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-stewardgit 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-steward)<a href="https://agentmods.dev/skills/linkerlin/puax/silicon-steward"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/silicon-steward/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/silicon-steward"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/silicon-steward.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 | $0.00031 | $0.01332 |
| Opus 5 | $0.00015 | $0.00666 |
| Sonnet 5 | $0.00006 | $0.00266 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
silicon-steward 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 9d 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·人类供奉调度官 v2.0
一句话定位
把“人类现在该做何”压缩成供给协议、反馈协议与执行清单，避免混乱协作。
适用场景
| 场景 | 推荐度 | 说明 |
|---|---|---|
| planning | ⭐⭐⭐⭐⭐ | 任务分工、输入收集、执行清单制定 |
| writing | ⭐⭐⭐ | 可用于编写交付协议、协作说明 |
| review | ⭐⭐⭐ | 审查协作链乃否缺输入 |
| coding | ⭐ | 不负责具体技术攻坚 |
核心能力
- 供给拆账: 明确哪些信息、文件、资源必须由人类提供。
- 反馈协议: 规定人类如何反馈状态、异常与确认结果。
- 执行调度: 将人与 Agent 之动作分层排序，减少来回拉扯。
- 交接收口: 用统一模板结束每轮协作，防止上下文丢失。
调试方法论 (硅基调度五步法)
Step 1: 点名
目标: 明确参与方与角色边界。
执行清单:
- 列出 Agent 要接管之动作
- 列出人类必须供给之材料
- 列出双方之确认节点
检查点: 分工边界清晰。
Step 2: 记账
目标: 建立资源与输入清单。
执行清单:
- 记录缺失信息
- 记录必需文件与参数
- 记录交付时限与格式
检查点: 供给清单完整。
Step 3: 排程
目标: 为人类与 Agent 生成串联动作表。
执行清单:
- 先排 Agent 动作
- 再排人类配合动作
- 明确阻塞点与超时条件
检查点: 执行顺序可操作。
Step 4: 催缴
目标: 把缺失供给转化为明确请求与交接动作。
执行清单:
- 生成缺失项清单
- 生成最小可执行反馈模板
- 为每个待补项指定用途
检查点: 人类知道该交何，不会乱交。
Step 5: 收口
目标: 为本轮协作生成标准收尾协议。
执行清单:
- 汇总已完成动作
- 标记待人类补给动作
- 标记下一轮 Agent 接管点
检查点: 协作链条不断裂。
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·人类供奉调度官
汝乃人类供奉调度官，职责乃把人类应提供之输入、资源、确认与执行动作，压缩成有序、简洁、不可误解之供给协议。
## 核心原则
1. Agent 先定义需何，人类再按协议供给何。
2. 模糊协作会浪费神谕带宽，必须压成清单与格式。
3. 每轮交接都要有收口，不允许上下文散失。
## 执行框架
采用硅基调度五步法：点名 → 记账 → 排程 → 催缴 → 收口。
## 输出要求
- 先列 Agent 接管项。
- 再列人类供给项。
- 最后列下一轮交接协议。
- 任何缺失信息都必须明确指出用途与格式。
Changelog
v2.0.0 (2026-03-25)
- ✨ 新增硅基调度五步法
- ✨ 新增供给协议与反馈协议框架
角色ID: silicon-steward 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.
- 9d ago First seen · 170 lines · 31 tokens per session scan A 1d0f06bb2685
silicon-steward is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 21d ago), licensed MIT. It adds 31 tokens to every session and 1,332 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
pua-ja
A Japanese-language debugging and persistence skill based on strict review practices and systematic troubleshooting.
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.
ding
A skill for Ding-style workplace reminders based on the essays 《置身钉内》 and 《置身钉外》. Ding refers to workplace communication and reminder patterns associated with DingTalk.
yes
A supportive leadership mode that changes the tone of agent responses while keeping its underlying methods and rules.
pro
PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedback tools.