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/taskstoissues)<a href="https://agentmods.dev/commands/loulanyue/spec-kit-zh/taskstoissues"><img src="https://agentmods.dev/badge/commands/loulanyue/spec-kit-zh/taskstoissues.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 | $0.00024 | $0.01252 |
| Opus 5 | $0.00012 | $0.00626 |
| Sonnet 5 | $0.00005 | $0.00250 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
taskstoissues 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 8d 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 — 151 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)。用户可能指定:
- 特定功能目录(例如
001-user-auth)——如指定则仅处理该目录。 - 过滤标签或阶段(例如
--phase=1)——仅创建匹配的 Issues。 - 额外的 GitHub Labels(以逗号分隔)——附加到每个新建 Issue。
语言要求
- Issue 标题和正文使用简体中文,除非项目
constitution.md另有规定。 - 代码示例、路径、命令保持原样,不翻译。
概述
本命令将 .specify/<FEATURE_DIR>/tasks.md 中的结构化任务列表转换为 GitHub Issues,
并按正确的依赖顺序提交,使团队可以立即在 GitHub Project Board 上开始追踪进度。
执行流程
步骤 1 — 前置条件检查
在仓库根目录运行 {SCRIPT},解析 FEATURE_DIR 和 AVAILABLE_DOCS 列表。
- 所有路径必须使用绝对路径。
- 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)。
步骤 2 — 解析任务文件
从脚本输出中提取 tasks 文件路径,读取其内容。
每个任务条目应包含:
| 字段 | 格式 | 说明 |
|---|---|---|
| 任务 ID | T-NNN |
全局唯一编号 |
| 标题 | 字符串 | 简洁描述 |
| 阶段 | Phase N |
执行阶段 |
| 依赖 | T-NNN, T-NNN |
前置任务 ID |
| 验收条件 | Markdown 列表 | 完成标准 |
| 负责角色 | 字符串 | 开发者 / QA / DevOps 等 |
若 tasks.md 中缺少某字段,使用空字符串并在 Issue 正文中标注 TODO。
步骤 3 — 确认远端仓库
通过以下命令获取 Git 远端地址:
git config --get remote.origin.url
[!CAUTION] 仅当远端地址为 GitHub URL(
github.com)时,才继续执行后续步骤。 若为其他平台或本地路径,终止并提示用户。
从 URL 中解析 {OWNER} 和 {REPO}。验证你对该仓库有 issues:write 权限。
步骤 4 — 排序(拓扑排序)
根据依赖字段对任务做拓扑排序,确保:
- 无依赖任务优先创建。
- 被依赖的任务 Issue 编号在创建依赖任务时已知,可填入正文。
- 若存在循环依赖,报告错误并终止,列出循环路径。
步骤 5 — 创建 Issues
对排序后的每个任务,使用 GitHub MCP Server 创建 Issue,格式如下:
Issue 标题:[T-NNN] <任务标题>
Issue 正文模板:
## 任务描述
<任务说明,来自 tasks.md>
## 验收条件
<来自 tasks.md 的验收条件列表>
## 依赖关系
- 前置 Issues:<若有,列出 #<issue_number>,否则填"无">
## 元数据
| 字段 | 值 |
|---|---|
| 阶段 | Phase N |
| 负责角色 | <角色> |
| 任务 ID | T-NNN |
| 功能目录 | `.specify/<FEATURE_DIR>/` |
---
*此 Issue 由 `speckit.taskstoissues` 命令自动生成,来源:`tasks.md`。*
Labels(如仓库已存在对应标签则自动应用):
spec-kit— 标记所有自动生成的 Issuesphase-N— 对应执行阶段- 用户通过
$ARGUMENTS额外传入的标签
[!CAUTION] 在任何情况下,都绝对不允许在与远端 URL 不匹配的仓库中创建 Issue。
步骤 6 — 汇总报告
所有 Issue 创建完成后,输出汇总报告:
✅ 已创建 Issues 汇总
========================
T-001 #42 初始化数据库 Schema
T-002 #43 实现用户注册 API 依赖 → #42
T-003 #44 前端登录页面 依赖 → #43
...
总计:N 个 Issues 已创建于 github.com/{OWNER}/{REPO}
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.
- 8d ago First seen · 151 lines · 24 tokens per session scan A 6c4e10826c0e
taskstoissues is a command published in the GitHub repository loulanyue/spec-kit-zh (339 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 1,252 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
arrange-workspace-flow-choose-workspace-layout
Phase 1 Choose Workspace Layout of arrange-workspace-flow.
ijfw-status
Show IJFW state -- mode, routing, memory, recent activity, codebase index, settings. Use when you want the at-a-glance banner you'd otherwise get at session start.
ijfw-ship
Run the IJFW workflow Ship phase (Deep D6). Pre-flight, deploy, and close. Usage: /ijfw-ship.
team
Manage your project's agent team. Usage: /team [setup|list|add|remove|swap].
workflow
Start or resume the IJFW project workflow. Usage: /workflow [discover|plan|execute|verify|ship|status].
create-issue
Create a GitHub issue with proper template discovery and population.