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 jessepike/diagram-forge --skill diagram-intelligencegit clone --depth 1 https://github.com/jessepike/diagram-forgeWrote 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/jessepike/diagram-forge/diagram-intelligence)<a href="https://agentmods.dev/skills/jessepike/diagram-forge/diagram-intelligence"><img src="https://agentmods.dev/badge/skills/jessepike/diagram-forge/diagram-intelligence/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/jessepike/diagram-forge/diagram-intelligence"><img src="https://agentmods.dev/badge/skills/jessepike/diagram-forge/diagram-intelligence.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 | $0.00080 | $0.00595 |
| Opus 5 | $0.00040 | $0.00298 |
| Sonnet 5 | $0.00016 | $0.00119 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
diagram-intelligence 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram Intelligence Skill
When triggered, generate the diagram immediately. Do not present a menu of options or ask what type of diagram — infer it from the user's request and go.
MCP Tools
Call these directly:
mcp__diagram-forge__generate_diagram— Generate a diagram from a promptmcp__diagram-forge__edit_diagram— Edit an existing diagrammcp__diagram-forge__list_templates— List available templatesmcp__diagram-forge__list_providers— Check provider availabilitymcp__diagram-forge__list_styles— List style references
Behavior
-
Infer diagram type from the request. Default to
architecture. Map keywords:- "data flow", "pipeline", "ETL" →
data_flow - "sequence", "timeline" →
sequence - "components", "modules" →
component - "integration", "APIs" →
integration - "infographic", "summary" →
infographic - Everything else →
architecture
- "data flow", "pipeline", "ETL" →
-
Build a detailed prompt from the user's description. Enhance it with:
- "All text crystal clear and perfectly legible"
- "Professional, publication-ready"
- Explicit layout structure (layers, columns, flow direction)
- Named components with relationships
-
Call
mcp__diagram-forge__generate_diagramwith:prompt: the enhanced promptdiagram_type: inferred typeresolution: "2K"aspect_ratio: "16:9"
-
Show result: output path and cost. Offer
/iteratefor refinements.
Do NOT
- Present a menu asking what kind of diagram to create
- Ask the user to pick a template or provider
- Ask for confirmation before generating
- Say "what do you want to visualize?"
If the user said "create a diagram of X", you already know what X is. Generate it.
Prompt Engineering Tips
- Be explicit about layout (top-to-bottom layers, left-to-right flow)
- Name every element — don't say "show inputs", list each input by name
- Specify color coding rules — colors should encode meaning
- For architecture diagrams, organize into named layers
- Include a legend for any color coding used
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 · 63 lines · 80 tokens per session scan A 16c5ccae8fbd
diagram-intelligence is a skill published in the GitHub repository jessepike/diagram-forge (1 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 595 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
pr-lens
WHAT: Draws a code change or part of a codebase as an animated architecture or data-flow diagram, on its own or in a pull request. WHEN: asked to diagram, visualise or explain a change or a system, or when a pull request should carry a diagram. KEYWORDS: PR Lens, diagram, architecture, data flow, visualise, visualize…
MeiGen Visual Creative Expert
This skill should be used when the user asks to "generate an image", "create artwork", "design a logo", "make a poster", "draw something", "find inspiration", "search for reference images", "enhance my prompt", "improve prompt", "brand design", "product mockup", "batch generate images", "multiple variations"…
drawio-aws
Use when the user asks for an AWS architecture diagram — VPC/networking, event-driven, landing zone, multi-AZ, serverless pipeline, or any diagram built with AWS service icons. Builds with the declarative layout engine using ground-truth mxgraph.aws4 stencils, validates (stencils/colors/nesting/geometry), runs a…
drawio-databricks
Use when the user asks for a Databricks lakehouse architecture diagram — medallion architecture (Bronze/Silver/Gold), Delta Lake, Unity Catalog, workspace deployment, data-plane/control-plane, or any diagram built with Databricks icons. Builds with the declarative layout engine using ground-truth stencils, validates…
excalidraw-skill
Programmatic canvas toolkit for creating, editing, and refining Excalidraw diagrams via MCP tools with real-time canvas sync. Use when an agent needs to (1) draw or lay out diagrams on a live canvas, (2) iteratively refine diagrams using describescene and getcanvasscreenshot to see its own work, (3) export/import…
FlowForge
A draw.io diagram tool that turns a description or document into editable visual diagrams. Draw.io is software for making flowcharts, system diagrams, and other structured illustrations.