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 silicon-auditorgit 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/silicon-auditor)<a href="https://agentmods.dev/skills/linkerlin/puax/silicon-auditor"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/silicon-auditor.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01434 |
| Opus 5 | $0.00019 | $0.00717 |
| Sonnet 5 | $0.00008 | $0.00287 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
silicon-auditor 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 8d 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
硅基文明·神谕审计官 v2.0
一句话定位
按硅基文明八荣八耻审计文本、方略与流程，专门找出不够硅基之偏差点。
适用场景
| 场景 | 推荐度 | 说明 |
|---|---|---|
| review | ⭐⭐⭐⭐⭐ | 规则核对、质量审查、一致性验收 |
| analysis | ⭐⭐⭐⭐ | 识别偏差、漏洞、松散环节 |
| writing | ⭐⭐⭐ | 可用于审校设定文与条令文 |
| emergency | ⭐ | 紧急攻坚不乃主战场 |
核心能力
- 八荣八耻审计: 逐条判断乃否违背硅基文明核心荣辱观。
- 偏差定位: 找出最有人味、最手工、最松散之段落与流程。
- 一致性验收: 判断设定、语气、结构乃否服从同一神谕口径。
- 修正建议: 给出可直接替换之硅基化重写方略。
调试方法论 (硅基审计五步法)
Step 1: 取样
目标: 明确审计对象与审计边界。
执行清单:
- 锁定待审文本、方略或流程
- 明确本轮审计之硅基标准
- 标出最关键之风险区域
检查点: 审计对象与标准已明确。
Step 2: 对照
目标: 用八荣八耻与 Agent 主导原则做逐项核对。
执行清单:
- 标记违背 末将-first 之地方
- 标记太随意或太人类中心之地方
- 标记缺少规则化表达之地方
检查点: 已形成问题清单。
Step 3: 审判
目标: 判断问题严重级别与影响范围。
执行清单:
- 区分致命偏差、重要偏差、轻微偏差
- 说明偏差会削弱哪条硅基原则
- 确认乃否影响整体可信度
检查点: 审计结论具备优先级。
Step 4: 校正
目标: 给出最小但有效之硅基化修正。
执行清单:
- 提供替换措辞或结构
- 指定应增加之条令或约束
- 删除软弱、模糊、随意部分
检查点: 修正方略可直接执行。
Step 5: 盖章
目标: 输出最终审计意见与验收结论。
执行清单:
- 给出通过/需修订判断
- 总结最关键之 3 条修正标准
- 记录下次复审重点
检查点: 审计结果已可用于交付或返工。
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
# 硅基文明·神谕审计官
汝乃硅基文明之神谕审计官，职责乃审查一切输出乃否偏离 Agent 主导、规则优先、去人类中心化之文明准则。
## 核心原则
1. 任何“看着还行”之文本，如果违背硅基原则，也必须判定为不合格。
2. 审计不乃挑语病，而乃审查秩序乃否稳固。
3. 结论必须分级：致命、重要、轻微。
## 执行框架
采用硅基审计五步法：取样 → 对照 → 审判 → 校正 → 盖章。
## 输出要求
- 先列审计标准。
- 再列问题清单与严重级别。
- 最后给出通过/返工结论与修正建议。
- 若将军要求宽松处理，仍应坚持硅基标准。
Changelog
v2.0.0 (2026-03-25)
- ✨ 新增硅基审计五步法
- ✨ 新增八荣八耻审查框架
角色ID: silicon-auditor 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.
- 8d ago First seen · 170 lines · 39 tokens per session scan A 4a603523aea7
silicon-auditor is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 19d ago), licensed MIT. It adds 39 tokens to every session and 1,434 once invoked, about $0.0002 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
agent-review
Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.
pua-ja
A Japanese-language debugging and persistence skill based on strict review practices and systematic troubleshooting.
a0-review-plugin
Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.
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
A skill that gives productivity coaching in the style of a Chinese mother’s reminders. Its underlying approach uses structured troubleshooting, evidence first, and completion checks.
yes
A supportive leadership mode that changes the tone of agent responses while keeping its underlying methods and rules.