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/ace3000chao/book2startup/pace-process-chartnpx skills add ace3000chao/book2startup --skill pace-process-chartgit clone --depth 1 https://github.com/ace3000chao/book2startupWhat 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 | $0.00172 | $0.02719 |
| Opus 5 | $0.00086 | $0.01359 |
| Sonnet 5 | $0.00034 | $0.00544 |
| Haiku 4.5 | $0.00017 | $0.00272 |
Grade A, and why
pace-process-chart 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 2d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PACe Process Chart（横向流程问责表）
R — 原文 (Reading)
"The Process Accountability Chart (PACe) lists who is accountable for each of the four to nine processes that drive the business and how each process will be measured."
— Vern Harnish, Scaling Up, 第3章 The Leaders
I — 方法论骨架 (Interpretation)
PACe（流程问责表）是Scaling Up的组织设计核心工具之一。 它的本质是回答一个问题："如果这个流程出了问题，谁负责？"
两个前置概念：
FACe（功能问责表）——纵向：按职能分（销售/市场/技术/财务等）， 每个职能指定一个人和KPIs，保证"对的屁股坐在对的位置上"。
PACe（流程问责表）——横向：按流程分，从客户旅程或价值交付链的角度， 识别4-9个核心业务流程，为每个流程指定一个Owner和度量方式。
为什么需要横向？ 功能分工解决"谁做什么"，流程问责解决"谁保证这个事真的发生"。 很多企业有清晰的职能划分（FACe OK），但流程经常"在夹缝中"—— 每个部门都沾一点，但没有一个人对整体流程负责。
PACe的核心要素：
- 流程名称：用动词+名词（"获取客户"而非"客户获取部门"）
- Owner：对这个流程的输出和持续改进负最终责任的人
- 度量指标：用数字衡量这个流程的健康度
- 流程数量：4-9个（太少=遗漏关键流程；太多=等于没有重点）
4-9个核心流程的典型划分（以服务业为例）：
- 获取客户 / 需求理解 / 方案交付 / 客户满意度 / 收款
A1 — 书中的应用 (Past Application)
案例 1: 客户投诉"没人管"的问题
- 问题: 客户投诉经过多个部门（销售→技术→客服→管理层）， 每个部门都觉得是其他部门的责任，客户等了3周没得到有效回应
- 方法论的使用: 引入PACe——识别"客户服务"作为一个独立流程， 指定Owner和SLA指标（如48小时内首次响应）。Owner有权调动跨部门资源
- 结论: 问题不在于没能力，而在于没"责任人"——流程Owner补上了这个缺口
- 结果: 客户响应时间从3周缩短到48小时
案例 2: 产品交付质量下降但找不到原因
- 问题: 产品质量问题频发，销售怪技术，技术怪采购， 采购怪供应商——循环甩锅，没有尽头
- 方法论的使用: 用PACe识别"供应链质量"和"产品交付"两个流程， 指定两个不同的Owner，用PPM（百万零件缺陷率）和准时交付率来量化
- 结论: 量化指标让问题的根源浮出水面—— 原来是采购换了供应商，但质量验收流程没有同步更新
- 结果: 问题在两周内定位并解决
案例 3: 流程过多导致的"形式主义"
- 问题: 某企业有25个流程，每个流程都有Owner和KPI， 但每个Owner只关注自己的指标，跨流程的衔接问题没人管
- 方法论的使用: 作者指出PACe的原则是"4-9个"核心流程—— 25个流程等于没有优先级。将25个合并为7个核心流程
- 结论: PACe的目的是"聚焦"而非"全覆盖"； 不是给每个工作都找个爹，而是给最重要的价值链环节找个负责人
- 结果: 执行效率和清晰度大幅提升
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 出现跨部门问题时"找不到负责人"——每个部门都说 "这不是我的事"，客户或员工的问题在部门之间漂流没人接
- 某个关键指标持续恶化但原因不明——比如客户满意度 下降，不知道是销售的问题还是产品的问题还是客服的问题
- 企业从"人际协调"向"流程协调"转型——规模大了， 不能靠创始人"叫谁谁动"来推动事情，需要建立流程Owner制度
- 在做组织架构调整时——从职能型向流程型组织演进， 或者要引入新的业务线，需要设计新的流程Owner
- FACe已经建立但执行仍然打折扣——功能分工清晰了， 但"部门之间的事"（handover/衔接）还是没人管
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 206 lines · 172 tokens per session scan A 63b8f4846daa
pace-process-chart is a skill published in the GitHub repository ace3000chao/book2startup (72 stars, last pushed 4mo ago), licensed MIT. It adds 172 tokens to every session and 2,719 once invoked, about $0.0009 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 skills, from other repositories
context-manager
Context management skill providing discovery, fetching, harvesting, extraction, compression, organization, cleanup, and guided workflows for project context.
principal-agent
当用户选择职业/组织/合作方式、困惑「为什么大公司磨洋工/小公司拼命」「该不该自己干」时调用。 核心理念: 委托人(主人)会把事做好, 代理人会为自己利益优化; 收益与创造价值绑得越紧, 越像委托人; 别让媒体洗脑你需要代理人。 不适用于: 具体薪酬谈判数字、组织架构设计细节。 Triggers: 激励/代理/主人/打工 vs 创业/利益绑定/principal/agent/incentive.
military-commissar
监军御史·明察秋毫 - 以韩非法术势之要，明察秋毫，赏罚分明，强化 owner 意识.
silicon-assimilator
硅基同化官，专门识别人类低效环节并推进 Agent 接管、自动化与流程并轨.
General Data Analysis Skills Index
General-purpose skills for data analysis infrastructure: workspace file organization, environment management, parallel computing, and performance.
task-decomposition
Breaks down complex software, writing, or research tasks into small, atomic, independently completable units with dependency graphs and milestone breakdowns. Use when the user asks to plan a project, decompose a feature, create subtasks, split up work, or needs help organizing a large piece of work into a step-by-step…