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 agentmods add skills/fmind/dot/mermaidnpx skills add fmind/dot --skill mermaidgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/mermaid)<a href="https://agentmods.dev/skills/fmind/dot/mermaid"><img src="https://agentmods.dev/badge/skills/fmind/dot/mermaid.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00876 |
| Opus 5 | $0.00022 | $0.00438 |
| Sonnet 5 | $0.00009 | $0.00175 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
mermaid 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 yesterday.
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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mermaid Diagram Standard
Mermaid is the default diagram format because the same editable text renders in GitHub Markdown, Hugo sites (Hextra bundles it), and Slidev decks. Keep the source portable, reviewable, and close to the prose it explains; the choice between Mermaid, D2, LikeC4, or no diagram lives in fmind-visuals.
Workflow
-
State the thesis: one visual claim and the reader decision it supports; omit the diagram when prose, code, a list, or a table is more direct.
-
Pick a stable type: prefer
flowchart,sequenceDiagram,stateDiagram-v2,classDiagram, anderDiagram; avoid a newly released type until every target renderer's Mermaid version supports it (GitHub reports its version from a block containinginfo). -
Write portable source: a fenced
mermaidblock when the diagram belongs to one Markdown document, a.mmdfile when it is reused or rendered independently; keep labels short, direction intentional, and the node count readable without zooming. -
Configure in frontmatter: put configuration in Mermaid frontmatter, never in
%%{init: ...}%%directives or renderer-specific fence options; apply the Fmind theme from fmind-theme when the work represents Médéric orwww.fmind.dev. -
Validate and render:
mmdc -i diagram.mmd -o diagram.svg -b transparent -
Inspect the render: clipping, line crossings, contrast, spelling, label density, and mobile or slide readability.
-
Ship the source: keep the Mermaid text; add SVG only when the target cannot render Mermaid and PNG only when a platform requires raster output, and add
accTitleandaccDescror surrounding prose so the conclusion survives without the image.
Gotchas
- No browser found:
mmdcfails withCould not find chrome-headless-shellwhen the Puppeteer download is absent; point it at system Chrome:PUPPETEER_EXECUTABLE_PATH=/usr/bin/google-chrome mmdc -i diagram.mmd -o diagram.svg. - Clipped labels: set one renderer-stable font stack through root-level
config.fontFamily; late-loading web fonts change label measurements after layout and clip inside fixed bounds. - Deprecated option:
flowchart.htmlLabelsis deprecated; do not add it to new diagrams. - Non-portable features: keep remote images, custom JavaScript, click callbacks, and renderer plugins out of shared source.
- Dense diagrams: split into views instead of shrinking labels; left-to-right for slide-sized processes, top-to-bottom for document hierarchies.
- Invented structure: preserve source terminology; never add metrics, components, trust boundaries, or causal links the evidence does not show.
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.
- yesterday First seen · 44 lines · 44 tokens per session scan A 51d5eba3cd29
mermaid is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 876 once invoked, about $0.0002 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
fmind-visuals
Apply the Fmind visual identity and route slide or diagram work to Slidev, Mermaid, LikeC4, or D2. Use for Fmind talks, decks, article diagrams, architecture visuals, and www.fmind.dev assets.
mermaid
Create, theme, validate, and embed Mermaid diagrams as the default text-based diagram format for GitHub, Slidev, documentation, and technical communication.
d2
Create, theme, validate, and export D2 diagrams when an existing D2 source or a bespoke standalone composition is a better fit than the default Mermaid workflow.
google-workspace-cli
Use gws across Workspace APIs with schema-first calls, profile isolation, bounded reads, and verified Drive, Docs, Sheets, Gmail, Calendar, or Chat writes.
product-design-review
Critique customer interface flows using interaction, visual, responsive, keyboard and screen-reader accessibility, content, and runtime evidence. Use for UX audits, design reviews, UI polish, onboarding, empty states, or redesign.
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.