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.
npx agentmods add skills/xtyooo/specpilot-codex/specpilot-updatenpx skills add xtyooo/specpilot-codex --skill specpilot-updategit clone --depth 1 https://github.com/xtyooo/specpilot-codexWrote 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/skills/xtyooo/specpilot-codex/specpilot-update)<a href="https://agentmods.dev/skills/xtyooo/specpilot-codex/specpilot-update"><img src="https://agentmods.dev/badge/skills/xtyooo/specpilot-codex/specpilot-update.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 | $0.00046 | $0.01646 |
| Opus 5 | $0.00023 | $0.00823 |
| Sonnet 5 | $0.00009 | $0.00329 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
specpilot-update 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 4d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SpecPilot: 更新需求
处理需求变更,根据需求当前状态和变更范围选择合适的处理方式。
参数
the user-provided arguments after the command text- 格式:REQ-xxx [变更内容]或仅REQ-xxx(变更内容在文档中)
使用场景
- 开发中的需求有调整
- 已完成的需求需要修复 bug
- 已完成的需求需要新增功能
- 需求理解有偏差需要修正
变更内容来源(二选一)
- 命令参数直接提供:
/specpilot:update REQ-001 新增xxx功能,修改xxx逻辑 - 在 draft 文件的【变更请求】章节中写明(AI 自动读取)
执行步骤
阶段一:读取需求和变更内容
- 从
the user-provided arguments after the command text解析需求编号和变更内容 - 读取
docs/specpilot/requirements/index.md获取需求当前状态 - 读取草稿文件:
docs/specpilot/requirements/REQ-{编号}-draft.md - 读取项目指南:
docs/specpilot/project-guide.md - 获取变更内容:
- 如果命令参数中包含变更内容,使用参数中的内容
- 否则检查 draft 文件是否有【变更请求】章节
- 如果都没有,提示用户提供变更内容
阶段二:分析变更影响
-
深入分析变更内容:
- 变更涉及哪些功能点
- 变更影响哪些代码文件
- 变更是否改变核心逻辑
- 变更与原需求的关系
-
判断变更类型:
| 变更类型 | 判断标准 | 处理方式 |
|---|---|---|
| Bug 修复 | 代码实现与需求不符,或有逻辑错误 | 原需求追加修复 |
| 需求微调 | 改动 ≤3 个文件,不改变核心逻辑 | 原需求追加修改 |
| 需求新增 | 在原有基础上新增独立功能点 | 建议创建新需求 |
| 需求重做 | 改变核心逻辑,改动 >5 个文件 | 必须创建新需求 |
- 输出分析结果:
## 变更分析 - REQ-{编号}
**当前状态**:{状态}
**变更内容**:{用户提供的变更描述}
### 变更影响分析
**变更类型**:{Bug修复/需求微调/需求新增/需求重做}
**影响范围**:
- 涉及文件:{文件列表}
- 核心逻辑变化:{是/否}
- 预估改动量:{小/中/大}
**处理建议**:{原需求修改 / 创建新需求迭代}
是否同意此处理方式?
阶段三:更新需求文档
情况A:原需求修改(Bug修复/微调)
-
更新 index.md 状态:
- 如果是
completed,改为🔧 updating - 如果是
in_progress,保持不变
- 如果是
-
在 draft 文件中记录变更:
在【需求确认】章节后添加或更新【变更记录】:
---
## 【变更记录】
### 变更 #1 - {日期}
**变更类型**:{Bug修复/需求微调}
**变更原因**:
{为什么需要变更}
**变更内容**:
{具体变更了什么}
**影响范围**:
- 涉及文件:{文件列表}
- 涉及功能:{功能点}
**变更后的需求**:
{更新后的需求描述,整合到原需求中}
-
更新【需求确认】章节:
- 整合变更内容到原有需求确认中
- 更新数据模型、业务规则、数据流等(如有变化)
- 更新涉及代码文件列表
-
进入确认流程:
- 如果变更较复杂,重新进行需求确认(类似 /specpilot:confirm)
- 如果变更简单明确,直接进入执行
情况B:创建新需求迭代(新增/重做)
- 询问用户确认:
该变更涉及较大改动,建议创建新需求进行迭代。
- 原需求:REQ-{编号} - {描述}
- 新需求:REQ-{新编号}(迭代自 REQ-{编号})
是否同意?输入"同意"继续,或"坚持原需求"在原需求上修改。
- 如果同意创建新需求:
- 自动执行类似
/specpilot:new的流程 - 新需求自动填充:
- 关联需求:
迭代自:REQ-{原编号} - 代码位置说明:复制原需求
- 需求内容:包含原需求摘要 + 新变更内容
- 关联需求:
- 更新 index.md 关联关系
- 原需求状态可选改为
🔄 iterated(如果完全替代)
- 自动执行类似
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.
- 4d ago First seen · 217 lines · 46 tokens per session scan A 173fd5b46882
specpilot-update is a skill published in the GitHub repository xtyooo/specpilot-codex (10 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 1,646 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
glab-issue
Create, view, update, and manage GitLab issues. Use when working with issue tracking, bug reports, feature requests, or task management. Operations include creating issues, listing with filters, viewing details, adding comments/notes, updating labels/assignees/milestones, closing/reopening, and board management.…
add-asana
Add Asana project management MCP integration to Deus. Gives host-side Claude Code sessions read/write access to Asana tasks, projects, sections, and tags via @roychri/mcp-server-asana.