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 aiocean/claude-plugins --skill aio-mermaidgit clone --depth 1 https://github.com/aiocean/claude-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/aiocean/claude-plugins/aio-mermaid)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-mermaid"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-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 5.1 | $0.00097 | $0.01575 |
| Opus 5 | $0.00048 | $0.00788 |
| Sonnet 5 | $0.00019 | $0.00315 |
| Haiku 4.5 | $0.00010 | $0.00158 |
Grade A, and why
aio-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 7d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MinimalMermaid URL Generator
Environment
- bun: !
which bun 2>/dev/null || echo "NOT INSTALLED" - node: !
which node 2>/dev/null || echo "NOT INSTALLED"
Base URL: https://mimaid.aiocean.dev/
🚨 CRITICAL: NO MARKDOWN IN MERMAID CODE
Mermaid is NOT markdown. These will BREAK your diagram:
❌ **bold** - NEVER use double asterisks
❌ *italic* - NEVER use single asterisks
❌ _underscore_ - NEVER use underscores for emphasis
❌ [link](url) - NEVER use markdown links
❌ `code` - NEVER use backticks inside labels
❌ # headers - NEVER use hash headers
✅ CORRECT: A[User clicks button]
❌ WRONG: A[User **clicks** button]
❌ WRONG: A[User _clicks_ button]
❌ WRONG: A[See [docs](url)]
Use Mermaid v11 Syntax
Use flowchart NOT graph:
flowchart TD
A[Start] --> B[End]
Use v11 shape syntax:
flowchart TD
A@{ shape: stadium, label: "Terminal" }
B@{ shape: diamond, label: "Decision" }
C@{ shape: cyl, label: "Database" }
A --> B --> C
Available shapes: rect, rounded, stadium, diamond, hex, cyl, doc, docs, delay, trap-t, trap-b, fork, cloud, odd
Use styling instead of markdown:
flowchart TD
A[Important] --> B[Step]
style A fill:#ff6b6b,stroke:#c92a2a,color:#fff
How It Works
MinimalMermaid stores diagram code in the URL hash using LZ-String compression:
- Compression:
LZString.compressToEncodedURIComponent(code) - Decompression:
LZString.decompressFromEncodedURIComponent(hash)
Generating URLs
Use JavaScript to generate shareable URLs:
// Using lz-string library
const LZString = require("lz-string");
const mermaidCode = `flowchart TD
A[Start] --> B{Decision}
B -->|Yes| C[Do Something]
B -->|No| D[Do Nothing]
C --> E[End]
D --> E`;
const compressed = LZString.compressToEncodedURIComponent(mermaidCode);
const url = `https://mimaid.aiocean.dev/#${compressed}`;
console.log(url);
Quick Generation (Bash)
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.
- 7d ago First seen · 179 lines · 97 tokens per session scan A 9c40a75fe0bb
aio-mermaid is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 1,575 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
plan-review-experience
Experience-dimension reviewer for written plans (UX + DX). Use when running plan-review or directly when an experience review is wanted. Activate for keywords like "UX review", "DX review", "experience review", "error states", "API ergonomics", "developer experience", "user states". Scores 5 sub-dimensions 0-10…
vellum-workspace-theme
Customize the app's visual theme — author design-token overrides (accent, background, surfaces, text, message-bubble colors) in the workspace ui/theme.json, validated by the assistant runtime and applied live to connected clients. Covers the token slots, the all-or-none override groups, the contrast floor, and reading…
vellum-avatar
Customize the assistant's avatar - build a native character, upload an image, or generate one with AI.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.