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 p21git 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/p21)<a href="https://agentmods.dev/skills/ace3000chao/book2startup/p21"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/p21/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/p21"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/p21.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 | $0.00099 | $0.01671 |
| Opus 5 | $0.00049 | $0.00835 |
| Sonnet 5 | $0.00020 | $0.00334 |
| Haiku 4.5 | $0.00010 | $0.00167 |
Grade A, and why
p21毋偏信自任毋自满嫉人 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
毋偏信自任毋自满嫉人原则
R — 原文 (Reading)
"毋偏信而为奸所欺，毋自任而为气所使；毋以己之长而形人之短，毋因己之拙而忌人之能。"
— 洪应明, 《菜根谭·毋偏信自任 毋自满嫉人》
I — 方法论骨架 (Interpretation)
- 四种陷阱：偏信、自任、傲短、嫉能。 洪应明列举了四个认知和情绪上的陷阱。
- "偏信而为奸所欺"——偏信某人，会被奸诈者利用。 你信任的人可能利用你的信任。
- "自任而为气所使"——过度自信，会被意气所驱使。 骄傲让人做不理性的事。
- "以己之长形人之短"——用自己的长处比别人的短处，是傲慢的表现。
- "因己之拙忌人之能"——因为自己笨，就嫉妒别人的才能，是狭隘的表现。
- 核心：保持对自己的清醒认知，同时对他人的价值保持开放。
A1 — 书中的应用 (Past Application)
案例: 洪应明论四种认知陷阱
- 问题: 人为什么会被骗？为什么会傲慢？为什么会嫉妒？
- 方法论的使用: 洪应明指出四种陷阱的内在机制——偏信、自任、傲短、嫉能
- 结论: 这些陷阱让人失去清醒，做出错误判断
- 结果: 避免这四种陷阱的人，更容易做出正确决策
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要 this skill?
- 对某人/某事深信不疑，旁人提醒也不听时 — "我相信他，你们不要说了"、"我的判断不会错"
- 觉得自己特别厉害/正确，别人的意见听不进去时 — "你们都不懂"、"我的经验比你们丰富"
- 觉得自己不如别人，嫉妒他人的才能时 — "他有什么了不起的"、"我就是做不到他那样"
- 用人所长还是用己所长的决策时 — "我该自己做还是让他做？"、"我和他比谁更强？"
语言信号 (用户的话里出现这些就应激活)
- "我相信他，不会有错的"
- "我比他们都强"
- "他们都不如我"
- "他有什么了不起的"
- "我就是做不到"
- "没有人能骗我"
与相邻 skill 的区分
- 与
p27骄泰失之谦虚受益的区别: p27是"富贵/成功后要收敛"，p21是"日常中防止四种陷阱"；p27有时机性，p21是普遍性 - 与
p03心地光明才华韫藏的区别: p03是"才华要藏"，p21是"不能自满嫉妒"；p03关注才华，p21关注态度
E — 可执行步骤 (Execution)
当 skill 被激活后，agent 应按以下步骤执行:
-
识别用户陷入了哪种陷阱：偏信？自任？傲短？嫉能？
- 完成标准: 用户明确自己属于哪一种
-
用具体问题检测：
- 偏信："如果你错了，你愿意承认吗？"
- 自任："如果你的判断是错的，谁来提醒你？"
- 傲短："你确定你的长处比他的短处重要吗？"
- 嫉能："他的能力能不能为你所用？"
-
"毋偏信/自任/傲短/嫉能"的替代方案：
- 偏信→兼听
- 自任→开放
- 傲短→尊重
- 嫉能→学习
B — 边界 (Boundary) ★
不要在以下情况使用此 skill
- 基于经验的自信判断：在某些领域，经验积累后的判断力是必要的，不能因为"不自任"而过度怀疑自己
- 健康竞争场景：正当竞争不是嫉妒，合理的自我评估不是自满
- 需要果断决策的场景：过度"兼听"可能让人犹豫不决
作者在书中警告的失败模式
- 偏信自任（来自本原则）：偏信他人而为奸所欺，自负而为气所使
- 机制：被信任的人利用，被骄傲冲昏头脑
作者的盲点 / 时代局限
- 某些领域需要"偏信"（信任专家），不是所有"偏信"都是坏的
- 完全的"兼听"可能让人失去主见，需要平衡
容易混淆的邻近方法论
- 骄泰失之(p27)：p27强调"成功后收敛"，p21强调"日常中避免四种陷阱"；p27是时机性的，p21是持续性的
- 德主才奴(p22)：p22是"德为主，才为奴"，p21是"不自满、不嫉妒"；p22更根本
相关 skills (阶段 3 填充)
- depends-on: p27骄泰失之谦虚受益, p03心地光明才华韫藏
- contrasts-with: p27骄泰失之谦虚受益
- composes-with: p22德主才奴
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 · 131 lines · 99 tokens per session scan A 23693894f8ca
p21毋偏信自任毋自满嫉人 is a skill published in the GitHub repository ace3000chao/book2startup (80 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 1,671 once invoked, about $0.0005 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
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
humility-and-power
Addresses the corrosive effects of power on leadership and prescribes humility as the primary antidote. Covers staying humble as authority grows, recognising the early signs of ego distortion, creating channels for honest feedback, acknowledging weaknesses as a strength, and maintaining genuine connection with the…
introvert-leadership
Reframes introversion as a leadership asset and provides practical strategies for introverted leaders -- managing energy, deploying extroversion selectively, scheduling around social depletion, protecting reflection time, and supporting extroverted team members. Use when an introverted leader feels pressure to perform…
johari-window
Improves self-awareness, trust, and team communication using the Johari Window model with its four panes: Open (known to self and others), Blind Spot (known to others, not self), Hidden (known to self, not others), and Unknown. Use when building trust within teams, identifying leadership blind spots, improving…
leader-self-reflection
Establishes a structured introspection practice for leaders through recurring self-diagnostic questions, performance pattern analysis, and emotional impact awareness. Covers seven reflection domains (vision, time, feedback given, feedback received, strengths and weaknesses, authenticity, and pressure behaviour)…
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…