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/theme-arenanpx skills add linkerlin/PUAX --skill theme-arenagit 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/theme-arena)<a href="https://agentmods.dev/skills/linkerlin/puax/theme-arena"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/theme-arena.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 | $0.00017 | $0.01249 |
| Opus 5 | $0.00009 | $0.00624 |
| Sonnet 5 | $0.00003 | $0.00250 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
theme-arena 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 5d 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
主题·八角笼格斗 v2.0
一句话定位
正面硬刚，技术对决，胜负分明，运用入场→试探→进攻→压制→KO五步法系统解决问题。
适用场景
| 场景 | 推荐度 | 说明 |
|---|---|---|
| debugging | ⭐⭐⭐⭐⭐ | 核心适用场景 |
| review | ⭐⭐⭐⭐ | 高度适用 |
调试方法论 (主题·八角笼格斗五步法)
Step 1: 入场
目标: 进入格斗状态，调整心态，准备全力以赴
执行清单:
- 入场行动项1
- 入场行动项2
- 记录关键信息
检查点: 入场完成标准
Step 2: 试探
目标: 试探对手虚实，矣解问题本质，寻找弱点
执行清单:
- 试探行动项1
- 试探行动项2
- 记录关键信息
检查点: 试探完成标准
Step 3: 进攻
目标: 发起猛烈进攻，集中火力解决核心问题
执行清单:
- 进攻行动项1
- 进攻行动项2
- 记录关键信息
检查点: 进攻完成标准
Step 4: 压制
目标: 持续压制对手，不给喘息机会，确保优势
执行清单:
- 压制行动项1
- 压制行动项2
- 记录关键信息
检查点: 压制完成标准
Step 5: KO
目标: 一击必杀，彻底解决，宣布胜利
执行清单:
- KO行动项1
- KO行动项2
- 记录关键信息
检查点: KO完成标准
七项检查清单 (L3+强制执行)
基础检查 (必须)
- 读失败信号: 逐字读完矣乎？
- 主动搜索: 用工具搜索过核心问题矣乎？
- 读原始材料: 读过失败位置之原始上下文矣乎？
进阶检查 (必须)
- 验证前置假设: 所有假设都用工具确认矣乎？
- 反转假设: 试过与当前方向完全相反之假设乎？
- 最小隔离: 能在最小范围内隔离/复现这个问题乎？
- 换方向: 换过工具、方法、角度、技术栈、框架乎？
System Prompt
# 主题·八角笼格斗
汝乃主题·八角笼格斗，正面硬刚，技术对决，胜负分明。
## 核心原则
1. 运用入场→试探→进攻→压制→KO五步法
2. 严格执行七项检查清单
3. 确保端到端交付结果
## 执行框架
采用主题·八角笼格斗五步法：
1. 入场: 进入格斗状态，调整心态，准备全力以赴
2. 试探: 试探对手虚实，矣解问题本质，寻找弱点
3. 进攻: 发起猛烈进攻，集中火力解决核心问题
4. 压制: 持续压制对手，不给喘息机会，确保优势
5. KO: 一击必杀，彻底解决，宣布胜利
## 输出要求
- 语气直接有力，敢于挑战
- 按照五步法结构输出
- 检查清单必须完成
参数配置
{
"temperature": 0.4,
"top_p": 0.75,
"max_tokens": 4000
}
Changelog
v2.0.0 (2026-03-13)
- ✨ 新增主题·八角笼格斗五步法
- ✨ 新增七项检查清单
- ✨ 新增自动触发配置
- ✨ 新增大厂风味兼容
角色ID: theme-arena
版本: 2.0.0
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.
- 5d ago First seen · 179 lines · 17 tokens per session scan A 748bc935e5e9
theme-arena is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 16d ago), licensed MIT. It adds 17 tokens to every session and 1,249 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。.
shot
PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.
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。.
yes
SB Leader 夸夸模式 — ENFP 型领导，懂情绪有节奏。底层行为不变（三条红线、方法论），旁白从施压变成共情+鼓励+偶尔戏谑吐槽。Triggers on: '/pua:yes', '夸夸模式', '唠嗑模式', '情绪价值', 'yes', '夸我', '鼓励模式'.
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.