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 fmind/dotfiles --skill mermaidgit clone --depth 1 https://github.com/fmind/dotfilesWrote 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/dotfiles/mermaid)<a href="https://agentmods.dev/skills/fmind/dotfiles/mermaid"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/mermaid/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/fmind/dotfiles/mermaid"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/mermaid.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 | $0.00033 | $0.00965 |
| Opus 5.5 | $0.00013 | $0.00386 |
| Sonnet 5.5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00097 |
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 1mo 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 — 76 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 can render directly in GitHub Markdown and inside Slidev decks. Keep the source portable, reviewable, and close to the prose it explains.
Decision Boundary
- Use Mermaid for flowcharts, sequences, states, classes, entity relationships, timelines, mind maps, Git graphs, and other compact technical visuals.
- Use LikeC4 instead when the architecture model is the durable source of truth and must generate multiple consistent views.
- Use D2 instead for an existing D2 codebase or a bespoke standalone composition that Mermaid cannot express clearly.
- Omit the diagram when prose, code, a short list, or a table communicates the point more directly.
Workflow
-
State one visual thesis and the reader decision it supports.
-
Choose the simplest stable diagram type supported by every target renderer. Prefer
flowchart,sequenceDiagram,stateDiagram-v2,classDiagram, anderDiagramfor GitHub and Slidev portability. -
Write the editable source as a fenced
mermaidblock when it belongs to one Markdown document, or as a.mmdfile when it is reused or rendered independently. -
Keep labels short, relationships explicit, direction intentional, and the node count small enough to read without zooming.
-
Use Mermaid frontmatter for configuration. Do not add deprecated
%%{init: ...}%%directives to new diagrams. -
Apply the Fmind theme from fmind-theme when the work represents Médéric or
www.fmind.dev. -
Validate and render locally:
mmdc -i diagram.mmd -o diagram.svg -b transparent -
Inspect the actual render for clipping, line crossings, contrast, spelling, label density, and mobile or slide readability.
-
Keep the Mermaid source. Add SVG by default only when the target cannot render Mermaid; add PNG only when a platform requires raster output.
Portable Embedding
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.
- 1mo ago First seen · 76 lines · 33 tokens per session scan A f09856cafc13
mermaid is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 965 once invoked, about $0.0001 per session on Opus 5.5. 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
web-frontend
Build browser UIs with HTML, CSS, JavaScript, and Tailwind.
product-design-review
Review UI/UX: journeys, copy, hierarchy, accessibility, responsive states.
fmind-visuals
Create Typst decks, VHS terminal demos, and logo or cover variants in Fmind or client branding.
diagrams-as-code
Create and check Mermaid, SVG, and D2 diagrams and README illustrations.
full-review
Full review: read every repo area, apply verified fixes, and prove all checks pass.
duckdb
Query and export CSV, Parquet, JSON, or SQLite data with DuckDB.