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 p09git 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/p09)<a href="https://agentmods.dev/skills/ace3000chao/book2startup/p09"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/p09/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/p09"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/p09.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 | $0.00093 | $0.01725 |
| Opus 5 | $0.00046 | $0.00863 |
| Sonnet 5 | $0.00019 | $0.00345 |
| Haiku 4.5 | $0.00009 | $0.00172 |
Grade A, and why
p09净从秽生明从暗出 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
净从秽生明从暗出原则
R — 原文 (Reading)
"粪虫至秽，变为蝉而饮露于秋风；腐草无光，化为萤而跃彩于夏月。因知洁常自污出，明每从晦生也。"
— 洪应明, 《菜根谭·净从秽生 明从暗出》
I — 方法论骨架 (Interpretation)
- 洁净不是从洁净中来，而是从污秽中诞生的。 蝉的幼虫在粪土中生活，最后却饮露于秋风。
- 光明不是从光明中来，而是从黑暗中诞生的。 腐草无光，化为萤火虫，在夏夜跃彩。
- 困境/污秽不是终点，是蜕变的起点。 重要的不是你身处什么环境，而是你是否能完成转化。
- "至秽"和"无光"是过程，不是定性。 粪虫在那个阶段是秽的，但它没有停留在那个状态。
- 逆境中的绝望是因为只看到当前，没看到转化后的可能性。 看到萤火虫时，没人记得它曾经是腐草。
A1 — 书中的应用 (Past Application)
案例: 洪应明论"粪虫变蝉、腐草化萤"
- 问题: 如何理解"洁净"与"污秽"、"光明"与"黑暗"的辩证关系
- 方法论的使用: 洪应明用两个自然界的转化（粪虫→蝉、腐草→萤火虫）来说明洁净和光明不是凭空产生的，而是从对立面转化而来
- 结论: 困境不是绝境，而是转化的必经阶段；"至秽"是过程，"饮露"是结果
- 结果: 处于污秽中时，不要自暴自弃，因为污秽可能是通向洁净的路径
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 处于逆境困境，感到绝望想放弃时 — "我不想再撑了"、"我真的没希望了吗？"
- 被糟糕的环境困住，觉得"出淤泥而不染"太难时 — "这个环境太差了，我能怎么办？"、"在这里我只会越来越糟"
- 看到别人成功，对比自己的困境时 — "为什么他行我不行？"、"我是不是这辈子就这样了？"
语言信号 (用户的话里出现这些就应激活)
- "我运气太差了"
- "为什么偏偏是我？"
- "这个环境太恶劣了"
- "我还有希望吗？"
- "我是不是没救了？"
- "别人怎么都比我好？"
与相邻 skill 的区分
- 与
p16动中真静的区别: p16是"动中静"——在喧嚣中保持内心平静；p09是"从秽到净"——在污秽中完成蜕变。p16更偏向心态，p09更偏向方向和转化 - 与
p04快意早回头（逆境部分）: p04的"败后或反成功"是线性思维（失败→成功），p09的"净从秽生"是辩证思维（污秽是净化的必经阶段）
E — 可执行步骤 (Execution)
当 skill 被激活后，agent 应按以下步骤执行:
-
识别用户是在"当前困境"中看不到出口 — 不是需要具体方案，而是需要重新定义困境的意义
- 完成标准: 用户明确自己感到绝望的不是当前状态，而是看不到转化可能性
-
用"粪虫→蝉"测试：你现在的"秽"是什么？这个状态有没有可能成为转化的一部分？
- 完成标准: 用户找到当前困境与未来目标之间的潜在联系
-
找到"饮露于秋风"那个画面——转化完成后的景象是什么？
- 完成标准: 用户能够描述转化后的自己/处境，建立希望感
B — 边界 (Boundary) ★
不要在以下情况使用此 skill
- 需要实际行动方案时：只给用户乐观心态但不给具体路径，可能让用户继续空想
- 严重心理健康问题：严重抑郁患者需要专业心理帮助，不能用这种原则替代
- 客观条件恶劣到生命安全受威胁时：此时应先脱离危险，不是"享受污秽"
作者在书中警告的失败模式
- 欲情道狭（来自反例ce08）：沉迷于物欲名利的追逐，患得患失，利欲熏心
- 机制：追求物欲如同走狭窄泥泞小路，步步陷阱，陷入后无力自拔。执着于"结果"而不能接受"过程"
作者的盲点 / 时代局限
- 某些困境确实是客观条件造成的，不是"心态问题"，需要实际改变环境而非调整心态
- "净从秽出"不能被滥用为"你应该感恩困境"——这可能合理化虐待和剥削
容易混淆的邻近方法论
- 苦中真乐(p16)：p16强调在苦中保持喜乐；p09强调秽→净的转化过程，p16更强调主观感受，p09更强调客观转化路径
- 塞翁失马(p07历史案例)：p07案例强调祸福转化；p09强调转化需要过程和等待，不是简单的"坏事变好事"
相关 skills (阶段 3 填充)
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 · 123 lines · 93 tokens per session scan A ac8c7e2e36cf
p09净从秽生明从暗出 is a skill published in the GitHub repository ace3000chao/book2startup (80 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 1,725 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
stoic-fortitude-and-resilience
Provides the philosophical foundations of inner strength, endurance, and anti-fragility drawn from Stoic thought, teaching entrepreneurs why hardship strengthens character, how to prepare mentally for adversity through voluntary discomfort, and why patience and perseverance outperform luck as long-term competitive…
stoic-problem-solving
Teaches Marcus Aurelius's central method for converting obstacles into advantages, covering the reverse clause, creative reframing, persistence under adversity, and the discipline of focused action. Use when a startup faces setbacks that feel terminal, when market conditions shift against you, when key plans fail and…
api-rate-limit-handler
Implement bounded, idempotency-aware API throttling, backoff, and retry handling for 429 and transient 5xx responses.
acceptance
A personal decision framework for difficult situations, built around three choices: change the situation, accept it, or leave it.
chain-patterns
Chain patterns for multi-phase pipelines: MCP detection, handoff files, checkpoint-resume, worktree agents, CronCreate monitoring. Use when building or debugging a pipeline skill.
langgraph
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph…