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 skills add ace3000chao/book2startup --skill f34git clone --depth 1 https://github.com/ace3000chao/book2startupWrote 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/ace3000chao/book2startup/f34)<a href="https://agentmods.dev/skills/ace3000chao/book2startup/f34"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/f34/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ace3000chao/book2startup/f34"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/f34.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00151 | $0.02315 |
| Opus 5 | $0.00076 | $0.01157 |
| Sonnet 5 | $0.00030 | $0.00463 |
| Haiku 4.5 | $0.00015 | $0.00231 |
Grade A, and why
f34-upward строго-downward-仁 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 9d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
事上敬谨 待下宽仁框架
R — 原文 (Reading)
"士君子处权门要路，操履要严明，心气要和易，毋少随而近腥膻之党，亦毋过激而犯蜂虿之毒。"
— 洪应明, 事上敬谨 待下宽仁
I — 方法论骨架 (Interpretation)
这是管理者/当权者的处世四维框架，核心是避免两个极端：
四个维度：
-
操履严明：原则清晰，规矩分明，不因人而异。对所有人都用同一个标准，不能对亲近的人放松，对不喜欢的人苛刻。
-
心气和易：态度温和，不盛气凌人。不因为自己有权力就高高在上，不对下属摆脸色。
-
不近腥膻之党：不与奸邪小人结盟。一旦与之为伍，就失去了道义的根基，终将被拖累。
-
不激化与蜂虿之毒：不主动激化与阴险小人的冲突。与恶人正面冲突往往两败俱伤，最好保持距离，不给他们伤害你的机会。
核心逻辑：管理者处于复杂的人际生态中，既要有清晰的原则（严明），又要有弹性的态度（和易）；既不能站错队（腥膻之党），也不能树敌过多（蜂虿之毒）。
A1 — 书中的应用 (Past Application)
案例 1: 萧何月下追韩信
- 问题: 韩信有大才但出身低微，萧何作为刘邦的重臣，如何在刘邦身边为韩信争取机会
- 方法论的使用: 萧何对刘邦"操履严明"——始终以大局为重，不因私废公；对韩信等人才"心气和易"——愿意为他们争取机会
- 结论: 好的管理者既能维护原则，又能包容人才
- 结果: 韩信被拜为大将，助刘邦定鼎天下
案例 2: 项羽的失败——严而不和
- 问题: 项羽本身有能力、有魅力，但团队最终离散
- 方法论的使用: 项羽"操履严明"但"心气不和易"——待人刻薄（范增多次建议不被采纳），不能容忍不同意见
- 结论: 只有严明没有和易，团队会失去人心
- 结果: 韩信、陈平等人才纷纷离开，投奔刘邦，最终乌江自刎
案例 3: 刘邦的宽仁——和而不严的反面
- 问题: 刘邦在某些时候过于宽容（对雍齿的背叛既往不咎）
- 方法论的使用: 刘邦在"心气和易"上做得很好，但"操履严明"时有欠缺——有时候因私情而破坏了规矩
- 结论: 只有和易没有严明，同样会出问题
- 结果: 刘邦靠团队（张良/韩信/萧何）的集体智慧弥补了个人缺陷，但仍然出现了一些管理问题
案例 4: 曾国藩的平衡
- 问题: 曾国藩处于晚清复杂的政治环境中，上面有朝廷，下面有湘军各级将领
- 方法论的使用: 对朝廷"敬谨"——不显山露水，功高不震主；对下属"宽仁"——宽容有才者不好的一面，笼络人心
- 结论: "敬谨"和"宽仁"在不同维度同时使用，而不是非此即彼
- 结果: 功高震主却得以善终，是清代最成功的军事-政治领袖之一
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 新晋管理者困惑：刚当上领导，不知道如何拿捏对上的态度和对下属的态度
- 团队管理困境：对下属太严，团队氛围差、离职率高；对下属太松，下属不听话、工作没质量
- 政治敏感性时刻：面对复杂的办公室政治，不知道该站哪边、该保持什么距离
- 对上关系处理：不知道如何在领导面前既保持原则又不显得不服从
语言信号 (用户的话里出现这些就应激活)
- "我对下属太严厉了吗"
- "老板对我有看法我不知道怎么办"
- "我对下属已经很好了但他们还是不满意"
- "当了领导不知道怎么拿捏"
- "我该严还是松"
- "这个人是"小人"我不知道该怎么对待他"
- "我不喜欢这个人但他工作能力强，我不知道怎么和他相处"
- "上面有压力，下面有怨气，我不知道怎么处理"
与相邻 skill 的区分
- 与
f04 中和处世决策框架的区别：f04是通用的性情判断（躁/刻/执），本框架是管理者专属的政治-人际平衡 - 与
f33 不动声色应变框架的区别：f33是被动应对（被骗/被辱），本框架是主动构建管理者的人际策略
E — 可执行步骤 (Execution)
当 skill 被激活后, agent 应按以下步骤执行:
- 诊断当前失衡
- 完成标准: 用户对照四个维度自我评估：哪里强了（过于极端）？哪里弱了（过于忽视）？
- 操履严明过强 → 对下属苛刻、规矩太多
- 心气和易过强 → 对下属放纵、失去威信
- 过于接近某一方 → 可能站错队
- 过于激化冲突 → 树敌过多
- 完成标准: 用户对照四个维度自我评估：哪里强了（过于极端）？哪里弱了（过于忽视）？
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.
- 9d ago First seen · 156 lines · 151 tokens per session scan A 50a30f50d049
f34-upward строго-downward-仁 is a skill published in the GitHub repository ace3000chao/book2startup (80 stars, last pushed 4mo ago), licensed MIT. It adds 151 tokens to every session and 2,315 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
hackman-enabling-conditions
Diagnoses and designs team effectiveness using Hackman's six enabling conditions: a real team, compelling direction, right people, sound structure, supportive context, and expert coaching. Shifts focus from blaming team members to establishing the structural and environmental conditions that make high performance…
leadership-style-adaptation
Provides practical self-diagnosis exercises and daily habits for recognising when a leader's default style fails and adapting in real time. Focuses on behavioural flexibility rather than theory -- how to read the room, when to shift approach, and how to stay authentic while flexing. Complements the theoretical models…
situational-leadership
Matches leadership style to follower development level using Hersey and Blanchard's Situational Leadership model. Maps four styles -- directing, coaching, supporting, delegating -- to four development levels based on competence and commitment per task. Use when diagnosing style mismatches causing disengagement…
radical-candor
Applies Kim Scott's Radical Candor framework to improve feedback culture by balancing caring personally with challenging directly. Maps management behaviour across four quadrants: Radical Candor, Ruinous Empathy, Obnoxious Aggression, and Manipulative Insincerity. Use when preparing difficult performance…
apply-enabling-structure
Use when building or leading a team, organization, or system — to create the conditions, remove the obstacles, and design the structures that let people execute with high autonomy, rather than directing through control, because the best leaders are barely visible in their teams' day-to-day success.
apply-managerial-leverage
Use when deciding how to allocate a manager's or leader's limited time across competing activities — before defaulting to whatever is most urgent, estimate each candidate activity's leverage (how many people's output it affects, for how long, and whether it requires your specific position), because a manager's actual…