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 mermaidgit 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)<a href="https://agentmods.dev/skills/fprochazka/claude-code-plugins/mermaid"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/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/fprochazka/claude-code-plugins/mermaid"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/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 | $0.00101 | $0.01969 |
| Opus 5.5 | $0.00040 | $0.00788 |
| Sonnet 5.5 | $0.00020 | $0.00394 |
| Haiku 4.5 | $0.00010 | $0.00197 |
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mermaid
A diagram in a plan, an MR description or a review comment is a sketch: selective, carrying one idea, thrown away when the work lands. It is not a specification of the system, and completeness is not the goal — "comprehensiveness is the enemy of comprehensibility" (Fowler).
The unit of work is a standalone .mmd file in the scratchpad, one diagram per file, with no code fence around it. Write it, validate it there, then hand the file content to whatever document needs it inside a mermaid code fence. Inlining is the calling command's last step, not this skill's.
1. Whether to draw at all
Write text instead when the relationship is linear (a numbered list), there are fewer than about three nodes (a sentence), the content is a payload or a data structure (a code fence), the reader needs exact values such as timeouts or error codes (a table), or you cannot say in one sentence what the reader should conclude. A picture with no conclusion is decoration.
Draw when a flow crosses three or more components, an entity has a lifecycle with guarded transitions, the point is ordering — a race, a retry, a handshake — or a structure changes and the before/after difference is the finding.
2. Which type
flowchart— the path a request takes through components, a decision with branches. The default when nothing more specific fits.sequenceDiagram— who calls whom in what order, two to six participants. The only type that shows time.stateDiagram-v2— one entity's lifecycle: order status, job state, a saga. Not a process with no return.erDiagram— tables and cardinality for a schema change. Not an object model.
Secondary, when they clearly fit: classDiagram, gitGraph, timeline. Every type with -beta in its keyword, every C4* type and mindmap are opt-in only — use one when the user asks for it by name. references/diagram-types.md has the per-type "use when / do not use when / pitfalls" table, including the reasons the beta types are excluded.
What ships with it
3 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.
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 · 78 lines · 101 tokens per session scan A ffe25b990ea4
mermaid is a skill published in the GitHub repository fprochazka/claude-code-plugins (15 stars, last pushed 7d ago), licensed MIT. It adds 101 tokens to every session and 1,969 once invoked, about $0.0004 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.