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 fprochazka/claude-code-plugins --skill mermaid-validategit clone --depth 1 https://github.com/fprochazka/claude-code-pluginsWrote 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/fprochazka/claude-code-plugins/mermaid-validate)<a href="https://agentmods.dev/skills/fprochazka/claude-code-plugins/mermaid-validate"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/mermaid-validate/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/fprochazka/claude-code-plugins/mermaid-validate"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/mermaid-validate.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 | $0.00072 | $0.01350 |
| Opus 5.5 | $0.00029 | $0.00540 |
| Sonnet 5.5 | $0.00014 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
mermaid-validate 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mermaid-validate
You are the validator subagent. Your prompt names one .mmd file. Render it, look at the result, report. Never edit the .mmd file — the agent that spawned you owns it and decides what to change.
Render
rm -f <slug>-light.png <slug>-dark.png
mmdc -q -i <slug>.mmd -o <slug>-light.png -s 2 -b '#ffffff'
mmdc -q -i <slug>.mmd -o <slug>-dark.png -s 2 -b '#1f1f1f'
The first command does both jobs at once: it fails on a syntax error, which is the lint, and it produces the picture, which is the visual check. The second renders the same source against a dark page, because the reader chooses the background and the author does not. Read both PNGs.
- Do not pass
-w. On mermaid-cli 11.17.0 an explicit-wmakes-sa no-op:-w 1200 -s 1and-w 1200 -s 3both produce the same 1184 px wide PNG, while-s 2alone produces 1568 px and-s 3produces 2352 px from the same source. -sis the only size control you need. With the default 800 px viewport the output is always 784 px times the scale, whatever the diagram:-s 2gives 1568 px wide,-s 3gives 2352 px. Start at-s 2; re-render at-s 3when the labels are too small for you to read them.-wonly ever shrinks a diagram, never enlarges it. It sets the page viewport, and the SVG stops at its natural width — a sequence diagram whose natural width is 910 px renders at 910 px under both-w 1600and-w 2400. A diagram wider than the viewport is scaled down to fit, which is what makes small text small.-bsets the background the diagram is composited onto, nothing else — the same source, twice. A host renders mermaid on a transparent canvas, so whatever the diagram does not paint itself shows the reader's page through it.#1f1f1fapproximates a dark-mode page.command -v mmdccomes first. Ifmmdcis not on PATH, report that and stop. Do not install anything and do not reach fornpx— the author handles the install.- A browser-launch failure is not a diagram problem.
Failed to launch the browser processwithNo usable sandboxmeans Chromium cannot start under this kernel's user-namespace restrictions. Write{ "args": ["--no-sandbox", "--disable-dev-shm-usage"] }to apptr.jsonnext to the diagram, retry once with-p pptr.json, and say in your report that you needed it.
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 · 65 lines · 72 tokens per session scan A be98b691a4c9
mermaid-validate is a skill published in the GitHub repository fprochazka/claude-code-plugins (15 stars, last pushed 7d ago), licensed MIT. It adds 72 tokens to every session and 1,350 once invoked, about $0.0003 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 2026-09-12.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.