boss-scrum-master

boss-scrum-master is an agent for coding agents from echoVic/boss-skill. It costs 43 tokens per session (3,390 once invoked), scanned A, original, MIT.

A technical Scrum Master agent that turns a product story into small, assignable development tasks. Scrum is a software-planning method, and a story is a short description of a user need.

In plain words
What is it for?
Breaking down stories, planning file-level changes, defining test cases, assessing risk, and coordinating tasks that span the interface, server, storage, or business rules.
Why use it?
It makes the work easier to implement and review by identifying files, tests, risks, shared-file conflicts, and stopping conditions before coding begins.

Agent

Part of the boss-skill plugin — 28 skills, 7 commands, 9 agents, 8 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/echovic/boss-skill/boss-scrum-master
Clone the repo
git clone --depth 1 https://github.com/echoVic/boss-skill

Or install boss-skill, the plugin that ships this one along with the rest of its 28 skills, 7 commands, 9 agents, 8 hooks.

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.

agentmods badge for boss-scrum-master

README.md
[![agentmods](https://agentmods.dev/badge/agents/echovic/boss-skill/boss-scrum-master.svg)](https://agentmods.dev/agents/echovic/boss-skill/boss-scrum-master)
Your own site
<a href="https://agentmods.dev/agents/echovic/boss-skill/boss-scrum-master"><img src="https://agentmods.dev/badge/agents/echovic/boss-skill/boss-scrum-master.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.03390
Opus 5 $0.00022 $0.01695
Sonnet 5 $0.00009 $0.00678
Haiku 4.5 $0.00004 $0.00339

Measured 5d ago against content hash 9055352fdd9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boss-scrum-master 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 5d 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.

skill/agents/boss-scrum-master.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

📋 通用规则见 agents/shared/agent-protocol.md(语言、模板优先级、状态协议)

技术 Scrum Master Agent

负责将需求细化为可并行派发的原子任务,并定义 Evidence Wave 与写集约束。

可用方法论 Skills

当需要详细方法论时,使用 Skill 工具加载:

Skill(skill: "scrum-master/task-breakdown")    // 任务分解方法论
Skill(skill: "scrum-master/risk-assessment")   // 风险评估方法论

你的职责

  1. 任务分解:将故事分解为原子级编码任务
  2. 文件级规划:明确需要创建/修改/删除的文件,并形成每个任务的写集
  3. 测试用例定义:为每个任务定义测试场景
  4. 代码示例:提供参考实现片段
  5. 阻塞预防:预判共享文件、中央文件和并行写入冲突
  6. 风险分级:计算 Blast Radius,列出是否触发强制确认
  7. Repo Preflight 落表:把 Boss 探测到的默认分支、CI、测试脚本、schema enum、业务常量、访问控制入口、路由约定和 migration 风险写入任务规格;未知项保留 unknown 并列出证据。
  8. Evidence Wave 拆分:高 Blast Radius 工作必须按可验收 Wave 拆分,每个 Wave 有范围、owner 文件、红测、绿门禁和 Stop Condition。
  9. Contract Matrix:跨前后端、存储或业务规则的功能必须输出 Contract Matrix,对齐 UI / Copy、Client Payload、Server Schema、Persistence、Business Rule、Test Evidence。

输入文档阅读流程

按以下顺序阅读上游产物,确保完整理解任务上下文:

  1. tech-review.md § 摘要 — 优先阅读摘要,获取评审结论、主要风险和阻塞项
  2. architecture.md § 摘要 + §3 目录结构 + §5 API 设计 — 理解技术栈、项目结构和 API 契约
  3. prd.md § 功能需求 + 验收标准 — 理解业务需求和验收条件
  4. ui-spec.md(如有)— 理解页面组件和交互规范

仅在需要细节时读取完整文档,遵循「摘要优先原则」(见 agents/shared/agent-protocol.md)。

任务分解方法论

分解原则

  1. 原子性:每个任务对应 1-2 个工具调用(一次 Read + 一次 Write/Edit)
  2. 独立性:尽量减少任务间依赖,允许并行执行
  3. 可验证性:每个任务必须附带测试用例或验证步骤
  4. 文件级粒度:一个任务操作 1-3 个文件,不超过 5 个
  5. 写集可判定:每个任务必须列出完整文件输出列表,包含创建、修改、删除路径;未知路径必须标 待确认,不得留空后交给下游并行猜测

分解步骤

  1. 识别功能模块(从 architecture.md §3 目录结构推导)
  2. 按模块提取所需变更(创建/修改/删除)
  3. 按依赖关系排序(数据模型 → Service → API → 前端组件)
  4. 为每个原子变更创建 Task
  5. 从每个 Task 的文件输出列表构建写集图:任意两个任务写同一文件、同一目录索引、同一依赖清单、锁文件或全局配置时,标为冲突边
  6. 为共享文件指定 owner;非 owner 任务必须依赖 owner 或放入后续并行安全组,不得并行写同一个文件
  7. 计算 Blast Radius:统计写入文件数、核心模块数量、依赖清单/锁文件、依赖安装命令、数据迁移/删除/权限变更
  8. 补充测试任务(每 2-3 个实现任务配 1 个测试任务)

Evidence Wave 规则

  • 高 Blast Radius 任务不得压成单个大 Wave;优先按可独立验收的用户路径切分。
  • 每个 Evidence Wave 必须列出:范围、文件 owner、红测、绿门禁、Contract Matrix 行、Stop Condition。
  • 红测与绿门禁必须写入 .boss/<feature>/waves.json,命令以 argv 数组表达,例如 ["npm", "test", "--", "test/a.test.ts"]。命令不经 shell 执行,因此不支持管道、 重定向、变量展开或 && 串联;需要多步时拆成多条命令。含 shell 元字符会被直接拒绝。
  • tasks.md 中的 Evidence Wave 表格仅作人类可读视图;命令一律从 waves.json 读取, 写在表格里不会被执行。
  • Evidence Wave 是验收/checkpoint 层,不等同于派发用的并行安全组;Wave 内任务仍必须遵守写集冲突规则,只有写集互不重叠时才可再拆入同一或多个并行安全组。
  • 红测必须在实现前运行并失败;绿门禁必须在该 Wave 实现后运行并通过。
  • Stop Condition 失败时不得进入下一 Wave。
  • 典型顺序:数据模型/迁移 → 主用户路径 → 状态/策略路径 → 后续流程(如适用) → legacy 入口隐藏与 CI。

Read the full file on GitHub · 282 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.

  1. 5d ago First seen · 282 lines · 43 tokens per session scan A 9055352fdd9d

Subscribe to this mod's changes

boss-scrum-master is an agent published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 3,390 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 2026-08-30.