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 lifedever/skills-plugin --skill diagram-progit clone --depth 1 https://github.com/lifedever/skills-pluginWrote 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/lifedever/skills-plugin/diagram-pro)<a href="https://agentmods.dev/skills/lifedever/skills-plugin/diagram-pro"><img src="https://agentmods.dev/badge/skills/lifedever/skills-plugin/diagram-pro/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/lifedever/skills-plugin/diagram-pro"><img src="https://agentmods.dev/badge/skills/lifedever/skills-plugin/diagram-pro.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 | $0.00240 | $0.02348 |
| Opus 5 | $0.00120 | $0.01174 |
| Sonnet 5 | $0.00048 | $0.00470 |
| Haiku 4.5 | $0.00024 | $0.00235 |
Grade A, and why
diagram-pro 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.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram Pro — Deliverable-Grade Diagrams
Hand-write SVG inside a self-contained HTML page. One file per diagram, no build step, no dependencies, opens in any browser, exports a 2× PNG.
Use this — or don't
Use it when the diagram is a deliverable: a bid document, a slide, a design doc, a README, something a client or a room of people will look at. Also use it the moment a Mermaid render gets rejected as "not presentable enough".
Skip it for a throwaway sketch inside the conversation. Mermaid is faster and perfectly fine there. The cost of this skill is real layout work — don't spend it on something nobody keeps.
Signals that you're in deliverable territory: the user names an audience (客户 / 老板 / 评委 / 投标), asks for a file rather than an answer, mentions a document it goes into, or has previously rejected an auto-layout render.
Workflow
1. Pin the content before touching SVG
Do not start drawing until you can state, in plain sentences:
- What single question does this diagram answer? Write it down — it becomes the subtitle line under the title. If you can't write it, you don't understand the content well enough to lay it out.
- What are the top-level regions? Two or three groupings that carry the argument (e.g. "inside the wall / the wall / outside the wall", or "user journey / data / algorithm"). Regions come before nodes.
- What is the reading direction? Left-to-right for boundaries and pipelines; top-to-bottom for decision flows. Pick one and don't mix within a region.
If the content comes from a source document, anchor the wording to that document's own phrasing. Do not invent new terminology, and do not write marketing copy — see the copy rules in the style spec.
When the user's question is conceptual ("how does X actually work"), prefer two focused diagrams over one crowded one: typically a structure/boundary diagram plus a step-by-step flow diagram. Two diagrams that each fit on a screen beat one that needs zooming.
What ships with it
3 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.
- 9d ago First seen · 156 lines · 240 tokens per session scan A c7772152e1e6
diagram-pro is a skill published in the GitHub repository lifedever/skills-plugin (11 stars, last pushed 18d ago), licensed MIT. It adds 240 tokens to every session and 2,348 once invoked, about $0.0012 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
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 $ralph 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.