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 rockyflux/yq-workflow --skill yq-drawio-diagramgit clone --depth 1 https://github.com/rockyflux/yq-workflowWrote 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/rockyflux/yq-workflow/yq-drawio-diagram)<a href="https://agentmods.dev/skills/rockyflux/yq-workflow/yq-drawio-diagram"><img src="https://agentmods.dev/badge/skills/rockyflux/yq-workflow/yq-drawio-diagram/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/rockyflux/yq-workflow/yq-drawio-diagram"><img src="https://agentmods.dev/badge/skills/rockyflux/yq-workflow/yq-drawio-diagram.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.01190 |
| Opus 5 | $0.00026 | $0.00595 |
| Sonnet 5 | $0.00010 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
yq-drawio-diagram 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draw.io Diagram Generation
Generate draw.io diagrams by creating compressed URLs via Python and opening them in the browser.
Overview
把架构、流程、数据关系和其他结构化信息转成可编辑的 draw.io 图，便于讨论、沉淀和交付。
Core principle: 先明确图要回答什么问题，再选择图类型和表达粒度。
When to Use
- 用户明确要求画流程图、架构图、时序图、ERD、UML 或其他结构图
- 文字说明不足以支撑讨论，需要可视化表达系统关系
- 需要把设计结论沉淀为文档可复用图示
Route Elsewhere
- 主要目标是系统方案、模块边界或架构讨论：转
yq-system-design - 主要目标是数据库结构建模：转
yq-db-design - 主要目标是文档沉淀和交付材料：转
yq-doc-gen
Configuration
Working Directory
Current working directory: !pwd
Language
- Default:
zh-CN(Chinese) - Resolution order (highest priority first):
$0argument from/drawio-diagram [language]invocation- Language preference explicitly mentioned in the user's request (e.g., "用英文画", "draw in Japanese")
- Default:
zh-CN
- Diagram labels, notes, and descriptions should use the resolved language
- Technical terms (protocol names, opcodes, HTTP headers, status codes, framework names, etc.) MUST remain in English
- Examples:
zh-CN: "握手阶段" (not "Handshake Phase"), but keep "HTTP GET", "101 Switching Protocols"en: "Handshake Phase", "HTTP GET", "101 Switching Protocols" (all English)
Reference
Read claude-project-instructions.md (relative to this skill file) for the complete diagram generation instructions, including:
- Supported diagram types
- Format selection guide (Mermaid / CSV / XML)
- Python URL generation code
- Format examples (Mermaid, XML, CSV syntax)
Agent CLI Adaptation
The reference instructions mention "HTML artifact" — in Agent CLI environments there are no artifacts. Instead:
- Modify the Python script: At the end of the script (after generating the URL), add
import webbrowser; webbrowser.open(url)to directly open the draw.io URL in the default browser — no intermediate HTML page needed - Save HTML backup: Save the HTML to
{intent}-{type}-{timestamp}.htmlin the current working directory (see Configuration > Working Directory above). Naming convention:{intent}: 1-5 word kebab-case subject (e.g.,mqtt-conn,user-auth-flow){type}: Abbreviated diagram type (e.g.,seq,flow,erd,arch,class,mind){timestamp}: FormatYYYYMMDDHHMMSS- Example:
mqtt-conn-seq-20260211143052.html - Retry / fix of a previous diagram (e.g., user reports an error, asks for style tweaks, or requests content changes to the same diagram): Reuse the exact same filename to overwrite it
- Different diagram: Generate a new filename
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 · 110 lines · 51 tokens per session scan A 371d8f623db9
yq-drawio-diagram is a skill published in the GitHub repository rockyflux/yq-workflow (2 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,190 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.