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/killvxk/pm-skills-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/killvxk/pm-skills-zh/sprint)<a href="https://agentmods.dev/commands/killvxk/pm-skills-zh/sprint"><img src="https://agentmods.dev/badge/commands/killvxk/pm-skills-zh/sprint.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 | $0.00021 | $0.01576 |
| Opus 5 | $0.00010 | $0.00788 |
| Sonnet 5 | $0.00004 | $0.00315 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
sprint 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sprint -- Sprint 全生命周期
覆盖 Sprint（冲刺）全生命周期的三种模式：plan（规划）用于 Sprint 计划会，retro（回顾）用于回顾会，release-notes（发布说明）用于发布沟通。
Invocation（调用示例）
/sprint plan 2 周 Sprint，4 名工程师，聚焦结账流程优化
/sprint retro [粘贴团队反馈或 Sprint 数据]
/sprint release-notes [粘贴工单、变更日志或 PRD]
/sprint # 询问当前所处阶段
Modes（模式）
Plan Mode（规划模式）
通过容量估算、故事选取和风险识别，为 Sprint 计划会做准备。
Workflow（工作流程）
Step 1：收集 Sprint 背景信息
- Sprint 时长（1 周或 2 周）
- 团队组成（工程师、设计师、QA——及各自可用时间）
- Sprint 目标或聚焦方向
- 待考虑的待办事项（粘贴、上传或描述）
- 上一个 Sprint 的遗留事项
- 已知中断因素（假期、值班、会议）
Step 2：估算容量
应用 sprint-plan 技能：
- 扣除会议、值班、PTO（带薪休假）后，计算可用的工程工时/故事点
- 根据历史数据（如有提供）或行业标准（理论容量的 70%）应用速率调整
- 展示每位团队成员的容量明细
Step 3：选取并排序故事
- 推荐哪些故事在容量范围内可完成
- 标注依赖链（A 必须在 B 开始前完成）
- 识别风险：规格不清晰的故事、有外部依赖的故事或需要设计输入的故事
- 平衡快速见效的小任务与较大工作项
- 确保每个故事都有验收标准
Step 4：生成 Sprint 计划
## Sprint 计划：[Sprint 名称/编号]
**时长**: [日期范围]
**Sprint 目标**: [一句话描述]
**团队**: [成员及可用时间]
### 容量
| 成员 | 可用天数 | 故事点/工时 | 备注 |
|------|---------|-----------|------|
**总容量**: [X] 故事点/工时
**推荐承诺量**: [Y] 故事点/工时（含缓冲）
### 已选故事
| # | 故事 | 故事点 | 负责人 | 依赖项 | 风险 |
|---|------|--------|-------|-------|------|
### Sprint 风险
1. [风险] — 缓解措施：[行动]
### 完成标准（Definition of Done）
- [ ] 代码已评审
- [ ] 测试通过
- [ ] 已部署到预发布环境
- [ ] QA 已审批
- [ ] 文档已更新（如适用）
Retro Mode（回顾模式）
组织结构化的回顾会，产出可落地的改进措施。
Workflow（工作流程）
Step 1：收集 Sprint 反馈
接受以下输入：
- 团队反馈（从问卷、Slack 或协作文档粘贴）
- Sprint 指标（速率、缺陷数、故障数）
- 用户自己的观察
询问："你偏好哪种回顾格式？"
- Start/Stop/Continue（开始/停止/继续）（简单快速）
- 4Ls（Liked 喜欢、Learned 学到、Lacked 缺少、Longed for 期望）
- 帆船模型（Wind 风=助力、Anchor 锚=阻力、Rocks 礁石=风险、Island 岛屿=目标）
Step 2：分析与结构化
应用 retro 技能：
- 按所选框架对反馈进行分类
- 识别主题和规律
- 区分表象与根因
- 突出值得庆祝的亮点
Step 3：生成回顾会摘要
## Sprint 回顾会：[Sprint 名称]
**日期**: [今天]
**格式**: [Start/Stop/Continue | 4Ls | 帆船模型]
**参与者**: [如已知]
### 做得好的方面
[按主题分组，附支撑证据]
### 做得不好的方面
[按主题分组，附根因分析]
### 关键洞察
[2-3 个浮现出的规律]
### 行动项
| # | 行动内容 | 负责人 | 截止日期 | 优先级 |
|---|--------|-------|---------|--------|
### 本 Sprint 指标
| 指标 | 本 Sprint | 上 Sprint | 趋势 |
|------|---------|---------|------|
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 · 194 lines · 21 tokens per session scan A 96e018965245
sprint is a command published in the GitHub repository killvxk/pm-skills-zh (154 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 1,576 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
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
create-release-note
Generate bug fix release notes from Jira tickets and linked GitHub PRs.
pr
Create a GitHub PR from current branch with unpushed commits — discovers templates, analyzes changes, pushes.
sync-coordinator
Multi-package synchronization and version alignment with ruv-swarm coordination for seamless integration between claude-code-flow and ruv-swarm packages.
github-modes
This document describes all GitHub integration modes available in Claude-Flow with ruv-swarm coordination. Each mode is optimized for specific GitHub workflows and includes batch tool integration for maximum efficiency.
iteration-drive
Drive the active iteration to completion — Phase 2 Autonomous Execute, Phase 3 iteration-close, Phase 4 Create PR, Phase 5 PR merge-ready loop (prefer babysit/-babysit; optional greploop when repo has it; else CI fallback) until mergeable. Not Done until Phase 5 exit checklist passes.