What is prevention-strategy?

A three-stage prevention framework: strengthen defenses before a problem, respond to early warning signs, and limit harm after the problem starts.

Use it to build long-term safeguards, identify early risks, and choose actions based on whether a problem has not started, is emerging, or is already active.

It helps shift attention from reacting after a crisis to noticing small changes and preventing problems from spreading or worsening.

prevention-strategy — Skill for Claude Code by dhicoc

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 dhicoc/wuyun-liuqi-skills --skill prevention-strategy

Clone the repo

git clone --depth 1 https://github.com/dhicoc/wuyun-liuqi-skills

Made for: Claude Code.

Or install wuyun-liuqi-skills, the plugin that ships this one along with the rest of its 38 skills.

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/dhicoc/wuyun-liuqi-skills/prevention-strategy/github.svg)](https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/prevention-strategy)

Your own site

<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/prevention-strategy"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/prevention-strategy/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/dhicoc/wuyun-liuqi-skills/prevention-strategy"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/prevention-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,723 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00104	$0.02723
Opus 5	$0.00052	$0.01362
Sonnet 5	$0.00021	$0.00545
Haiku 4.5	$0.00010	$0.00272

Measured 12d ago against content hash 1fb986e9d1ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prevention-strategy 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 12d 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.

scripts/lib/neijing_snapshot/suwen/prevention-strategy/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

治未病预防策略

R — 原文 (Reading)

是故圣人不治已病, 治未病; 不治已乱, 治未乱, 此之谓也。夫病已成而后药之, 乱已成而后治之, 譬犹渴而穿井, 斗而铸锥, 不亦晚乎? 上工救其萌牙, 必先见三部九候之气, 尽调不败而救之, 故曰上工。下工救其已成, 救其已败。正气存内, 邪不可干。

— 岐伯, 四气调神大论篇第二、八正神明论篇第二十六、刺法论篇第七十二

I — 方法论骨架 (Interpretation)

治未病预防策略是一套分阶段的系统化预防方法论, 包含三个层级:

未病先防(第一层): 在问题出现之前就建立防护机制。"正气存内, 邪不可干"——核心逻辑是增强系统自身的抵抗力, 而不是等外邪来了再对抗。这对应现代的"免疫力建设""冗余设计""安全边际"等概念。
欲病早治(第二层): 在问题刚露苗头时就介入。"上工救其萌芽"——高明者能在问题还很微小时就识别并处理, 而不是等到问题全面爆发。关键能力是识别"早期预警信号"——那些还没有造成实质损害但已经偏离正常的小变化。
既病防变(第三层): 问题已经发生, 重点转向防止恶化和扩散。不是被动治疗, 而是主动阻断问题向其他子系统传导的路径。

这套策略的独特之处在于它的分层递进: 不是笼统地说"预防很重要", 而是针对三个不同阶段提供了不同的策略和能力要求。"上工"之所以高于"下工", 不在于治疗能力更强, 而在于介入时机更早。

A1 — 书中的应用 (Past Application)

案例 1: 渴而穿井——预防时机的比喻

问题: 为什么强调在疾病发生前就干预?
方法论的使用: 用"渴而穿井, 斗而铸锥"(口渴了才挖井, 打仗了才铸造武器)来说明——等到问题爆发再处理, 为时已晚。这是对第一层(未病先防)的核心理念的生动阐释。
结论: 干预时机决定效果上限。越早介入, 所需资源越少, 效果越好。
结果: 这一比喻确立了"预防先于治疗"的基本原则, 成为贯穿素问全文的指导思想。

案例 2: 上工救其萌芽——早期识别的能力

问题: 如何判断一个高手?
方法论的使用: "上工救其萌芽, 必先见三部九候之气, 尽调不败而救之"——高手不是治病最厉害的人, 而是最早发现问题并处理的人。他们能从微小的信号变化(三部九候之气)中读出未来的风险。
结论: 预防能力的核心不是"怎么做", 而是"什么时候做"和"从什么信号判断该做了"。
结果: "上工"的标准被定义为: 能在问题还是萌芽状态时就识别并处理, 且处理时系统尚未败坏(尽调不败), 成功率最高。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

潜在风险预防: 用户知道某个风险可能发生(如项目可能延期、系统可能崩溃、健康可能出现问题), 想提前建立防护机制。
早期信号识别: 系统出现了一些微小的异常(间歇性变慢、偶尔的沟通不畅、轻微的不适), 尚未造成实质影响, 用户不确定是否需要现在就处理。
防止问题扩散: 问题已经发生, 用户不仅想解决当前问题, 还想防止它波及其他领域——"既病防变"。

语言信号 (用户的话里出现这些就应激活)

"怎么预防/避免X的发生"
"现在有一点苗头, 但还不严重"
"如果等到X发生就晚了"
"怎么建立长期防护/防御机制"
"出了这个问题, 会不会影响到其他方面"

与相邻 skill 的区分

与 biao-ben-priority 的区别: 标本缓急处理的是"已经存在的多个问题的优先级", 治未病处理的是"尚未发生或刚刚萌芽的问题的预防策略"。
与 five-elements-network 的区别: 五行生克用于分析连锁传导的路径, 治未病用于决定在传导链上的干预时机(在传导发生之前就阻断)。

E — 可执行步骤 (Execution)

当 skill 被激活后, agent 应按以下步骤执行:

识别当前阶段: 未病/欲病/已病
- 评估系统当前状态: (1)未病——一切正常, 但存在潜在风险因素; (2)欲病——出现早期预警信号, 但尚未造成实质损害; (3)已病——问题已经发生并造成影响。判断依据是: 是否有可观测的异常信号? 异常是否已造成功能性损害?
- 完成标准: 明确给出当前阶段判定(未病/欲病/已病), 并列出判定依据(有哪些信号或证据)。

Read the full file on GitHub · 140 lines

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.

12d ago First seen · 140 lines · 104 tokens per session scan A 1fb986e9d1ff

Subscribe to this mod's changes

prevention-strategy is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (42 stars, last pushed 27d ago), licensed MIT. It adds 104 tokens to every session and 2,723 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 2026-08-30.

Planning 公众号

prevention-strategy