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 larsboes/Axon --skill diagramsgit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/diagrams)<a href="https://agentmods.dev/skills/larsboes/axon/diagrams"><img src="https://agentmods.dev/badge/skills/larsboes/axon/diagrams/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/larsboes/axon/diagrams"><img src="https://agentmods.dev/badge/skills/larsboes/axon/diagrams.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 | $0.00150 | $0.01281 |
| Opus 5 | $0.00075 | $0.00641 |
| Sonnet 5 | $0.00030 | $0.00256 |
| Haiku 4.5 | $0.00015 | $0.00128 |
Grade A, and why
diagrams 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagrams
A diagram source is text. A figure is the PNG it renders to. This skill turns the first into the second with the colours of the artifact that will embed it.
The tool surface is <skill>/scripts/diagrams theme|render|doctor. Python runs
through uv, which pins the interpreter. The renderer is pinned in the code, not
floating.
The one idea
The palette is the source, and the renderer theme is derived. A deck already
carries a palette in theme.json. A paper carries one in whatever file its plot
tooling reads. A diagram must not have a third one, because a diagram authored in
its own colours is the figure that makes the slides around it look borrowed.
So the Mermaid theme is never hand-written. diagrams theme reads a palette and
writes a renderer config. Change accent in theme.json and every diagram
follows on the next render.
| what Mermaid needs | where it comes from |
|---|---|
| node fill, node border, text | the theme's diagram.node_fill, accent, ink |
| edges and arrows | accent |
| cluster background and border | paper, diagram.cluster_edge |
| secondary and tertiary surfaces | secondary_light, paper |
| stroke width, wrapping width | layout defaults, overridable from diagram |
The full table is in references/mermaid.md, with the layout defaults and the
measurement behind each one.
Workflow
- [ ] 1. A .mmd source exists, or you write one
- [ ] 2. diagrams render <mmd-dir> → the theme is derived, the figures are written
- [ ] 3. Read the aspect ratio the tool prints
- [ ] 4. Place the figure, with alt= and — for reproduced material — credit=
- [ ] 5. Render the artifact and look at it
1. Write the source
A .mmd holds the structure, never a colour. Structure is flowchart TB for a
tree, flowchart LR for a sequence. Node text is **heavy** and <i>italic</i>
inside the label, because Mermaid renders HTML when htmlLabels is on. A <br/>
is the line break; a literal newline is not.
Node text should be labels, not sentences. A node that needs four lines of prose is a slide panel, not a diagram node.
What ships with it
8 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.
- references/mermaid.md 6.9 KB
- scripts/diagramkit/__init__.py 95 B runs code
- scripts/diagramkit/__main__.py 48 B runs code
- scripts/diagramkit/cli.py 6.1 KB runs code
- scripts/diagramkit/errors.py 181 B runs code
- scripts/diagramkit/render.py 2.9 KB runs code
- scripts/diagramkit/theme.py 6.5 KB runs code
- scripts/diagrams 942 B
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 · 114 lines · 150 tokens per session scan A 33bff3036483
diagrams is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 1,281 once invoked, about $0.0007 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 2026-09-15.
Other skills, from other repositories
open-design-landing
Produce a world-class single-page editorial landing site in the Atelier Zero visual language (Monocle / Apartamento / Études editorial collage) — the same aesthetic OpenDesign uses for its own marketing surface. The agent fills a typed inputs.json from a brand brief, optionally generates 16 collage assets via…
design-brief
Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief"…
critique
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
tweaks
Wrap any HTML artifact with a side panel of live, parameterized controls — accent color, type scale, density, motion, theme — that rewrite CSS custom properties in real time and persist to localStorage. Lets the user explore variants of a design without re-prompting the agent. Use when the brief asks for "variants"…
web-prototype
General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed assets/template.html and pasting section layouts from references/layouts.md. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.