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/plan)<a href="https://agentmods.dev/commands/loulanyue/spec-kit-zh/plan"><img src="https://agentmods.dev/badge/commands/loulanyue/spec-kit-zh/plan.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 | $0.00014 | $0.01159 |
| Opus 5 | $0.00007 | $0.00580 |
| Sonnet 5 | $0.00003 | $0.00232 |
| Haiku 4.5 | $0.00001 | $0.00116 |
Grade A, and why
plan 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 9d 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.
What it actually says
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制品与摘要,包括
plan.md、research.md、data-model.md、quickstart.md、合同描述和完成报告,都必须使用简体中文。 - 文件路径、命令、ID 和代码/配置键在需要时保持机器可读原样。
概述
-
设置:从仓库根目录运行
{SCRIPT}并解析 JSON 输出,获取 FEATURE_SPEC、IMPL_PLAN、SPECS_DIR 和 BRANCH 的路径。对于参数中的单引号(例如 "I'm Groot"),使用转义语法:例如'I'\''m Groot'(或尽量使用双引号)。 -
加载上下文:读取 FEATURE_SPEC 和
/memory/constitution.md的内容。加载已复制的 IMPL_PLAN 模板。 -
执行规划工作流:按照 IMPL_PLAN 模板的结构执行:
- 填写“技术上下文”(将未知项标记为 "NEEDS CLARIFICATION")
- 根据章程内容填写“宪章检查”部分
- 评估门禁(如果存在无合理解释的违反项则报错退出)
- 第 0 阶段:生成
research.md(解决所有 "NEEDS CLARIFICATION" 项) - 第 1 阶段:生成
data-model.md、contracts/目录和quickstart.md - 第 1 阶段:运行 agent 脚本以更新 agent 上下文
- 重新评估设计完成后的“宪章检查”
-
停止并报告:在完成第 2 阶段规划后结束命令。报告当前分支、IMPL_PLAN 路径以及已生成的制品。
阶段步骤
第 0 阶段:提纲与研究
-
从上方“技术上下文”中提取未知项:
- 每一个 NEEDS CLARIFICATION → 研究任务
- 每一个依赖项 → 最佳实践任务
- 每一个集成项 → 模式任务
-
生成并分派研究任务:
针对技术上下文中的每一个未知项: 任务:"研究 {unknown} 在 {feature context} 中的应用" 针对每一个技术选型: 任务:"寻找 {tech} 在 {domain} 领域的最佳实践" -
在
research.md中汇总研究结果,采用以下格式:- 决策:[选择了什么方案]
- 理由:[为什么选择该方案]
- 评估过的替代方案:[还评估了什么其他方案]
产出:完成 research.md 并解决所有 NEEDS CLARIFICATION 标记。
第 1 阶段:设计与契约
前置条件: research.md 已完成。
-
从功能规范中提取实体 →
data-model.md:- 实体名称、字段、关系
- 来自需求的验证规则
- 状态转移逻辑(如果适用)
-
定义接口契约(如果项目具有外部接口)→
/contracts/目录:- 识别项目向用户或其他系统暴露的接口
- 记录适合项目类型的契约格式
- 示例:库的公共 API、CLI 工具的命令行 Schema、Web 服务的端点、解析器的语法规则、应用程序的 UI 契约
- 如果项目纯粹是内部的(构建脚本、一次性工具等),则跳过此步
-
更新 Agent 上下文:
- 运行
{AGENT_SCRIPT} - 这些脚本会自动检测当前使用的 AI Agent
- 更新相应的 Agent 专用上下文文件
- 仅添加当前计划中的新技术
- 保留在标记之间的手动修改内容
- 运行
产出:data-model.md、/contracts/*、quickstart.md、Agent 专用上下文文件。
关键规则
- 始终使用绝对路径。
- 如果门禁检查失败或存在未解决的澄清项,则报错退出。
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.
- 9d ago First seen · 105 lines · 14 tokens per session scan A e0eca379d2e8
plan is a command published in the GitHub repository loulanyue/spec-kit-zh (339 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 1,159 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.