6F7FF | 选中背景、提示背景 |
| 主色-深 | #096DD9 | 按钮hover |
### 中性色
| 名称 | 色值 | 使用场景 |
|------|------|----------|
| 标题 | #262626 | 一级标题 |
| 正文 | #595959 | 正文内容 |
| 辅助 | #8C8C8C | 辅助文字 |
| 禁用 | #BFBFBF | 禁用状态 |
| 边框 | #D9D9D9 | 边框、分割线 |
| 背景 | #F5F5F5 | 页面背景 |
| 白色 | #FFFFFF | 卡片背景 |
### 功能色
| 名称 | 色值 | 使用场景 |
|------|------|----------|
| 成功 | #52C41A | 成功状态 |
| 警告 | #FAAD14 | 警告提示 |
| 错误 | #FF4D4F | 错误状态 |
| 信息 | #1890FF | 信息提示 |
---
## 2. 字体系统
### 字体族
```css
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI',
Roboto, 'Helvetica Neue', Arial, sans-serif;
字号层级
| 层级 | 字号 | 字重 | 行高 | 使用场景 |
|---|---|---|---|---|
| H1 | 28px | 600 | 1.4 | 页面标题 |
| H2 | 24px | 600 | 1.4 | 区块标题 |
| H3 | 20px | 500 | 1.4 | 卡片标题 |
| H4 | 16px | 500 | 1.5 | 列表标题 |
| Body | 14px | 400 | 1.6 | 正文 |
| Caption | 12px | 400 | 1.4 | 辅助说明 |
3. 间距系统
基础单位
基础间距单位: 4px
间距规范
| 名称 | 数值 | 使用场景 |
|---|---|---|
| xs | 4px | 紧凑元素间距 |
| sm | 8px | 相关元素间距 |
| md | 16px | 标准间距 |
| lg | 24px | 区块间距 |
| xl | 32px | 大区块间距 |
页面边距
| 端 | 边距 |
|---|---|
| 移动端 | 16px |
| 平板 | 24px |
| 桌面端 | 32px |
4. 圆角系统
| 元素 | 圆角 |
|---|---|
| 按钮-小 | 4px |
| 按钮-中 | 6px |
| 卡片 | 8px |
| 弹窗 | 12px |
| 头像 | 50% |
5. 阴影系统
| 层级 | 阴影值 | 使用场景 |
|---|---|---|
| 一级 | 0 1px 2px rgba(0,0,0,0.05) | 卡片 |
| 二级 | 0 4px 8px rgba(0,0,0,0.1) | 下拉菜单 |
| 三级 | 0 8px 16px rgba(0,0,0,0.15) | 弹窗 |
6. 组件规范
按钮
| 类型 | 高度 | 内边距 | 字号 |
|---|---|---|---|
| 大按钮 | 44px | 0 24px | 16px |
| 中按钮 | 36px | 0 16px | 14px |
| 小按钮 | 28px | 0 12px | 12px |
输入框
| 属性 | 值 |
|---|---|
| 高度 | 36px |
| 边框 | 1px solid #D9D9D9 |
| 圆角 | 4px |
| 内边距 | 0 12px |
卡片
| 属性 | 值 |
|---|---|
| 背景 | #FFFFFF |
| 圆角 | 8px |
| 内边距 | 16px |
| 阴影 | 一级阴影 |
7. 响应式断点
| 断点 | 范围 | 布局 |
|---|---|---|
| xs | < 576px | 单列 |
| sm | >= 576px | 单列 |
| md | >= 768px | 双列 |
| lg | >= 992px | 多列 |
| xl | >= 1200px | 最大宽度1200px |
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 · 161 lines · 0 tokens per session scan A 487f3c357e00
spec is a command published in the GitHub repository yezannnnn/agentGroup (149 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,251 tokens. 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.