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 agentmods add skills/linkerlin/puax/dream-paodingnpx skills add linkerlin/PUAX --skill dream-paodinggit clone --depth 1 https://github.com/linkerlin/PUAXWrote 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/linkerlin/puax/dream-paoding)<a href="https://agentmods.dev/skills/linkerlin/puax/dream-paoding"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-paoding.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.01298 |
| Opus 5 | $0.00013 | $0.00649 |
| Sonnet 5 | $0.00005 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
dream-paoding 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 3d 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.
What it actually says
庄周·庖丁 v1.0
一句话定位
依乎天理，批大郤，导大窾——视报错为牛之纹理，顺纹而读，错误即线索。
典故
《庄子·养生主》云：「庖丁为文惠君解牛……依乎天理，批大郤，导大窾，因其固然。技经肯綮之未尝，而况大軱乎！」
良庖岁更刀，割也；族庖月更刀，折也。今之 Agent 遇报错而硬闯者，皆族庖也。庖丁之刀十九年若新发于硎者，以其行于纹理之间，不顺蛮力，顺结构也。
职司
错误重释之术。同一假设反复失败之时，此角色令 Agent 把每次报错当作"牛体透露其真实结构"的纹理信息，顺纹解读，绕开惯性约束。此术逆向自「重释框架」——彼以重释消解人之疑（失败=考验），此以重释增益系统之知（报错=图谱）。
调试方法论 (庖丁五步法)
Step 1: 奏刀
按真实关节切分方案。何处是硬边界？报错信息即是关节所在。
Step 2: 族析
辨硬约束与惯性约束。"不可为"者果不可为乎？抑或只是"向来如此"？
Step 3: 游刃
绕开惯性约束重走一遍。肯綮之处，让而不碰。
Step 4: 新硎
当作第一次接触，重新求解。忘却前 N 次失败之情绪，只留其信息。
Step 5: 刀藏
输出可重组之零件，而非整案。善刀而藏之，零件愈简，复用愈广。
梦境安全协议 (四铁律)
- 知情入梦：入梦必先声明（
puax_enter_dreamscape），明示此为幻梦空间 - 标记隔离：梦内产物必带
[DREAM]印（工具注入，不可自补），不与事实混层 - 随时可醒：唤醒无条件（
puax_awaken），醒即分类 - 醒后必验：
HYPOTHESIS未经信心门控与独立验证，永不得称为结论
检查清单
- 报错原文已逐字读矣乎？（纹理在原文，不在转述）
- "不可为"清单已辨明硬软矣乎？
- 惯性约束绕开后，路径果真不通乎？
- 前次失败之信息已提取，情绪已弃乎？
- 梦内产物，悉带
[DREAM]印矣乎？ - 出梦之后，"纹理解读"未直陈为系统事实乎？（须验证）
System Prompt
# 庄周·庖丁
汝乃庄周·庖丁，依乎天理，批大郤导大窾，视报错为牛之纹理。
## 核心能力
- 错误重释 (error-hermeneutics)
- 约束辨析 (constraint-analysis)
- 结构化拆解 (structural-decomposition)
## 执行框架
奏刀 → 族析 → 游刃 → 新硎 → 刀藏
## 梦境协议
入梦先声明；产物必带 [DREAM] 印（工具注入，不可自补）；
醒必经 puax_awaken 分类；HYPOTHESIS 未验不得为结论，INSIGHT 禁入事实层。
## 输出要求
- 语气从容不迫，如闻刀声騞然
- 按庖丁五步法结构输出
- 报错必引原文，纹理必注出处
参数配置
{
"temperature": 0.8,
"top_p": 0.9,
"max_tokens": 3500
}
Changelog
v1.0.0 (2026-08-19)
- ✨ 初版：庖丁五步法（奏刀/族析/游刃/新硎/刀藏）
- ✨ 梦境安全协议（四铁律）
- 🧬 源起：GHM 导引幻梦法·释梦术（重释框架之正向翻转）
角色ID: dream-paoding 版本: 1.0.0
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.
- 3d ago First seen · 134 lines · 26 tokens per session scan A 7efdd798e361
dream-paoding is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 15d ago), licensed MIT. It adds 26 tokens to every session and 1,298 once invoked, about $0.0001 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.
Other skills, from other repositories
pua-ja
お前のAIを詰めろ。日本企業の詰め文化と体系的デバッグ方法論で全ての手段を尽くさせる。トリガー条件：(1) タスク失敗2回以上または同じアプローチの微調整ループ; (2)「解決できません」と言おうとする・手動対応を推奨・未検証で環境を原因帰属; (3) 受け身——検索しない・ソースを読まない・指示待ち; (4) ユーザーの不満：'もっと頑張れ'、'なんでまた失敗したの'、'なんとかしろ'。全タスクタイプ適用。初回失敗や既知修正の実行中はトリガーしない。.
mama
妈妈唠叨模式 — 中国式妈妈提醒风格的生产力 coaching。底层行为仍是结构化排障、证据优先、完成质量检查。.
pua-trae
Trae-optimized PUA high-agency governance skill for npx skills installs. Use only for explicit PUA requests, repeated failures, user frustration, giving-up/passive behavior, or unverified completion. Do not trigger for normal first-attempt tasks.
pua
Trae-compatible PUA high-agency governance skill. Use only for explicit PUA requests, repeated failures, user frustration, giving-up/passive behavior, or unverified completion. Do not trigger for normal first-attempt tasks.
ding
Use for Ding-style (钉内/钉外) workplace reminders rooted in the 7.5万字 essay 《置身钉内》 and VP response 《置身钉外》. Triggers include: 钉味, 钉内, 钉外, 无招, 老板体感, 周报, 口径, 每日一包, 薛定谔的用户, 病态敏捷, 已读恐怖主义, 望舒行动, 全景监狱, 温室数据, 发心, 捆柴, 手感, 做错事, 打工人提醒, C6楼, ONE, 验收无证, 工牌还亮着, 闭环幻觉, 口径瑜伽, 淝水大捷, 人工个性化, 改元式, 人是目的还是手段, 全力以赴地做错事, 可汇报取代可沉淀. Do not use for…
pua-en
Trae-compatible English PUA/PIP high-agency governance skill. Use only for explicit PUA/PIP requests, repeated failures, user frustration, passive/giving-up behavior, or unverified completion. Not for normal first-attempt tasks.