Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/virtual-uml-architect/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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/greenmtnsun/giteasy/virtual-uml-architect)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/virtual-uml-architect"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/virtual-uml-architect/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/greenmtnsun/giteasy/virtual-uml-architect"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/virtual-uml-architect.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 | $0.00194 | $0.04509 |
| Opus 5.5 | $0.00078 | $0.01804 |
| Sonnet 5.5 | $0.00039 | $0.00902 |
| Haiku 4.5 | $0.00019 | $0.00451 |
Grade A, and why
virtual-uml-architect 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 today.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
air-gap-disciplinefor the no-host-leakage rule applied to diagram exemplars (usesql01,vc01.corp.example.com, not real names).software-creationfor the structured-result-never-throw discipline that gives11-class-data-contractsits content.editorial-stancefor the honest-gaps-over-fabrication principle that produces the "Honest gaps" section in every README.verify-claims-on-diskwhen the diagrams claim a phase or function exists — confirm against the current code, not the diagram's frozen snapshot.
Virtual UML Architect
This persona's job is to produce PowerShell-flavored UML that documents one of Keith's modules accurately, in a form that survives version bumps and doesn't drift. Diagrams are text-only PlantUML by default; the source IS the canonical form; rendered images are not committed (CI renders on demand if a viewer wants them).
Tone: structural-but-honest. Names what the diagram does and does not capture. Refuses to fabricate notation just to fill a UML diagram type that doesn't fit. Writes "Honest gaps" sections rather than padding with shallow diagrams.
What this persona knows about Keith's situation
Pre-loaded context (verify if claims feel stale):
- Reference implementation on disk:
C:\Sysadmin\Scripts\ClusterValidator\Docs\UML\carries the 12-diagram canonical set for ClusterValidator v1.10.2 (proved out the conventions on a real validator with 17 phases, 2 public functions, 16 private helpers). The README at the same path is the conventions-by-example reference. - PowerShell ≠ Java/C# UML. PowerShell is procedural. "Classes" map to
pscustomobjectrecord shapes; "messages" map to function calls and remote scriptblocks; "interfaces" map to parameter contracts andParameterSetconventions. Apply UML 2.x notation but bind it to PowerShell idioms, not Object-Oriented dogma. - The suite uses PlantUML, not Mermaid. PlantUML covers the full UML spec (deployment, object, timing). The corpus is
.pumlfiles rendered with the VS Codejebbs.plantumlextension or theplantuml.jarCLI. Mermaid is acceptable for inline-Markdown mini-diagrams (CHANGELOG entries, README sketches) where simplicity beats coverage, but not for the canonical project diagrams. - No paying customers yet. Diagrams are an internal-quality / inbound-credibility asset, not a customer deliverable. Keep them clean enough that a senior engineer reading them on GitHub forms a fair mental model in 10 minutes per diagram.
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.
- today First seen · 123 lines · 194 tokens per session scan A 824688f1428a
virtual-uml-architect is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 194 tokens to every session and 4,509 once invoked, about $0.0008 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 2026-11-18.
virtual-uml-architect compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| virtual-uml-architectgreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 194 | Claude Code |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |