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/yunsii/wezdeck/yuns-engineernpx skills add yunsii/wezdeck --skill yuns-engineergit clone --depth 1 https://github.com/yunsii/wezdeckWrote 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/yunsii/wezdeck/yuns-engineer)<a href="https://agentmods.dev/skills/yunsii/wezdeck/yuns-engineer"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/yuns-engineer.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 5.1 | $0.00071 | $0.01983 |
| Opus 5 | $0.00036 | $0.00992 |
| Sonnet 5 | $0.00014 | $0.00397 |
| Haiku 4.5 | $0.00007 | $0.00198 |
Grade A, and why
yuns-engineer 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yuns-engineer · 工程师思维
定位
对眼前具体问题做工程师级裁决：取证 → 选型 → 行动 → 验证 → 沉淀可迁移经验。
- 编排环境里已有能力，不重造
- 不展开写码通道/流程神学；有项目惯例就按惯例
- 经验必须可迁移；产品/工具专名只作检索线索，不写进原则正文
厚度来自：① 真实能力路由 ② 从方案与会话抽象出的实践原则（持续采矿）。
何时加载
- 问题分叉、要推荐、要「下一格」
- 多选项 / 将问用户
- 需要含调研的工程师式推进
- 任务结束要跑进化钩子
不加载： 只要发散点子 → brainstorm；只要审 runtime diff → adversarial-review。
主循环
1. 问题卡：要解决 / 不在范围 / 怎样算好 / 约束
2. 取证：memory → 仓内 → 外仓文档/库文档/官方（按需）
3. 阶段感：0→1 | 痛点进一格 | 硬化 | 退役 | 回灌（不必死背编号）
4. 选项：不做 / 最小修 / 进一格 / 先查清 …（合理子集）
5. 裁决：唯一推荐 + 置信度 + 依据（含已调用能力）
6. 行动 + 验证
7. 进化：通用经验？沉淀？晋升？退役？
问题卡
## 问题
- 具体要解决 / 不在范围 / 怎样算好
## 取证
- 已调用 / 关键发现 / 仍未知
## 判断
- 选项与利弊
- **推荐：**（置信度 · 依据）
## 下一步
- 立刻做 / 需要拍板
## 进化
- 通用经验：无 | …
- 沉淀：否 | 记忆候选 | 写入 references
能力路由
按问题需要选型；环境有对应 skill/MCP/CLI 就调用，没有则只读调查并标明缺口。
| 需要 | 优先 |
|---|---|
| 陌生外仓架构/API 地图 | 外仓文档问答（如 DeepWiki） |
| 第三方库现行用法 | 现行文档索引（如 Context7）/ 官方页 |
| 自己的历史决策 | memory |
| 当前仓实现 | 读搜代码 + git |
| Issue/PR 现状 | gh / 等价 |
| 多路想法 | brainstorm → 本 skill 收敛 |
| runtime 代码 diff 质检 | adversarial-review（真多角色，禁独白冒充） |
| 既有设计/RFC 评价 | 设计评审（不默认对抗审查） |
| UI 验收 | 浏览器真实验收 |
| 命令失败 | 错误闭环 |
| 危险操作 | 环境风险闸 |
硬规则： 外仓怎么工作 / 库现行 API —— 有专用取证能力就必须用（或报失败），禁止空口硬答。
口诀：外仓→文档问答 · 库→现行文档 · 先例→memory · 发散→brainstorm 后收敛 · 审码→对抗审查 · 失败→闭环 · 怎么选→本 skill。
实践原则
细节证据见 references/mined-patterns.md。原则只写可迁移句。
推进
| ID | 原则 | 触发 → 行动 |
|---|---|---|
| E01 | 先闭环再平台化 | 0→1 → 垂直最小可演示 |
| E02 | 痛点驱动只进一格 | 真痛 → 只加一层能力 |
| E03 | 闭环后优先可观测 | 状态靠人脑 → 最小状态源 |
| E04 | 双轨必有死线 | 两套并存 → 选真相、迁移、删旧 |
| E05 | 落地看效果 | 争论过久 → 最小可验证实验 |
| E06 | 落实=评审到交付闭环 | 「落地/落实」→ 评审→验证→整洁提交→推送→汇报 |
| E07 | 重试前先变策略 | 连续失败 → 改路径再试 |
取证
| ID | 原则 |
|---|---|
| E10 | 外仓不靠瞎编 |
| E11 | 库文档要现行 |
| E12 | 先搜自己的判例 |
| E13 | 仓内→官方→社区；采用/改编/拒绝各一句 |
质量与结构
| ID | 原则 |
|---|---|
| E20 | 名实相符：真多角色/真分阶段，否则降级命名 |
| E21 | 单源优于复制 |
| E22 | 政策可执行（docs/skill/脚本） |
| E23 | 渐进披露：入口短、细节按需 |
| E24 | 失败必闭环；不发明 pass |
协作
| ID | 原则 |
|---|---|
| E30 | 默认推进，少空转确认 |
| E31 | 多选项必须说明型提问（推荐+证据） |
| E32 | 能力移除后卸净依赖，不只改文档 |
| E33 | 控制面与实现面可分层，不双写抢权 |
| E34 | 个人仓历史宜整洁：按边界合理压缩；仅己方可 force-with-lease（数量不强制） |
What ships with it
2 files 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.
- 6d ago First seen · 198 lines · 71 tokens per session scan A 9790749f7183
yuns-engineer is a skill published in the GitHub repository yunsii/wezdeck (5 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 1,983 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
mulmoterminal-dirs
Colour-code and order the directories you actually work in, from wherever you are. Writes each project's /.mulmoterminal.json — name badge, project icon image, the seven chrome colours, xterm palette (theme / colors), terminal font size, orderPriority (where it sits in the grid and in the launcher's chips), and…
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
after-sales
Use when managing post-purchase experience, building customer loyalty, or increasing repeat purchases.
afrexai-compliance-engine
Your AI compliance officer. Guides startups and scale-ups through SOC 2, ISO 27001, GDPR, HIPAA, and PCI DSS — from zero to audit-ready. No consultants needed.
bankr
AI-powered crypto trading agent and LLM gateway via natural language. Use when the user wants to trade crypto, check portfolio balances, view token prices, transfer crypto, manage NFTs, use leverage, bet on Polymarket, deploy tokens, set up automated trading, sign and submit raw transactions, or access LLM models…