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.
git clone --depth 1 https://github.com/loulanyue/spec-kit-zhWrote 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/loulanyue/spec-kit-zh/specify)<a href="https://agentmods.dev/commands/loulanyue/spec-kit-zh/specify"><img src="https://agentmods.dev/badge/commands/loulanyue/spec-kit-zh/specify.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 | $0.00011 | $0.03165 |
| Opus 5 | $0.00005 | $0.01582 |
| Sonnet 5 | $0.00002 | $0.00633 |
| Haiku 4.5 | $0.00001 | $0.00316 |
Grade A, and why
specify 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户输入
$ARGUMENTS
在继续之前,你必须考虑用户输入(如果不为空)。
语言要求
- 所有面向用户的生成内容,包括
spec.md、检查清单、澄清问题、摘要和状态报告,都必须使用简体中文。 - 分支名、文件路径、ID 和其他机器导向标识在兼容性需要时保持 ASCII。
- 如果用户提供英文术语,应在必要时保留原词,并以中文补充说明。
概述
用户在触发消息中 /speckit.specify 后输入的文本就是功能描述。即使下面字面显示 {ARGS},也应假设你始终可以在本次对话中访问该描述。除非用户输入为空,否则不要要求用户重复描述。
基于该功能描述,请执行以下操作:
-
为功能生成简洁的短名称(2-4 个单词),作为分支名:
- 当用户使用中文描述需求时,根据功能含义生成对应的 ASCII 短名称;分支名不得包含中文字符
- 分析功能描述,提取最有意义的关键词
- 创建一个 2-4 个单词的短名称,概括功能要点
- 尽量采用"动词-名词"格式(如
add-user-auth、fix-payment-bug) - 保留技术术语和缩写(OAuth2、API、JWT 等)
- 名称应简洁,同时足以让人一眼理解功能含义
- 示例:
- "我想添加用户身份验证" →
user-auth - "Implement OAuth2 integration for the API" →
oauth2-api-integration - "创建分析仪表板" →
analytics-dashboard - "修复支付处理超时 Bug" →
fix-payment-timeout
- "我想添加用户身份验证" →
-
创建功能分支:运行脚本时传入
--short-name(以及--json),不要传入--number(脚本会自动检测全局下一个可用编号):- Bash 示例:
{SCRIPT} --json --short-name "user-auth" "Add user authentication" - PowerShell 示例:
{SCRIPT} -Json -ShortName "user-auth" "Add user authentication"
重要说明:
- 不要传入
--number— 脚本会自动确定正确的下一个编号 - 始终包含 JSON 标志(Bash 用
--json,PowerShell 用-Json),以便可靠地解析输出 - 每个功能只运行一次此脚本
- JSON 输出包含 BRANCH_NAME 和 SPEC_FILE 路径,始终参考这些路径获取实际内容
- 对于包含单引号的参数(如 "I'm Groot"),使用转义语法:
'I'\''m Groot'(或尽可能使用双引号)
- Bash 示例:
-
加载
templates/spec-template.md以了解所需章节结构。 -
遵循以下执行流程:
- 从用户输入中解析功能描述 若为空:报错"未提供功能描述"
- 从描述中提取关键概念 识别:参与者、操作、数据、约束条件
- 对于不明确的内容:
- 基于上下文和行业惯例做出合理推断
- 仅在以下情况下标记
[NEEDS CLARIFICATION: 具体问题]:- 该选择对功能范围或用户体验有重大影响
- 存在多种合理解读,且各自有不同含义
- 没有合理的默认值
- 限制:最多 3 个 [NEEDS CLARIFICATION] 标记
- 按影响程度排列澄清优先级:范围 > 安全/隐私 > 用户体验 > 技术细节
- 填写用户场景与测试章节 若无法确定用户流程:报错"无法确定用户场景"
- 生成功能需求 每条需求必须可测试 对未明确的细节使用合理默认值(在"假设"章节中记录)
- 定义成功标准 创建可量化、与技术无关的结果指标 同时包含定量指标(时间、性能、数量)和定性指标(用户满意度、任务完成率) 每条标准无需了解实现细节即可验证
- 识别关键实体(如涉及数据)
- 返回:成功(规范已可进入规划阶段)
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 · 252 lines · 11 tokens per session scan A ecc35b9b9b5f
specify is a command published in the GitHub repository loulanyue/spec-kit-zh (339 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 3,165 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
sdd-continue
Continue the next SDD phase in the dependency chain.
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-status
Show structured SDD status for an active change.
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.