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/4d-frameworknpx skills add ace3000chao/book2startup --skill 4d-frameworkgit 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 | $0.00124 | $0.02457 |
| Opus 5 | $0.00062 | $0.01229 |
| Sonnet 5 | $0.00025 | $0.00491 |
| Haiku 4.5 | $0.00012 | $0.00246 |
Grade A, and why
4d-framework 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
4D Framework（四维决策框架）
R — 原文 (Reading)
"McKinsey has its 7-S Framework for large companies; we have our 4D Framework for growth firms. The framework includes: Driver, Demands, Disciplines, Decisions."
— Vern Harnish, Scaling Up, 第1章
I — 方法论骨架 (Interpretation)
4D框架是企业从"创始人驱动"走向"系统驱动"的导航坐标系。
Driver（驱动）：领导力引擎——创始人和高管团队的能量、方向感、决策速度。 任何组织的上限都是领导力的投影。
Demands（需求）：People与Process的动态平衡——企业需要足够的人才密度， 也需要足够的流程纪律。两者缺一不可，过度依赖任何一方都会翻车。
Disciplines（纪律）：执行三要素——①优先级清晰（不眉毛胡子一把抓）， ②数据说话（不是凭感觉），③会议节奏（让信息流动的物理机制）。
Decisions（决策）：四大决策域——People（谁来做）、Strategy（往哪走）、 Execution（怎么做）、Cash（钱够不够）。每错一个，Scaling就会卡住。
这四个维度不是并列关系，而是层层递进：Driver发动，Demands找到平衡点， Disciplines锁定执行，Decisions逐一做对。没有Driver，后三者都是空转。
A1 — 书中的应用 (Past Application)
案例 1: 框架的诞生背景
- 问题: McKinsey的7-S框架专为大型企业设计，中小企业需要一个等效的Scaling工具
- 方法论的使用: 作者团队在长期辅导成长型企业的过程中，总结出这四个最核心的维度
- 结论: 4D是Growth Firm的专属框架，与企业规模无关，与Growth Stage强相关
- 结果: 成为Scaling Up整个体系的底层结构，贯穿全书
案例 2: 章节应用
- 问题: 书中后续章节分别对应4D的某个维度——People对应团队章节， Strategy对应战略章节，Execution对应运营章节，Cash对应财务章节
- 方法论的使用: 读者可以把任何运营问题"投影"回4D，找到对应的决策域
- 结论: 4D不是分析工具，而是"问对问题"的框架
- 结果: 避免在错误维度上用力
案例 3: 常见误区
- 问题: 创始人往往只关注Driver（自己）和Strategy（方向），忽略Disciplines和People
- 方法论的使用: 用4D做季度自检：四个维度各打几分？
- 结论: 最短板决定企业上限
- 结果: 创始人学会"分精力"而非"只用力"
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 公司到了一定规模，创始人觉得越来越累——觉得什么事都得自己拍板， 不知道该放什么权出去，怀疑是不是团队不行
- 战略定得很清楚，执行却总是打折扣——年初目标分解到季度， 季度末发现完成度不到一半，不知道哪里出问题
- 团队扩张后反而效率下降——从10人扩到30人， 沟通成本暴增，项目推进反而更慢，开始怀疑"人多了反而坏事"
- 四大领域（人/战略/执行/现金）频繁冲突——销售要快速扩张， 财务要控制现金流；技术要打磨产品，市场要快速迭代……每天都在取舍
- 在做年度战略规划——需要把"战略"翻译成"组织能执行的东西"， 但不知道从哪个维度先开始
语言信号 (用户的话里出现这些就应激活)
- "我觉得公司现在什么问题都有，不知道从哪下手"
- "战略定了但落不下去，是不是执行层的问题？"
- "人有了、钱有了、方向也有了，怎么还是推不动？"
- "我一个人扛不住了，是不是该找人分担？"
- "怎么判断我现在最大的短板在哪？"
与相邻 skill 的区分
- 与
OPSP（一页战略计划）的区别: OPSP是"怎么写"，4D是"想什么"—— 4D先于OPSP，用OPSP之前先用4D把问题域定义清楚 - 与
Cash Conversion Cycle（现金转换周期）的区别: 现金只是4D的 四个决策域之一，4D覆盖面更广，是元框架 - 与
FACe（功能问责表）的区别: FACe是People维度的落地工具， 4D是包含People在内四个维度的顶层视角
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 · 178 lines · 124 tokens per session scan A 8a52a8adb7ee
4d-framework is a skill published in the GitHub repository ace3000chao/book2startup (72 stars, last pushed 4mo ago), licensed MIT. It adds 124 tokens to every session and 2,457 once invoked, about $0.0006 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
thinking-jobs-to-be-done
Deciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing workarounds.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
thinking-margin-of-safety
When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.
thinking-socratic
When a request is vague, assumption-laden, or "obvious," ask the few load-bearing questions that expose hidden requirements before building or committing.
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
thinking-bounded-rationality
Use when search or investigation could run forever. Set an explicit good-enough threshold first, then stop at the first option that clears it.