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 OKHP3/skillz --skill diagramminggit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/diagramming)<a href="https://agentmods.dev/skills/okhp3/skillz/diagramming"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/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/okhp3/skillz/diagramming"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/diagramming.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 | $0.00096 | $0.01458 |
| Opus 5 | $0.00048 | $0.00729 |
| Sonnet 5 | $0.00019 | $0.00292 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
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 6d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagramming
A diagram earns its place by answering one question faster than a paragraph could. A diagram showing everything answers nothing — it is the visual equivalent of a page with no headings.
Draw diagrams as code. A Mermaid block in the repository is diffable, reviewable, and edited by whoever changes the system. An exported PNG from someone's laptop is wrong within a month and nobody can fix it.
1. Decide the question, then pick the type
Match the diagram to what the reader is asking:
| Reader's question | Diagram |
|---|---|
| What are the pieces and how do they connect? | Component / C4 container |
| What happens, in what order, between whom? | Sequence |
| What states can this be in, and what moves it? | State |
| How is the data shaped and related? | ER |
| What are the steps and decisions? | Flowchart |
| Who depends on whom for deployment? | Deployment |
Choosing wrong is the most common failure. Component diagrams are drawn for questions that are really about ordering, and a sequence diagram would have answered them in half the space.
Done when: you can state the one question this diagram answers.
2. Pick one level of abstraction and stay there
Mixing levels is what makes diagrams unreadable — a box for "Payments" next to a box for "validate_card()" gives the reader no consistent scale to reason at.
The C4 levels are a useful discipline even without adopting the notation:
- Context — your system and the people and systems around it. One box for you
- Container — the deployable pieces: services, databases, queues, front ends
- Component — inside one container
- Code, usually better generated than drawn
Most useful diagrams are level 1 or 2. Level 3 dates fast; level 4 almost never earns its maintenance.
Done when: every box on the diagram is the same kind of thing.
3. Keep it under about nine boxes
Past roughly nine elements, a reader stops seeing structure and starts tracing lines.
When you exceed it: split into several diagrams at different levels, collapse a group into one labelled box, or cut everything not needed for this diagram's question. Splitting is almost always better than shrinking the font.
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.
- 6d ago First seen · 147 lines · 96 tokens per session scan A fdc997f4df5d
diagramming is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 1,458 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
pm-brand-motion
A guided process for defining a brand's motion style and making a logo animation demonstration.
pm-proto
A product-prototyping workflow for planning how an application should work and what its screens should contain. It connects product requirements to interface layouts and interactions.
json-canvas
An Obsidian skill for generating JSON Canvas files. JSON Canvas is a file format for arranging connected boxes and other elements on a visual canvas.
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
web-design-analyzer
A web-design analysis helper that extracts colours, typography, and component patterns from a webpage screenshot, then produces structured design-system data and a coding prompt.