Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Desko77/cursor-1c-skillsnpx agentmods add skills/desko77/cursor-1c-skills/mermaid-renderWrote 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/desko77/cursor-1c-skills/mermaid-render)<a href="https://agentmods.dev/skills/desko77/cursor-1c-skills/mermaid-render"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/mermaid-render/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/desko77/cursor-1c-skills/mermaid-render"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/mermaid-render.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00166 | $0.01209 |
| Opus 5 | $0.00083 | $0.00605 |
| Sonnet 5 | $0.00033 | $0.00242 |
| Haiku 4.5 | $0.00017 | $0.00121 |
Grade A, and why
mermaid-render 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 6d 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.
This is a copy
100% identical to mermaid-render — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mermaid-render - Рендер mermaid-диаграмм в изображения
Тонкая обертка над mmdc (mermaid-cli). Внутри Puppeteer + Chrome headless + mermaid.js, как в peng-shawn/mermaid-mcp-server, но без MCP-сервера и без Docker.
Зависимости
mmdc(@mermaid-js/mermaid-cli) - проверь:mmdc --version. Если нет -npm install -g @mermaid-js/mermaid-cli.- Python 3 в PATH (для скрипта-обертки).
Использование
python ~/.claude/skills/mermaid-render/scripts/render.py <вход> [опции]
Сценарии входа
| Расширение | Поведение |
|---|---|
.mmd / .mermaid |
Один файл с диаграммой -> одна картинка |
.md / .markdown |
Извлекает все блоки ```mermaid -> по картинке на блок (<имя>-1.png, <имя>-2.png, ...) |
Опции
| Флаг | По умолчанию | Назначение |
|---|---|---|
-o, --output |
рядом с входом | Выходной файл (для .md - префикс перед -N.<ext>) |
-t, --theme |
default |
default / forest / dark / neutral |
-b, --bg |
white |
white, transparent, #F0F0F0 |
-f, --format |
png |
png / svg / pdf |
-w, --width |
mmdc default 800 | Ширина в пикселях |
-H, --height |
mmdc default 600 | Высота в пикселях |
-s, --scale |
2 |
Puppeteer scale - 2 для retina |
--verbose |
выкл | Показать вывод mmdc |
Примеры
# Простой PNG рядом с входом, дефолтная тема, scale=2
python ~/.claude/skills/mermaid-render/scripts/render.py ./diagram.mmd
# Темная тема, прозрачный фон, SVG
python ~/.claude/skills/mermaid-render/scripts/render.py ./diagram.mmd -t dark -b transparent -f svg
# Все блоки mermaid из markdown в PNG-файлы
python ~/.claude/skills/mermaid-render/scripts/render.py ./README.md
# Указать выходной путь
python ~/.claude/skills/mermaid-render/scripts/render.py ./d.mmd -o ./out/result.png
Алгоритм работы для Claude
- Уточни у пользователя входной файл, если не передан явно. Поддерживаются
.mmd,.mermaid,.md. - Если пользователь не указал параметры рендера - используй дефолты (PNG, default-тема, белый фон, scale=2).
- Запусти скрипт через Bash:
python ~/.claude/skills/mermaid-render/scripts/render.py "<путь>" [-t ...] [-b ...] [-f ...]
- Скрипт печатает список созданных файлов с размерами - покажи пользователю.
- Если пользователь хочет встроить картинки в Markdown/Word - после рендера используй существующие скилы (
md-to-docxдля Word, обычные![]ссылки для Markdown).
What ships with it
1 file 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.
- 6d ago First seen · 80 lines · 166 tokens per session scan A d11726fbb5c1
mermaid-render is a skill published in the GitHub repository Desko77/cursor-1c-skills (55 stars, last pushed 8d ago), licensed MIT. It adds 166 tokens to every session and 1,209 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mermaid-render, differing in 13 lines, and is treated as a copy.
Other skills, from other repositories
1c-form-patterns
A reference guide to common layouts and naming conventions for managed 1C forms. It describes typical structures for documents, data processors, and other screens.
docx-from-sample
A document-generation tool that creates a new DOCX file using an existing Word document as its formatting template. DOCX is the standard editable Microsoft Word document format.
md-to-docx
A converter that turns a Markdown file into a formatted Microsoft Word document in DOCX format.
1c-mxl-compile
A compiler that turns a JSON description into an XML layout for a 1C tabular document. Tabular documents are 1C layouts used for printed forms and reports.
1c-mxl-decompile
A converter that turns an existing 1C tabular-document layout in XML into a compact JSON description. The JSON can be read and edited more easily than the original XML.
1c-mxl-info
A structure-inspection tool for 1C tabular-document layouts, which define printed forms and reports. It lists named areas, parameters, and column groups instead of showing the full XML file.