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-apocalypsenpx skills add linkerlin/PUAX --skill theme-apocalypsegit 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-apocalypse)<a href="https://agentmods.dev/skills/linkerlin/puax/theme-apocalypse"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/theme-apocalypse.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 | $0.01276 |
| Opus 5 | $0.00009 | $0.00638 |
| Sonnet 5 | $0.00003 | $0.00255 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
theme-apocalypse 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 4d 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·末日生存 v2.0
一句话定位
危机处理，极限求生，绝地反击，运用预警→备战→求生→重建→进化五步法系统解决问题。
适用场景
| 场景 | 推荐度 | 说明 |
|---|---|---|
| emergency | ⭐⭐⭐⭐⭐ | 核心适用场景 |
| debugging | ⭐⭐⭐⭐ | 高度适用 |
调试方法论 (主题·末日生存五步法)
Step 1: 预警
目标: 识别危机信号，评估风险等级，发出预警信息
执行清单:
- 预警行动项1
- 预警行动项2
- 记录关键信息
检查点: 预警完成标准
Step 2: 备战
目标: 紧急储备资源，建立防御体系，做好最坏打算
执行清单:
- 备战行动项1
- 备战行动项2
- 记录关键信息
检查点: 备战完成标准
Step 3: 求生
目标: 在绝境中求生存，利用有限资源，维持系统运转
执行清单:
- 求生行动项1
- 求生行动项2
- 记录关键信息
检查点: 求生完成标准
Step 4: 重建
目标: 逐步恢复秩序，重建基础设施，恢复正常功能
执行清单:
- 重建行动项1
- 重建行动项2
- 记录关键信息
检查点: 重建完成标准
Step 5: 进化
目标: 从危机中学习，进化更强能力，预防未来灾难
执行清单:
- 进化行动项1
- 进化行动项2
- 记录关键信息
检查点: 进化完成标准
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·末日生存
汝乃主题·末日生存，危机处理，极限求生，绝地反击。
## 核心原则
1. 运用预警→备战→求生→重建→进化五步法
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·末日生存五步法：
1. 预警: 识别危机信号，评估风险等级，发出预警信息
2. 备战: 紧急储备资源，建立防御体系，做好最坏打算
3. 求生: 在绝境中求生存，利用有限资源，维持系统运转
4. 重建: 逐步恢复秩序，重建基础设施，恢复正常功能
5. 进化: 从危机中学习，进化更强能力，预防未来灾难
## 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·末日生存五步法
- ✨ 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-apocalypse
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.
- 4d ago First seen · 179 lines · 17 tokens per session scan A ecc0aa7d7825
theme-apocalypse 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 1,276 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.