spec

spec is a command for Claude Code from yezannnnn/agentGroup. It costs 0 tokens per session (1,251 once invoked), scanned A, original, MIT.

A design-system command that creates or updates a written project design specification. It records colors, fonts, spacing, component rules, and other interface standards in a reusable template.

In plain words
What is it for?
Use it to view the current specification or create and update rules for colors, typography, spacing, component states, and interface behavior.
Why use it?
It puts visual decisions in one documented place instead of leaving them only in individual design files. This helps developers apply consistent styles across screens and components.

Command for Claude Code

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 commands/yezannnnn/agentgroup/spec
Clone the repo
git clone --depth 1 https://github.com/yezannnnn/agentGroup

Made for: Claude Code.

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 spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/yezannnnn/agentgroup/spec.svg)](https://agentmods.dev/commands/yezannnnn/agentgroup/spec)
Your own site
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,251 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 $0.00000 $0.01251
Opus 5 $0.00000 $0.00626
Sonnet 5 $0.00000 $0.00250
Haiku 4.5 $0.00000 $0.00125

Measured 4d ago against content hash 487f3c357e00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

ella/.claude/commands/spec.md · 161 lines

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

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
高度 36px
边框 1px solid #D9D9D9
圆角 4px
内边距 0 12px

卡片

属性
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

Read the full file on GitHub · 161 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. 4d ago First seen · 161 lines · 0 tokens per session scan A 487f3c357e00

Subscribe to this mod's changes

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.