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 Desko77/cursor-1c-skills --skill mermaid-diagramsgit clone --depth 1 https://github.com/Desko77/cursor-1c-skillsWrote 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-diagrams)<a href="https://agentmods.dev/skills/desko77/cursor-1c-skills/mermaid-diagrams"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/mermaid-diagrams/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-diagrams"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/mermaid-diagrams.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01729 |
| Opus 5 | $0.00016 | $0.00864 |
| Sonnet 5 | $0.00007 | $0.00346 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
mermaid-diagrams 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.
This is a copy
100% identical to mermaid-diagrams — 206 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mermaid Diagrams Skill
This skill provides:
- A conservative set of Mermaid templates that render on older renderers (VS Code/Markdown previewers, Git platforms) and remain clear to humans.
- Guidance on which diagram type to use for which situation.
- Compatibility tips and fallbacks when advanced Mermaid types are unavailable.
Compatibility Rules (Read First)
- Prefer
graph LR/graph TBfor flowcharts; some renderers fail onflowchartkeyword. - Quote labels containing spaces/special characters:
A["Text (x|y) |"]. - Do not use literal
\ninside labels - Mermaid does not interpret such line breaks. Use<br/>for line breaks. - Advanced types like
quadrantChart,sankey-beta,requirementDiagram,gitGraphmay not be available. Use provided flowchart fallbacks. - Code fences must start at column 0 with language
mermaid.
ASCII/Unicode Sidecar (Human-Readable Raw Markdown)
To optimize for quick human scanning in raw Markdown and robust parsing by agents, always ship an ASCII/Unicode sidecar immediately below each Mermaid block.
Policy:
- MUST include a monospace, text-only diagram right under the Mermaid block using fenced code with language
text. - MUST keep Mermaid and sidecar in sync (same nodes/edges, same labels where feasible). If they diverge, treat Mermaid as the source of truth and update the sidecar.
- SHOULD limit width to ~80 columns for readability in diffs and terminals.
- SHOULD use simple line art characters (ASCII first; Unicode box-drawing optional when environment supports it).
- MAY add a one-line caption above the pair:
Diagram: <name> (<type>).
Recommended primitives:
- Boxes:
[Name],(Name),+-----+\n| N |\n+-----+ - Flows:
-->, decisions as{cond?}lines, lists with-. - Sequence (text-based):
Actor -> Actor: messagewith indented lifelines.
Example (Flowchart):
graph LR
A["Start"] --> B{Auth?}
B -->|Yes| C["Dashboard"]
B -->|No| D["Login"]
Diagram: Auth flow (flowchart)
[Start] --> {Auth?}
{Auth?} -- Yes --> [Dashboard]
{Auth?} -- No --> [Login]
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 · 234 lines · 33 tokens per session scan A 876a1cb659b7
mermaid-diagrams is a skill published in the GitHub repository Desko77/cursor-1c-skills (57 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,729 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mermaid-diagrams, differing in 206 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.
1c-interface-edit
A tool for editing the command menu of a 1C subsystem, a functional area in the 1C business software platform. It can change which commands appear, their groups, and their order.
img-grid-analysis
An image-analysis command that places a numbered grid over a picture. The grid divides the image into measured rows and columns so layout proportions can be read more accurately.
composing-1c-queries
A guide for writing queries in the 1C:Enterprise query language. It covers how to select, filter, join, group, and summarize data from 1C catalogs, documents, and registers.
humanize-ai-text
A writing aid for rewriting text produced by language-model agents into a more natural human style. It keeps the original meaning, facts, numbers, and technical terms.
transcribe
A tool for turning video and audio recordings into written text, with optional speaker identification and video analysis.