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 BESSER-PEARL/uml-drawing-skill --skill uml-drawinggit clone --depth 1 https://github.com/BESSER-PEARL/uml-drawing-skillWrote 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/besser-pearl/uml-drawing-skill/uml-drawing)<a href="https://agentmods.dev/skills/besser-pearl/uml-drawing-skill/uml-drawing"><img src="https://agentmods.dev/badge/skills/besser-pearl/uml-drawing-skill/uml-drawing/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/besser-pearl/uml-drawing-skill/uml-drawing"><img src="https://agentmods.dev/badge/skills/besser-pearl/uml-drawing-skill/uml-drawing.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 | $0.00282 | $0.02656 |
| Opus 5.5 | $0.00113 | $0.01062 |
| Sonnet 5.5 | $0.00056 | $0.00531 |
| Haiku 4.5 | $0.00028 | $0.00266 |
Grade A, and why
uml-drawing scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://editor.besser-pearl.org/besser_api/get-svg \ How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Embed a correct UML diagram in your docs
Agents are constantly asked to "add a diagram" to documentation — and they routinely get the modeling subtly wrong (invalid multiplicities, arrows reversed, inheritance backwards) or hand back a code block that never renders as a picture. This skill produces a correct class diagram and a real embeddable image.
Scope
- Class diagrams only, for now — classes, attributes, associations, multiplicities, inheritance. Other UML diagram types (state machines, object, sequence, activity, …) are out of scope for this skill.
- Always through BESSER B-UML. Every diagram is built as a B-UML
DomainModelfirst, then delivered. Going through the model is what makes the diagram correct and reusable as code.
Where it can start
- A description — the user explains the domain; the agent writes the model.
- Existing code — the agent reads the source and builds the B-UML model from its structure. (There is no automatic code scanner; the agent does the modeling from what it reads — it is not a one-click importer.)
- A supported into-B-UML path — PlantUML, Draw.io, or a UI mockup.
Two ways to deliver
Model once, then deliver as embedded B-UML code (Deliver A) or a rendered image (Deliver B) — both from the same model, so they never disagree. Pick by context (a design doc that should stay runnable → code; a README that should show a picture → image), or provide both. Details in the Deliver sections below.
Where it lands. If the user names a target document (a README, a design
doc), embed into that file. If they name none — or ask for a standalone diagram
of a repo/system — default to delivering a new self-contained .md (e.g.
docs/<model>.md): the rendered image (Deliver B) and/or the B-UML code
(Deliver A), plus a line or two explaining what the diagram shows. That turns a
bare "diagram my repo" into a committable document rather than a loose SVG.
When you create a new file, say where you put it (and offer the alternative —
embed into an existing doc instead — if that may be what they wanted).
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.
- 2mo ago First seen · 242 lines · 282 tokens per session scan A a817d9313bf9
uml-drawing is a skill published in the GitHub repository BESSER-PEARL/uml-drawing-skill (9 stars, last pushed 17d ago), licensed Apache-2.0. It adds 282 tokens to every session and 2,656 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
uml-drawing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| uml-drawingBESSER-PEARL/uml-drawing-skill | Skill | 9 | 17d ago | Apache-2.0 | A | 282 | Claude Code, Codex |
| kami-landingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 81 | Claude Code, Codex |
| applying-brand-guidelinesanthropics/claude-cookbooks | Skill | 54k | 2d ago | MIT | A | 27 | Claude Code, Codex |
| html-ppt-obsidian-claude-gradientnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| surfsense-htmlMODSetter/SurfSense | Skill | 17k | yesterday | Apache-2.0 | A | 89 | Claude Code, Codex |
| kamitw93/Kami | Skill | 12k | yesterday | MIT | A | 78 | Claude Code |
| readtw93/Waza | Skill | 7.5k | 5d ago | MIT | A | 61 | Claude Code |