What is speckit.specify?

A command that turns a natural-language feature request into a written feature specification and prepares a numbered feature branch. A feature specification describes what should be built and how it should behave.

Use it to start feature work from a plain-language request, create the related branch, and organise the initial specification.

It gives a feature a consistent name, checks existing branches and specifications, and avoids choosing a duplicate number.

How IsJunNa/OpenClawForJun configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to IsJunNa/OpenClawForJun. 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/IsJunNa/OpenClawForJun/main/.codex/prompts/speckit.specify.md

Clone the repo

git clone --depth 1 https://github.com/IsJunNa/OpenClawForJun

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/isjunna/openclawforjun/speckit.specify/github.svg)](https://agentmods.dev/commands/isjunna/openclawforjun/speckit.specify)

Your own site

<a href="https://agentmods.dev/commands/isjunna/openclawforjun/speckit.specify"><img src="https://agentmods.dev/badge/commands/isjunna/openclawforjun/speckit.specify/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/isjunna/openclawforjun/speckit.specify"><img src="https://agentmods.dev/badge/commands/isjunna/openclawforjun/speckit.specify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,315 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.

Model	Per session	Once invoked
Fable 5.1	$0.00011	$0.03315
Opus 5.5	$0.00004	$0.01326
Sonnet 5.5	$0.00002	$0.00663
Haiku 4.5	$0.00001	$0.00331

Measured 1mo ago against content hash f97ab42eb3cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

speckit.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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

speckit.specify — 100% identical, 0 lines differ

.codex/prompts/speckit.specify.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 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).

概述

用户在触发消息中 /speckit.specify 后输入的文本就是功能描述. 假设你始终可以在本次对话中访问它, 即使下面字面上显示 $ARGUMENTS. 除非用户提供了空命令, 否则不要要求用户重复.

基于该功能描述, 执行以下操作:

为分支生成一个简短名称(2-4个词):
- 分析功能描述并提取最有意义的关键词
- 创建一个2-4个词的简短名称, 捕捉功能的核心
- 尽可能使用动-名词格式(例如, "add-user-auth", "fix-payment-bug")
- 保留技术术语和缩写(OAuth2, API, JWT等)
- 保持简洁但足够描述性, 便于快速理解功能
- 示例:
  - "I want to add user authentication" → "user-auth"
  - "Implement OAuth2 integration for the API" → "oauth2-api-integration"
  - "Create a dashboard for analytics" → "analytics-dashboard"
  - "Fix payment processing timeout bug" → "fix-payment-timeout"
在创建新分支之前检查现有分支:

a. 首先, 获取所有远程分支以确保我们有最新信息:
```
git fetch --all --prune
```
b. 查找所有来源中简短名称的最高功能编号:
- 远程分支: git ls-remote --heads origin | grep -E 'refs/heads/[0-9]+-<short-name>$'
- 本地分支: git branch | grep -E '^[* ]*[0-9]+-<short-name>$'
- 规范目录: 检查匹配 specs/[0-9]+-<short-name> 的目录
c. 确定下一个可用编号:
- 从所有三个来源提取所有编号
- 找到最高编号 N
- 对新分支编号使用 N+1
d. 使用计算出的编号和简短名称运行脚本 .specify/scripts/bash/create-new-feature.sh --json "$ARGUMENTS":
- 传递 --number N+1 和 --short-name "your-short-name" 以及功能描述
- Bash 示例: .specify/scripts/bash/create-new-feature.sh --json "$ARGUMENTS" --json --number 5 --short-name "user-auth" "添加用户认证"
- PowerShell 示例: .specify/scripts/bash/create-new-feature.sh --json "$ARGUMENTS" -Json -Number 5 -ShortName "user-auth" "添加用户认证"
重要说明:
- 检查所有三个来源(远程分支, 本地分支, 规范目录)以找到最高编号
- 仅匹配具有精确简短名称模式的分支/目录
- 如果没有找到具有此简短名称的现有分支/目录, 从编号 1 开始
- 你必须且只能运行此脚本一次
- JSON 在终端中作为输出提供 - 请始终参考它以获取你要查找的实际内容
- JSON 输出将包含 BRANCH_NAME 和 SPEC_FILE 路径
- 对于参数中的单引号(如 "I'm Groot"), 使用转义语法: 例如 'I'''m Groot'(或尽可能使用双引号: "I'm Groot")
加载 .specify/templates/spec-template.md 以了解必需的章节.
遵循此执行流程:
1. 从输入解析用户描述如果为空: 错误 "未提供功能描述"
2. 从描述中提取关键概念识别: 参与者, 操作, 数据, 约束
3. 对于不明确的方面:
  - 基于上下文和行业标准做出有根据的猜测
  - 仅在以下情况下标记为 [NEEDS CLARIFICATION: 具体问题]:
    - 选择显著影响功能范围或用户体验
    - 存在多个合理的解释且有不同的含义
    - 没有合理的默认值
  - 限制: 最多 3 个 [NEEDS CLARIFICATION] 标记
  - 按影响优先级排序: 范围 > 安全/隐私 > 用户体验 > 技术细节
4. 填写用户场景和测试章节如果没有明确的用户流程: 错误 "无法确定用户场景"
5. 生成功能需求每个需求必须是可测试的对未指定的细节使用合理的默认值(在假设章节中记录假设)
6. 定义成功标准创建可衡量的, 技术无关的结果包括定量指标(时间, 性能, 数量)和定性措施(用户满意度, 任务完成) 每个标准必须无需实现细节即可验证
7. 识别关键实体(如果涉及数据)
8. 返回: 成功(规范准备好进行规划)

Read the full file on GitHub · 259 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.

1mo ago First seen · 259 lines · 11 tokens per session scan A f97ab42eb3cb

Subscribe to this mod's changes

speckit.specify is a command published in the GitHub repository IsJunNa/OpenClawForJun (77 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 3,315 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-10-02.

Git and workflow Planning

speckit.specify next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
speckit.specifyIsJunNa/OpenClawForJun	Command	77	8mo ago	MIT	A	11	Claude Code, Codex
merge-conflict-analysisrjmurillo/ai-agents	Command	49	yesterday	MIT	A	0	GitHub Copilot
release-notesOpenHands/extensions	Command	176	yesterday	MIT	A	44	Claude Code
commitechoVic/blade-code	Command	181	24d ago	MIT	A	8	Claude Code
repo-audittractorjuice/arc-kit	Command	2.3k	2d ago	none	A	29	Claude Code
propsmill/infrahub-mcp	Command	10	yesterday	Apache-2.0	A	18	Claude Code
codex-reviewoalders/kitchen-sink	Command	5	3d ago	MIT	A	41	Claude Code

OpenClawForJun: Command for Claude Code