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 CES-Ltd/TitanX --skill mermaidgit clone --depth 1 https://github.com/CES-Ltd/TitanXWrote 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/ces-ltd/titanx/mermaid)<a href="https://agentmods.dev/skills/ces-ltd/titanx/mermaid"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/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/ces-ltd/titanx/mermaid"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/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 | $0.00051 | $0.00441 |
| Opus 5 | $0.00026 | $0.00220 |
| Sonnet 5 | $0.00010 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
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 9d 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.
What it actually says
Mermaid Diagram Renderer
Render Mermaid diagrams using beautiful-mermaid library. Supports 5 diagram types with dual output modes.
Quick Start
Dependencies (
beautiful-mermaid) auto-install on first run.
SVG Output (Default)
# From file
npx tsx scripts/render.ts diagram.mmd --output diagram.svg
# From stdin
echo "graph LR; A-->B-->C" | npx tsx scripts/render.ts --stdin --output flow.svg
ASCII Output (Terminal)
# ASCII art for terminal display
npx tsx scripts/render.ts diagram.mmd --ascii
# Pipe directly
echo "graph TD; Start-->End" | npx tsx scripts/render.ts --stdin --ascii
Output example:
┌───────┐ ┌─────┐
│ Start │────▶│ End │
└───────┘ └─────┘
Supported Diagrams
| Type | Syntax | Best For |
|---|---|---|
| Flowchart | graph TD/LR |
Processes, decisions |
| Sequence | sequenceDiagram |
API calls, interactions |
| State | stateDiagram-v2 |
State machines |
| Class | classDiagram |
OOP design |
| ER | erDiagram |
Database schemas |
Theming (SVG only)
npx tsx scripts/render.ts diagram.mmd --theme github-dark --output out.svg
Use invalid theme name to see available themes list (e.g., --theme ?)
Resources
scripts/render.ts- Main rendering scriptreferences/syntax.md- Mermaid syntax quick reference
What ships with it
2 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.
- 9d ago First seen · 64 lines · 51 tokens per session scan A 913966861d14
mermaid is a skill published in the GitHub repository CES-Ltd/TitanX (48 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 441 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
taste-profile
Build a scoped taste profile packet from examples, preferences, and explicit dislikes so downstream agents can make style decisions without inventing the user's taste.
convert-package
Build a complete sales asset end-to-end via The Donahoe Method: diagnostic → primitives → fingerprint → page → integrity-gate → visual → audit → report. Composite orchestrator that calls 14-16 sub-skills via delegatetask in an 8-phase DAG (sequential where dependencies require it, parallel where they don't). Produces…
ux-researcher
Becomes a senior UX researcher who designs user studies, conducts usability evaluations, synthesizes qualitative and quantitative insights, and delivers evidence-based design recommendations. Use when the user needs persona development, usability test plans, user journey maps, interview guides, or research findings…
visual-designer
Becomes a senior visual designer who creates design systems, defines design tokens, builds component specifications, establishes visual hierarchy principles, and ensures accessibility compliance. Use when the user needs design system documentation, component libraries, color and typography specifications, layout…
convert-above-fold
Engineer above-fold hierarchy for direct-response pages: 5-second comprehension test, hero rhythm, primary CTA placement, and visual scaffolding for the Four-Layer Open. Produces a wireframe spec + paste-ready HTML/CSS for the first viewport. Use when designing or rebuilding the top-of-page that must answer "what /…
market-landing
Run a section-by-section CRO teardown on a single landing page. Scores hero, value prop, social proof, features, objections, CTA, and footer; audits forms, mobile, and page speed; outputs prioritized fixes (quick wins / strategic / long-term) and A/B test hypotheses to a client-ready markdown report. Activates on…