Borrowing it
Nothing to install: this file belongs to lilepeeps/Azure-DrawIO-MCP. 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/lilepeeps/Azure-DrawIO-MCP/main/.github/skills/update-azure-shapes/SKILL.mdgit clone --depth 1 https://github.com/lilepeeps/Azure-DrawIO-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/lilepeeps/azure-drawio-mcp/update-azure-shapes)<a href="https://agentmods.dev/skills/lilepeeps/azure-drawio-mcp/update-azure-shapes"><img src="https://agentmods.dev/badge/skills/lilepeeps/azure-drawio-mcp/update-azure-shapes/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/lilepeeps/azure-drawio-mcp/update-azure-shapes"><img src="https://agentmods.dev/badge/skills/lilepeeps/azure-drawio-mcp/update-azure-shapes.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 | $0.00049 | $0.02619 |
| Opus 5 | $0.00024 | $0.01309 |
| Sonnet 5 | $0.00010 | $0.00524 |
| Haiku 4.5 | $0.00005 | $0.00262 |
Grade A, and why
update-azure-shapes 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 12d 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.
1. **Fetch icon data** using curl + jq (or Python if jq unavailable) How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Azure Shapes from DrawIO Repository
This skill helps you update the azure_shapes.py file with the latest Azure icons from the official DrawIO repository.
When to use this skill
Use this skill when:
- Asked to update or refresh Azure shape definitions
- Need to sync with the latest Azure icons from DrawIO
- Want to add new Azure services that are available in DrawIO
- Need to verify which Azure icons are available
Process Overview
- Fetch icon data using curl + jq (or Python if jq unavailable)
- Analyze what's new, removed, or changed
- Update azure_shapes.py with proper naming and categorization
- Validate the changes
Step 1: Analyze Differences
Use the provided analysis script to compare DrawIO repository with current shapes:
python .github/skills/update-azure-shapes/analyze_icons.py
This script will:
- Check for duplicate keys in azure_shapes.py (prevents bugs where duplicate keys cause earlier definitions to be invisible)
- Fetch the latest icon list from DrawIO GitHub repository
- Compare with current azure_drawio_mcp_server/azure_shapes.py
- Report new icons available in DrawIO
- Report any icons we reference that no longer exist
Important: The script exits with an error if duplicate keys are found, as these cause incorrect reporting of "new" icons. When a key appears twice in the dictionary, only the last definition is kept, making the first one appear as a missing icon.
Step 2: Analyze and Update azure_shapes.py
Read the current azure_drawio_mcp_server/azure_shapes.py file and:
-
Extract category and filename from each path:
- Path:
src/main/webapp/img/lib/azure2/compute/Virtual_Machine.svg - Category:
compute - Filename:
Virtual_Machine.svg - Relative path for code:
compute/Virtual_Machine.svg
- Path:
-
Generate Python key (CamelCase with smart singularization):
- Remove underscores and convert to CamelCase
- Singularize resource types (instances):
Virtual_Machines.svg→VirtualMachine - Preserve service names that are inherently plural:
Cognitive_Services.svg→CognitiveServices - Examples:
Subscriptions.svg→Subscription(resource type - singular)Storage_Accounts.svg→StorageAccount(resource type - singular)Managed_Identities.svg→ManagedIdentity(resource type - singular)Container_Instances.svg→ContainerInstance(resource type - singular)Cognitive_Services.svg→CognitiveServices(official Microsoft service name - plural)Analysis_Services.svg→AnalysisServices(official Microsoft service name - plural)Storage_Azure_Files.svg→StorageAzureFiles(official Microsoft service name - plural)
What ships with it
2 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.
- 12d ago First seen · 281 lines · 49 tokens per session scan A 7979fe6439b7
update-azure-shapes is a skill published in the GitHub repository lilepeeps/Azure-DrawIO-MCP (11 stars, last pushed 7mo ago), licensed MIT. It adds 49 tokens to every session and 2,619 once invoked, about $0.0002 per session on Opus 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.
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.