mermaid-authoring-guidelines

mermaid-authoring-guidelines is a skill for Claude Code, Codex from MatrixFounder/Agentic-development. It costs 83 tokens per session (4,608 once invoked), scanned A, original, Apache-2.0.

Guidelines for deciding whether a document needs a diagram and, if so, choosing a list, table, ASCII drawing, or Mermaid. Mermaid is a text format for diagrams that can be rendered in tools such as GitHub and code editors.

In plain words
What is it for?
Use them when creating or repairing architecture, sequence, state, or project-plan diagrams in Markdown documents.
Why use it?
They help prevent diagrams that are harder to read than the text, contain unsupported facts, or render poorly in different viewers. They also set rules for checking layout, legends, and fidelity across Mermaid versions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use them when creating or repairing architecture, sequence, state, or project-plan diagrams in Markdown documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matrixfounder/agentic-development/mermaid-authoring-guidelines
Install

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.

Any agent
npx skills add MatrixFounder/Agentic-development --skill mermaid-authoring-guidelines
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mermaid-authoring-guidelines

README.md
[![agentmods](https://agentmods.dev/badge/skills/matrixfounder/agentic-development/mermaid-authoring-guidelines/github.svg)](https://agentmods.dev/skills/matrixfounder/agentic-development/mermaid-authoring-guidelines)
Your own site
<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/mermaid-authoring-guidelines"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/mermaid-authoring-guidelines/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.

agentmods 80×15 button for mermaid-authoring-guidelines

Your own site · 80×15
<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/mermaid-authoring-guidelines"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/mermaid-authoring-guidelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.04608
Opus 5.5 $0.00033 $0.01843
Sonnet 5.5 $0.00017 $0.00922
Haiku 4.5 $0.00008 $0.00461

Measured 2d ago against content hash 561328b425db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mermaid-authoring-guidelines 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 2d 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.

.agent/skills/mermaid-authoring-guidelines/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mermaid authoring guidelines

Purpose. A figure in a Markdown artifact restates facts of the text in a form a reader traces at a glance, in every viewer that shows the document. This skill decides whether a figure is needed and in which form. When the form is Mermaid, it fixes how the figure is drawn: one concern, a size budget, no avoidable crossings, and nothing the text does not state. A render check runs in the two versions readers run: mermaid 11.17 (GitHub, VS Code) and 10.9 (JetBrains IDEs).

Load it before the first figure of any output, in any phase. The rules hold in any document language: scripts find caption and legend by their position, never by a word.

1. Red Flags (Anti-Rationalization)

  • "A diagram means Mermaid." Step 0 comes first. A terminal shows Mermaid as code, a many-to-many relation reads better as a table, and a short chain reads better as a list.
  • "One figure for the whole section is more complete." Structure, time and state in one figure produce edges nobody can follow. Split by concern; do not trim.
  • "The layout engine will sort it out." dagre reduces crossings heuristically. It cannot remove the ones the graph forces (Step 4.3). Reduce, aggregate or split the graph itself.
  • "I'll reorder the declarations until it looks right." Order moves nodes in some figures and not in others. Change the structure first (Step 4.7).
  • "The text implies this relation, I'll add it." Draw only what a line of the text states. An invented arrow is read as a fact by the next implementer.
  • "The colours explain themselves." A legend sits below the fence and names the notation this figure uses. Colour never carries a category alone.
  • "It renders in my preview." GitHub runs 11.17, JetBrains 10.9, and 12.x changed every default. GitHub also redraws HTML labels in its own font after mermaid sized them (RF-23 of references/renderer-facts.md). Check both pinned versions, or write not rendered in the hand-off.
  • "LR fits better." Width sets the text size: a 900 px column shrinks the text of an 1800 px figure to half. A flowchart of more than 6 nodes runs top to bottom.
  • "I'll set the font and the theme for a consistent look." Mermaid blanks any theme value containing -, _, : or /, so sans-serif disappears. A fixed theme draws dark text on GitHub's dark page. Set neither.

Read the full file on GitHub · 299 lines

Files

What ships with it

60 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.

Changes

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.

  1. 2d ago Changed · +4 lines 561328b425db
  2. 11d ago Changed · -5 lines b6b2e87bed21
  3. 13d ago First seen · 300 lines · 83 tokens per session scan A 7d568efb9540

Subscribe to this mod's changes

mermaid-authoring-guidelines is a skill published in the GitHub repository MatrixFounder/Agentic-development (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 4,608 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 2026-10-04.