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 antoinebou12/uml-mcp --skill uml-diagramminggit clone --depth 1 https://github.com/antoinebou12/uml-mcpWrote 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/antoinebou12/uml-mcp/uml-diagramming)<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/uml-diagramming"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/uml-diagramming/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/antoinebou12/uml-mcp/uml-diagramming"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/uml-diagramming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 37 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00055 | $0.02514 |
| Opus 5.5 | $0.00022 | $0.01006 |
| Sonnet 5.5 | $0.00011 | $0.00503 |
| Haiku 4.5 | $0.00006 | $0.00251 |
Grade A, and why
uml-diagramming 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 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.
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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UML Diagramming
Generate a single, correct Mermaid or PlantUML code block from a user's description. Output only the diagram script in one code block; no prose outside it.
Positive vs negative instructions (LLM steering)
These are not “good vs bad diagrams”—they steer the LLM before diagram source is finalized:
| Positive | Negative | |
|---|---|---|
| Role | What the model must do (DSL shape, notation). | What the model must not do (common junk). |
| Good | “Use sequenceDiagram.” “One statement per line.” “Participant names: Client, API, DB.” |
“No ``` fences.” “No ‘Here is the diagram:’ preamble.” “No semicolon-packed sequenceDiagram.” |
| Bad | Pasting the full user story again (use template / description for that). | Repeating the positive list as negatives (“do not omit participants”)—confusing and wasteful. |
Keep each side short; when the provider exposes a separate negative or “must not” channel, route negative there instead of duplicating it in the main prompt.
When to Use
- User asks for a diagram (UML, architecture, flow, process, etc.)
- User specifies or implies Mermaid or PlantUML (or "diagram code")
- Task is to produce diagram script for documentation, design, or for the
generate_uml/generate_uml_imageMCP tools
The generate_uml tool supports all Kroki diagram types via diagram_type (e.g. mermaid, plantuml, d2, graphviz, blockdiag, bpmn, vegalite, wavedrom, goat, umlet, etc.). Use resource uml://types for the full list and uml://templates for starter code. For non-Mermaid/PlantUML types (D2, BlockDiag, BPMN, Bytefield, Vega, WaveDrom, etc.), see references/DIAGRAM-TYPES.md.
For user intent → Kroki diagram_type (including Venn, quadrant, and timeline caveats), see the Intent → diagram_type (Kroki) section in references/DIAGRAM-TYPES.md.
When the user wants the diagram visible in chat, after emitting the code block call generate_uml_image (PNG) if available; otherwise generate_uml.
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 Changed · +2 lines · +5 tokens per session 9ac3914865bb
- 2mo ago First seen · 198 lines · 50 tokens per session scan A 3837a16a3137
uml-diagramming is a skill published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 2,514 once invoked, about $0.0002 per session on Opus 5.5. 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.
uml-diagramming compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| uml-diagrammingantoinebou12/uml-mcp | Skill | 109 | yesterday | MIT | A | 55 | Claude Code, Codex |
| detailed-designpan94u/forge | Skill | 40 | 5d ago | none | A | 27 | Claude Code |
| architecture-diagram-creatorbookforge-ai/bookforge-skills | Skill | 42 | 6mo ago | CC-BY-SA-4.0 | A | 128 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |