What is p14谨言慎行?

A principle of thinking before speaking or acting, especially when emotions are running high. It favors careful, plain communication over hurried words or clever-looking actions.

Use it before sending a message, making a public statement, or committing to a plan you have not considered fully. It helps review what you intend to say or do.

A single careless remark or failed decision can attract more criticism than many correct ones receive praise. Pausing lowers the chance of avoidable mistakes.

p14谨言慎行 — Skill for Claude Code and Codex by ace3000chao

Install

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.

Any agent

npx skills add ace3000chao/book2startup --skill p14

Clone the repo

git clone --depth 1 https://github.com/ace3000chao/book2startup

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ace3000chao/book2startup/p14/github.svg)](https://agentmods.dev/skills/ace3000chao/book2startup/p14)

Your own site

<a href="https://agentmods.dev/skills/ace3000chao/book2startup/p14"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/p14/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ace3000chao/book2startup/p14"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/p14.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,658 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00078	$0.01658
Opus 5	$0.00039	$0.00829
Sonnet 5	$0.00016	$0.00332
Haiku 4.5	$0.00008	$0.00166

Measured 9d ago against content hash a63a5b0193c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

p14谨言慎行 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.

菜根谭skills/skills/p14/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

谨言慎行原则

R — 原文 (Reading)

"十语九中，未必称奇，一语不中，则愆尤骈集；十谋九成，未必归功，一谋不成，则訾议丛兴。君子所以宁默毋躁，宁拙无巧。"

— 洪应明, 《菜根谭·谨言慎行君子之道》

I — 方法论骨架 (Interpretation)

说话和谋事的回报是不对称的。 说对十句没人记得，说错一句怨尤集身；谋对九次没人称赞，谋错一次众议蜂起。
在这个不对称下，最优策略是沉默和拙朴。 不是说不能说话，而是不要为了表现而多言；不是说不能谋事，而是不要为了邀功而多谋。
"宁默毋躁"——宁可沉默，不要急躁。 急躁说话容易出错，沉默至少不会说错。
"宁拙无巧"——宁可笨拙，不要耍巧。 笨拙做事至少扎实，耍巧容易露馅。
核心：减少"被评价"的次数，就是减少"被负面评价"的概率。 不说话、不多谋，就不会有失败可被评价。

A1 — 书中的应用 (Past Application)

案例: 洪应明论"十语九中一语不中则愆尤骈集"

问题: 为什么做了很多、说了很多，却换来负面评价？
方法论的使用: 洪应明指出这个不对称性——正面贡献不被记得，负面失误被放大
结论: 君子选择"宁默毋躁，宁拙无巧"——通过减少失败概率来保护声誉
结果: 少说少错，多说多错；少谋少败，多谋多败

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

说完话后担心是不是说多了/说错了 — "我是不是不该说这个？"、"我这样说会不会让人误会？"
准备发言/演讲，担心说不好时 — "我不知道该说什么"、"万一我说错了怎么办"
做决策前犹豫要不要再想想 — "我是不是太冲动了？"、"我是不是考虑得太少了？"
看到别人说错话/做错决定，觉得自己也要小心时 — "我以后也要谨慎点"、"言多必失"

语言信号 (用户的话里出现这些就应激活)

"我是不是说多了？"
"我会不会说错话？"
"我是不是太冲动了？"
"我还没想好该怎么说"
"言多必失啊"
"我说了会不会有问题？"

与相邻 skill 的区分

与 p13中和为福偏激为灾 的区别: p13是整体性格（不要太急躁），p14是具体行为（说话和谋事要谨慎）；p13是战略，p14是战术
与 p20放下屠刀 的区别: p20是情绪控制（怒火时猛然转念），p14是日常行为（说话前先想想）；p20是应急反应，p14是长期习惯

E — 可执行步骤 (Execution)

当 skill 被激活后，agent 应按以下步骤执行:

识别用户当前是要"说"还是要"做" — 说话前还是说话后？谋事前还是谋事后？
- 完成标准: 用户明确自己的情境
说话前：用"十语九中"测试——这句话说出来，十个人里有几个会记住？有一个说错的后果是什么？
- 完成标准: 用户权衡说话的风险和收益
说话后/做错后：用"宁默毋躁"测试——现在补救会越描越黑，还是沉默更好？
- 完成标准: 用户决定是补救还是沉默

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

需要清晰表达观点的场景：如重要谈判、汇报、领导力展现，此时过度沉默可能被认为没有立场
创意发散阶段：需要大量试错和讨论，不能因为"怕说错"而不说
关系中的真诚沟通：有时需要"说错话"才能表达真实感受

作者在书中警告的失败模式

谨言慎行不及（来自反例ce07）：说话不假思索脱口而出，计谋过度患得患失，总想表现自己的聪明
机制：话说多错多，十句对九句无人称赞，一句不中则怨尤集身

作者的盲点 / 时代局限

现代职场强调"存在感"和"声音"，过度沉默可能影响职业发展
某些组织文化鼓励"大胆发言"，此时"宁默毋躁"可能被视为消极

容易混淆的邻近方法论

中和为福(p13)：p13更强调性格层面的平衡，p14更强调说话和谋事的行为层面
心地光明(p03)：p03是"心地要光明"，p14是"说话要谨慎"——p03要求透明，p14要求收敛

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.

test-prompts.json 3.4 KB

Changes

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 · 124 lines · 78 tokens per session scan A a63a5b0193c6

Subscribe to this mod's changes

p14谨言慎行 is a skill published in the GitHub repository ace3000chao/book2startup (81 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 1,658 once invoked, about $0.0004 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.

Productivity caution self-control speech

voice-commander

A voice-command manager for registering commands, defining macros, and linking commands into chains.

chainlesschain/chainlesschain · 32 tokens

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…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

p14谨言慎行