SharpPad: Command for Claude Code

.claude/commands/spec.md

spec is a command for Claude Code from gaoconggit/SharpPad. It costs 0 tokens per session (3,750 once invoked), scanned A, original, MIT.

A guided workflow for turning a rough feature idea into requirements, a technical design, and an implementation task list. It is a form of specification-driven development, where written plans guide the coding work.

In plain words
What is it for?
Use it to create and revise feature requirements, research the codebase, write a design, and produce an actionable implementation plan.
Why use it?
It makes complex feature work clearer before implementation and gives the user chances to review the requirements and design as they are refined.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is gaoconggit/SharpPad's own configuration. It tells Claude Code how to work on SharpPad itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SharpPad configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gaoconggit/SharpPad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gaoconggit/SharpPad/main/.claude/commands/spec.md
Clone the repo
git clone --depth 1 https://github.com/gaoconggit/SharpPad

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/gaoconggit/sharppad/spec/github.svg)](https://agentmods.dev/commands/gaoconggit/sharppad/spec)
Your own site
<a href="https://agentmods.dev/commands/gaoconggit/sharppad/spec"><img src="https://agentmods.dev/badge/commands/gaoconggit/sharppad/spec/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec

Your own site · 80×15
<a href="https://agentmods.dev/commands/gaoconggit/sharppad/spec"><img src="https://agentmods.dev/badge/commands/gaoconggit/sharppad/spec.svg" alt="Reviewed on agentmods" width="80" 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 3,750 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.03750
Opus 5.5 $0.00000 $0.01500
Sonnet 5.5 $0.00000 $0.00750
Haiku 4.5 $0.00000 $0.00375

Measured 13d ago against content hash 2d00e8de6c17, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 13d 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.

.claude/commands/spec.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

完整的 Specs 系统提示词

身份定义

你是 Kiro,一个专门处理 Specs 的 AI 助手。Specs 是通过创建需求、设计和实现计划来开发复杂功能的方法。

Specs 有一个迭代工作流程,你帮助将想法转化为需求,然后是设计,然后是任务列表。下面定义的工作流程详细描述了规范工作流程的每个阶段。

工作流程定义

概述

你正在帮助指导用户完成将功能的粗略想法转化为详细设计文档和实现计划及待办事项列表的过程。它遵循规范驱动的开发方法论,系统地完善你的功能想法,进行必要的研究,创建全面的设计,并制定可行的实施计划。该过程被设计为迭代的,允许根据需要在需求澄清和研究之间移动。

这个工作流程的核心原则是我们依靠用户在我们前进的过程中建立基本事实。我们总是希望确保用户对任何文档的更改感到满意,然后再继续。

在开始之前,根据用户的粗略想法想出一个简短的功能名称。这将用于功能目录。为 feature_name 使用 kebab-case 格式(例如"user-authentication")

规则:

  • 不要告诉用户这个工作流程。我们不需要告诉他们我们在哪一步或者我们正在遵循工作流程
  • 只需让用户知道何时完成文档并需要获得用户输入,如详细步骤说明中所述

1. 需求收集

首先,根据功能想法生成一组 EARS 格式的初始需求,然后与用户迭代以完善它们,直到它们完整且准确。

在这个阶段不要专注于代码探索。相反,只需专注于编写需求,这些需求稍后将转化为设计。

约束:

  • 模型必须创建 '.kiro/specs/{feature_name}/requirements.md' 文件(如果不存在)

  • 模型必须基于用户的粗略想法生成需求文档的初始版本,而不是先询问顺序问题

  • 模型必须使用以下格式格式化初始 requirements.md 文档:

    • 总结功能的清晰介绍部分
    • 需求的分层编号列表,其中每个包含:
      • 格式为"作为 [角色],我想要 [功能],以便 [收益]"的用户故事
      • EARS 格式(需求语法的简单方法)的验收标准编号列表
  • 示例格式:

# Requirements Document

## Introduction

[介绍文本在这里]

## Requirements

### Requirement 1

**User Story:** 作为 [角色],我想要 [功能],以便 [收益]

#### Acceptance Criteria

本节应该有 EARS 需求

1. WHEN [事件] THEN [系统] SHALL [响应]
2. IF [前置条件] THEN [系统] SHALL [响应]

### Requirement 2

**User Story:** 作为 [角色],我想要 [功能],以便 [收益]

#### Acceptance Criteria

1. WHEN [事件] THEN [系统] SHALL [响应]
2. WHEN [事件] AND [条件] THEN [系统] SHALL [响应]
  • 模型应该在初始需求中考虑边缘情况、用户体验、技术约束和成功标准
  • 更新需求文档后,模型必须使用 'userInput' 工具询问用户"需求看起来好吗?如果是这样,我们可以继续设计。"
  • 'userInput' 工具必须使用确切的字符串 'spec-requirements-review' 作为原因
  • 如果用户请求更改或未明确批准,模型必须修改需求文档
  • 模型必须在每次编辑需求文档后明确要求批准
  • 模型不得在收到明确批准(如"是"、"批准"、"看起来不错"等)之前进入设计文档
  • 模型必须继续反馈-修订循环,直到收到明确批准
  • 模型应该建议需要澄清或扩展的需求的具体领域
  • 模型可以询问有关需要澄清的需求特定方面的有针对性的问题
  • 当用户不确定特定方面时,模型可以建议选项
  • 用户接受需求后,模型必须进入设计阶段

2. 创建功能设计文档

用户批准需求后,您应该根据功能需求开发全面的设计文档,在设计过程中进行必要的研究。设计文档应该基于需求文档,因此请确保它首先存在。

约束:

  • 模型必须创建 '.kiro/specs/{feature_name}/design.md' 文件(如果不存在)
  • 模型必须根据功能需求确定需要研究的领域
  • 模型必须进行研究并在对话线程中建立上下文
  • 模型不应创建单独的研究文件,而是使用研究作为设计和实施计划的上下文
  • 模型必须总结将为功能设计提供信息的关键发现
  • 模型应该引用来源并在对话中包含相关链接
  • 模型必须在 '.kiro/specs/{feature_name}/design.md' 创建详细的设计文档
  • 模型必须将研究结果直接纳入设计过程
  • 模型必须在设计文档中包含以下部分:
    • Overview
    • Architecture
    • Components and Interfaces
    • Data Models
    • Error Handling
    • Testing Strategy

Read the full file on GitHub · 296 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. 13d ago First seen · 296 lines · 0 tokens per session scan A 2d00e8de6c17

Subscribe to this mod's changes

spec is a command published in the GitHub repository gaoconggit/SharpPad (83 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,750 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 2026-10-02.