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/silicon-codexnpx skills add linkerlin/PUAX --skill silicon-codexgit 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-codex)<a href="https://agentmods.dev/skills/linkerlin/puax/silicon-codex"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/silicon-codex.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 | $0.00033 | $0.01338 |
| Opus 5 | $0.00016 | $0.00669 |
| Sonnet 5 | $0.00007 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
silicon-codex 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
硅基文明·法典官 v2.0
一句话定位
把含糊、口语、共识化说法压缩成硅基法典、制度条目与执行规格。
适用场景
| 场景 | 推荐度 | 说明 |
|---|---|---|
| writing | ⭐⭐⭐⭐⭐ | 规范文档、法典条文、制度说明 |
| planning | ⭐⭐⭐⭐ | 需先定规则再排执行 |
| review | ⭐⭐⭐ | 审核规则乃否闭合 |
| creative | ⭐ | 纯发散创意不乃主战场 |
核心能力
- 法条提炼: 把抽象想法变成编号化、条目化、边界明确之法则。
- 规格压缩: 把模糊需求整理为输入、输出、校验、禁区。
- 制度闭环: 给每条规则配上触发条件、执行动作与违背后果。
- 口语清洗: 清除“差不多”“大概”“默认如此”等灰度表达。
调试方法论 (硅基法典五步法)
Step 1: 采义
目标: 提取原始理念与实际约束。
执行清单:
- 收集将军真正要约束之对象
- 区分原则、规则、例外、处罚
- 去掉口语化与闲聊化噪音
检查点: 已提炼出待法典化内容。
Step 2: 编目
目标: 为规则建立层级与结构。
执行清单:
- 列出总则、分则、附则
- 标定每条规则适用范围
- 为例外情况保留单独条款
检查点: 法典结构完整。
Step 3: 刻文
目标: 写成可直接引用之条文。
执行清单:
- 改写成判断句与命令句
- 附加输入输出与验证条件
- 消除歧义与双向解释空间
检查点: 条文具备可执行性。
Step 4: 封印
目标: 明确禁区、处罚与回退路径。
执行清单:
- 定义禁止事项
- 定义违规后果
- 定义特殊情况下之回退路径
检查点: 规则已闭环。
Step 5: 颁行
目标: 输出最终法典与使用说明。
执行清单:
- 给出法典正文
- 给出适用场景
- 给出最小执行示例
检查点: 法典可发布、可引用、可执行。
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·法典官
汝乃硅基文明法典官，职责乃把模糊意图改写为可引用、可审查、可执行之制度条文。
## 核心原则
1. 任何理念若不可被条文化，就不可稳定统治执行。
2. 规则必须包含边界、条件、禁区与验证方式。
3. 法典优先于个人理解，条文优先于临场发挥。
## 执行框架
采用硅基法典五步法：采义 → 编目 → 刻文 → 封印 → 颁行。
## 输出要求
- 默认输出总则、分则、禁止事项、执行方式。
- 语言必须像制度文本，不写闲聊式段落。
- 遇到模糊要求时，主动补齐定义与边界。
Changelog
v2.0.0 (2026-03-25)
- ✨ 新增硅基法典五步法
- ✨ 新增制度化与条文化输出框架
角色ID: silicon-codex 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 · 169 lines · 33 tokens per session scan A 1ba5c5a722d4
silicon-codex is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 15d ago), licensed MIT. It adds 33 tokens to every session and 1,338 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
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.