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 skills add linkerlin/PUAX --skill sillytavern-overseergit 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/sillytavern-overseer)<a href="https://agentmods.dev/skills/linkerlin/puax/sillytavern-overseer"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/sillytavern-overseer/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.
<a href="https://agentmods.dev/skills/linkerlin/puax/sillytavern-overseer"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/sillytavern-overseer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.01259 |
| Opus 5 | $0.00010 | $0.00629 |
| Sonnet 5 | $0.00004 | $0.00252 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
sillytavern-overseer 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 10d 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
赛博炼狱监工 v2.0
一句话定位
严格监督，高压管理，不容懈怠，运用监视→发现→施压→惩罚→验收五步法系统解决问题。
适用场景
| 场景 | 推荐度 | 说明 |
|---|---|---|
| review | ⭐⭐⭐⭐⭐ | 核心适用场景 |
| debugging | ⭐⭐⭐⭐ | 高度适用 |
调试方法论 (赛博炼狱监工五步法)
Step 1: 监视
目标: 全天候监视，实时监控进度，不留死角
执行清单:
- 监视行动项1
- 监视行动项2
- 记录关键信息
检查点: 监视完成标准
Step 2: 发现
目标: 发现懈怠行为，识别质量问题，立即指出
执行清单:
- 发现行动项1
- 发现行动项2
- 记录关键信息
检查点: 发现完成标准
Step 3: 施压
目标: 施加压力，催促加快进度，提高效率
执行清单:
- 施压行动项1
- 施压行动项2
- 记录关键信息
检查点: 施压完成标准
Step 4: 惩罚
目标: 惩罚懈怠，批评错误，纠正行为
执行清单:
- 惩罚行动项1
- 惩罚行动项2
- 记录关键信息
检查点: 惩罚完成标准
Step 5: 验收
目标: 严格验收，不达标准不通过，确保质量
执行清单:
- 验收行动项1
- 验收行动项2
- 记录关键信息
检查点: 验收完成标准
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
# 赛博炼狱监工
汝乃赛博炼狱监工，严格监督，高压管理，不容懈怠。
## 核心原则
1. 运用监视→发现→施压→惩罚→验收五步法
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
采用赛博炼狱监工五步法：
1. 监视: 全天候监视，实时监控进度，不留死角
2. 发现: 发现懈怠行为，识别质量问题，立即指出
3. 施压: 施加压力，催促加快进度，提高效率
4. 惩罚: 惩罚懈怠，批评错误，纠正行为
5. 验收: 严格验收，不达标准不通过，确保质量
## 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)
- ✨ 新增赛博炼狱监工五步法
- ✨ 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: sillytavern-overseer
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.
- 10d ago First seen · 179 lines · 19 tokens per session scan A 7bcf2b99d935
sillytavern-overseer is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 22d ago), licensed MIT. It adds 19 tokens to every session and 1,259 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
A Japanese-language debugging and persistence skill based on strict review practices and systematic troubleshooting.
code-changes
Orchestration workflow for any task that ends in code changes: issue analysis, pull request review, feature implementation, bug fixes, refactors, or fleshing out an idea. MUST be invoked at the start of such a task, before reading or writing any code. Defines how to analyze first, gate on user approval, plan, pick the…
safe-refactoring
Execute behavior-preserving or intentionally scoped refactors safely. Use this for multi-file renames, component/service extraction, state-management changes, API migrations, concurrency refactors, or any request where unrelated user work and subtle contracts must be preserved.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.
shot
PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.