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 Dong90/oh-my-taiyiforge --skill taiyi-diagram-archgit clone --depth 1 https://github.com/Dong90/oh-my-taiyiforgeWrote 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/dong90/oh-my-taiyiforge/taiyi-diagram-arch)<a href="https://agentmods.dev/skills/dong90/oh-my-taiyiforge/taiyi-diagram-arch"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-diagram-arch/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/dong90/oh-my-taiyiforge/taiyi-diagram-arch"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-diagram-arch.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 | $0.00048 | $0.01438 |
| Opus 5 | $0.00024 | $0.00719 |
| Sonnet 5 | $0.00010 | $0.00288 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
taiyi-diagram-arch 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 12d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
taiyi-diagram-arch
目的
把 DESIGN.md 里的文字架构落成可读、可版本管理、可导出高清的架构图——组件边界、数据流、部署视图、产品级全景图（Flow-X 风格海报）。
何时使用
| 时机 | 说明 |
|---|---|
taiyi-design 写 Architecture 节 |
默认推荐（与 ASCII/mermaid 并列） |
| 新模块 / 跨服务边界 | 必做 C4 或组件图 |
| 仓库级文档 | docs/*-architecture.svg + PNG |
taiyi-evolve 发现架构漂移 |
同步更新架构图 |
可跳过：纯文案/配置改动、无新组件且无边界变化。
输入
- 优先真源：
diagrams/c4/containers.md或docs/c4/containers.md（由/taiyi:diagram-c4产出） REQUIREMENT.md、DESIGN.md（Decision + Architecture 草稿）CONTEXT.md（既有模块与路径）- （可选）
adr/、docs/ARCHITECTURE.md
流水线第 2 步：加载本 Skill 时同步 C4 真源，勿重新划分模块。总编排：/taiyi:diagram-pipeline。
输出（择一或组合）
| 产物 | 路径 | 适用 |
|---|---|---|
| 变更内架构说明 | .taiyi/changes/<slug>/diagrams/architecture.md |
九阶段工件（mark-aux 检测） |
| 嵌入 DESIGN | DESIGN.md § Architecture 内 mermaid 代码块 |
轻量变更 |
| 矢量海报 | diagrams/architecture.svg + architecture.png |
产品/对外文档 |
| 仓库级 | docs/<name>-architecture.svg |
本仓库参考：docs/taiyiforge-architecture.svg |
mark-aux：独立文件路径时执行 scripts/taiyi-forge.sh mark-aux <slug> taiyi-diagram-arch。
图类型选型
| 问题 | 推荐图型 | 工具 |
|---|---|---|
| 模块谁依赖谁 | graph TB / graph LR |
Mermaid |
| 请求怎么走 | sequenceDiagram |
Mermaid |
| 部署/运行时 | graph + subgraph 环境 |
Mermaid |
| 产品全景（六大标准+九阶段+门禁） | 分栏海报 SVG | Python 脚本或手调 SVG |
| C4 容器级 | Mermaid C4（若渲染器支持）或结构化 graph | Mermaid |
执行步骤
- 若存在
diagrams/c4/containers.md：以其为节点/边界真源；顶部加> C4 真源：diagrams/c4/containers.md - 读 DESIGN Decision：只画「已选定方案」，不把未选 Option 画进主图
- 列节点清单：组件名 = 仓库内真实路径/包名（如
src/core/workflow-engine.ts） - 选视图：默认 1 张组件图 + 1 张关键序列图（有外部 API 时）
- 写 Mermaid（变更内首选）：
# Architecture Diagram
## Component view
\`\`\`mermaid
graph LR
CLI[taiyi CLI] --> Engine[workflow-engine]
Engine --> Manifest[workflow-manifest.yaml]
Engine --> Skills[skills/taiyi-*]
\`\`\`
## Notes
- 与 DESIGN.md §Decision 一致
- 更新日期：ISO8601
- （可选）导出 PNG：
node scripts/render-mermaid.mjs .taiyi/changes/<slug>/diagrams/architecture.md - （产品海报） 宽屏分栏布局参考
docs/taiyiforge-architecture.svg；可 forkscripts/generate-architecture-svg.py改文案后重跑 - 回链 DESIGN.md：Architecture 节写
详见 diagrams/architecture.md或内嵌同一段 mermaid - mark-aux（若写了独立 diagrams 文件）
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.
- 12d ago First seen · 115 lines · 48 tokens per session scan A c8adddfb4cce
taiyi-diagram-arch is a skill published in the GitHub repository Dong90/oh-my-taiyiforge (888 stars, last pushed 5d ago), licensed MIT. It adds 48 tokens to every session and 1,438 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
create-pi-theme
Como criar um tema visual para o TUI do pi. Use quando o usuário quiser personalizar cores e aparência do terminal.
visual-design
A design skill for turning content into complete, self-contained HTML pages and visual materials such as websites, banners, posters, reports, resumes, and portfolios. It follows a defined visual design system and does not use outside images or code libraries.
review
Use when the user wants code assessed rather than changed — "review PR 88", "is this branch ready to merge?", "look over my changes", "any problems with this diff?", "give me a code review", "what do you think of this PR?", "sanity-check this branch", "ship it?". Applies to a pull request or the current branch when…
fix
PRFlow's code-review reception skill (formerly receiving-code-review), used by the review-and-fix loop and available directly. Use when addressing review feedback already posted on a pull request — verifying findings before applying them — as distinct from /prflow:review-and-fix, which runs the review itself and then…
docs-bootstrap-internal
Use when a codebase has no structured developer documentation yet and needs it built from scratch — "we have no docs at all", "set up internal docs for this repo", "the docs directory is a mess, start over", "create developer documentation for this codebase" — including an empty or disorganized docs directory or a…
docs-sync-internal
Use when code changes on the current branch need matching internal or developer documentation — "update our internal docs", "the architecture docs are stale after this change", "document what I just changed", "do the dev docs still match the code?" — or as a pre-push check that developer docs track the code. Narrower…