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 f18git 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/f18)<a href="https://agentmods.dev/skills/ace3000chao/book2startup/f18"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/f18/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/f18"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/f18.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 | $0.00134 | $0.01850 |
| Opus 5 | $0.00067 | $0.00925 |
| Sonnet 5 | $0.00027 | $0.00370 |
| Haiku 4.5 | $0.00013 | $0.00185 |
Grade A, and why
f18-listen-both-sides 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
兼听则明决策框架
R — 原文 (Reading)
"毋因群疑而阻独见，毋任己意而废人言；毋私小惠而伤大体，毋借公论以快私情。"
— 洪应明, 辨别是非 认识大体
I — 方法论骨架 (Interpretation)
这是一个决策偏见自检清单，在拍板之前逐一核查四种常见认知偏误：
- 从众偏误：不因为多数人怀疑，就放弃自己的独立判断。多数人反对不等于你错。
- 固执偏误：不因为坚持己见，就忽视他人的反对意见。自己的判断也需要被挑战。
- 小惠伤大：不因为局部的小恩小惠，破坏了整体的大局利益。
- 公论私用：不假借"大家都这么说"的公共舆论，来满足自己的私心。
核心逻辑：决策质量取决于偏见被识别的速度，而不是决策速度。这四条是四个"触发器"，遇到任何一个就亮红灯。
A1 — 书中的应用 (Past Application)
案例 1: 秦桧和珅依附权势身首异处
- 问题: 南宋秦桧、清朝和珅面临选择：坚守道德原则还是依附权势求取富贵
- 方法论的使用: 若以"兼听"原则审视，依附权势虽能满足一时私欲，但违背了"天理"这个"公论"；而以"独见"审视，道德才是真正的长远之计
- 结论: 依附权势短期看似得利，实则把自己命运交给他人控制
- 结果: 秦桧跪像至今被人唾弃，和珅被嘉庆赐死，身首异处凄凉万古
案例 2: 李斯贪权身败名裂
- 问题: 秦朝李斯面临是否继续追逐更大权力的诱惑
- 方法论的使用: 若以"毋私小惠而伤大体"自检，权力越大越危险；若以"毋任己意"自检，则应听取扶苏的劝谏而非赵高的胁迫
- 结论: 贪恋权位是"以短攻短"，最终失去一切
- 结果: 李斯被腰斩于咸阳，夷三族
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 团队讨论僵局：开会时大部分人反对某一个方案，但主事者内心仍想坚持
- 个人决策前夜：做了一个决定，但在发布前想最后再核查一遍是否陷入了某种偏误
- 被"政治正确"裹挟：有人用"大家都是这么想的"、"历史证明这是对的"等公共舆论施压
语言信号 (用户的话里出现这些就应激活)
- "大家都说不行，但我总觉得……"
- "我担心这个决定太主观了"
- "怕别人说我独断专行"
- "这样做会不会因为小利失了大局？"
- "他说的好像也有道理，但直觉告诉我不对"
- "这事就这么定了，谁也别劝我"（反向信号）
与相邻 skill 的区分
- 与
f04 中和处世决策框架的区别：f04关注性格偏激（躁/刻/执），本框架关注决策时的信息来源偏误（从众/固执/私惠/公论私用） - 与
f14 观人四步框架的区别：f14是观察他人的方法，本框架是审视自己决策过程的偏见清单
E — 可执行步骤 (Execution)
当 skill 被激活后, agent 应按以下步骤执行:
-
亮出四个偏见触发器
- 完成标准: 用户看到"从众偏误 / 固执偏误 / 小惠伤大 / 公论私用"四个词，并理解各自的含义
-
逐条核查
- 完成标准: 针对当前决策，逐一回答：这四条中，哪条最可能在发生？用户给出明确判断
- 判停条件: 若四条都没有触发（用户清晰判断无偏），则跳过步骤3，直接输出"此决策无需修正"
-
输出修正建议
- 完成标准: 对触发的那一条，给出具体的"修正动作"建议（例如：若触发"从众偏误"，则建议"把你的独见写成利弊分析，给一个你信任的局外人看"）
B — 边界 (Boundary) ★
不要在以下情况使用此 skill
- 纯信息查询类问题（问"今天天气如何"不需要核查偏见）
- 已经有明确制度或流程约束的常规决策（这时候"偏见"可能是对的）
- 紧急危机决策（时间紧迫，来不及多方征询，需要用其他skill如
f33 不动声色应变框架）
作者在书中警告的失败模式
- ce07（谨言慎行不及）："十语九中，未必称奇，一语不中，则愆尤骈集"——话多谋多反而更容易招祸，本框架不是说越多越好，而是在决策前的质量核查
- ce08（欲情道狭）："人欲路上甚窄，才寄迹，眼前俱是荆棘泥涂"——若决策被私利主导，则任何判断都会导向荆棘
容易混淆的邻近方法论
- f04（中和处世）：关注的是性格特征（太急/太刻/太执），本框架关注的是信息来源和动机（谁在说/为什么说/说的是谁的利）
- f09（天理人欲分判）：提供方向性判断（公利vs私利），本框架提供的是决策过程检查清单
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 · 128 lines · 134 tokens per session scan A 3e7af64ff543
f18-listen-both-sides is a skill published in the GitHub repository ace3000chao/book2startup (80 stars, last pushed 4mo ago), licensed MIT. It adds 134 tokens to every session and 1,850 once invoked, about $0.0007 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
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-opportunity-cost
Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.
thinking-red-team
For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
thinking-circle-of-competence
Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.