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 iammrduncan/fxbot --skill mermaidgit clone --depth 1 https://github.com/iammrduncan/fxbotWrote 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/iammrduncan/fxbot/mermaid)<a href="https://agentmods.dev/skills/iammrduncan/fxbot/mermaid"><img src="https://agentmods.dev/badge/skills/iammrduncan/fxbot/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/iammrduncan/fxbot/mermaid"><img src="https://agentmods.dev/badge/skills/iammrduncan/fxbot/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 | $0.00062 | $0.01157 |
| Opus 5.5 | $0.00025 | $0.00463 |
| Sonnet 5.5 | $0.00012 | $0.00231 |
| Haiku 4.5 | $0.00006 | $0.00116 |
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 4d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagrams
Your replies and Markdown pages draw ```mermaid code blocks as diagrams, in the app's own colors and font. They're drawn by Pele, which reads Mermaid's syntax. The owner sees the diagram, and can switch to its code, copy it, download it, or open it full screen.
When to draw one
| To show | Draw |
|---|---|
| A process with steps and choices | flowchart |
| What happens between people, services, or systems, in order | sequenceDiagram |
| States, and what moves between them | stateDiagram-v2 |
| Things and how they relate | erDiagram, classDiagram, or mindmap |
| Dates and durations | gantt or timeline |
| Shares of a whole | pie |
| Numbers over time | xychart |
Don't draw one for a list, a few steps in a row, or a comparison: a list or a table says it better. Keep a diagram to one point, under about 25 nodes or 15 messages. For more, draw two.
Say in a sentence what it shows, next to it.
Writing one that draws
- Open with the fence and the type:
```mermaid, then the type on the first line, such asflowchart LR. - Quote a label with punctuation:
A["Step 1 (draft)"]. For a quote mark inside one, write#quot;. - No lowercase
endas a word in a flowchart's text or as an id. WriteEnd, or quote it. - A space after a link before an id that starts with
oorx:dev --- ops, notdev---ops, which reads as a circle arrow. - One statement a line. Arrows are
-->in a flowchart, and->>and-->>in a sequence diagram. A link's label goesA -->|yes| B. - Direction:
LRreads left to right,TDtop to bottom. On a phone, a wide diagram turns to run top to bottom by itself. - What fxbot leaves out: links and
click, images, icons such asfa:fa-car, math, and HTML in labels. Frontmatter and%%{init}%%can't change its colors, fonts, or look: the app sets them.
Check it
Before you send a diagram, call mermaid_check with its source, without the fence. It draws it as the owner will see it, and answers what it drew, or the error and its line. Fix it, and check again.
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.
- 4d ago First seen · 129 lines · 62 tokens per session scan A 4f06c1ec3517
mermaid is a skill published in the GitHub repository iammrduncan/fxbot (16 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 1,157 once invoked, about $0.0002 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 2026-11-11.
mermaid compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mermaidiammrduncan/fxbot | Skill | 16 | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| frontend-designyrris/pro-agent | Skill | 23 | 3mo ago | none | A | 38 | Claude Code, Codex |
| prototyperengwu/iudex | Skill | 15 | 4mo ago | none | A | 90 | Claude Code, Codex |
| skin-creatornetease-youdao/LobsterAI | Skill | 6.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| a2uiPrism-Shadow/penguin-harness | Skill | 3.2k | today | Apache-2.0 | A | 203 | Claude Code, Codex |
| oma-designfirst-fluke/oh-my-agent | Skill | 1.5k | today | MIT | A | 32 | Claude Code |
| visual-acceptancehuiliyi37/Tianshu-harness | Skill | 1.3k | 9d ago | Apache-2.0 | A | 89 | Claude Code, Codex |