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/walidboulanouar/Ay-Skillsnpx agentmods add skills/walidboulanouar/ay-skills/excalidraw-diagramWrote 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/walidboulanouar/ay-skills/excalidraw-diagram)<a href="https://agentmods.dev/skills/walidboulanouar/ay-skills/excalidraw-diagram"><img src="https://agentmods.dev/badge/skills/walidboulanouar/ay-skills/excalidraw-diagram/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/walidboulanouar/ay-skills/excalidraw-diagram"><img src="https://agentmods.dev/badge/skills/walidboulanouar/ay-skills/excalidraw-diagram.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 | $0.00087 | $0.06073 |
| Opus 5.5 | $0.00035 | $0.02429 |
| Sonnet 5.5 | $0.00017 | $0.01215 |
| Haiku 4.5 | $0.00009 | $0.00607 |
Grade B, and why
excalidraw-diagram scanned grade B with 1 finding 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 2mo 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- **Don't write a Python generator script.** The templating and coordinate math seem helpful but introduce a layer of indirection that makes debugging harder. Hand-crafted JSON with descriptive IDs is more maintainable. This is a copy
94% identical to excalidraw-diagram — 57 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 — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excalidraw Diagram Creator
Generate .excalidraw JSON files that argue visually, not just display information.
Setup: If the user asks you to set up this skill (renderer, dependencies, etc.), see README.md for instructions.
AY Automate Style Defaults (always apply unless told otherwise)
Visual style
roughness: 2 ← hand-drawn / sketchy (NOT clean/sharp) — boxes only
strokeWidth: 2 ← medium stroke weight
roundness: {"type":3} ← rounded corners on all rectangles
fontFamily: 1 ← Virgil (handwritten font) — NOT mono, NOT sans
Boxes / shapes: strokeStyle: "dotted" + roughness: 2
Arrows / lines: strokeStyle: "solid" + roughness: 1 — arrows are clean, only boxes are dotted
Text rules
- Titles are free text — never wrap the title in a box. Just a plain text element above the diagram.
- Write titles in lowercase — "ralph loop", not "RALPH LOOP". Natural handwritten feel.
- Use line breaks inside node labels — split label and sub-label with
\n - Keep labels short and human — "reads files" not "file ingestion module"
- Write like you're explaining to a non-technical person
- Free-floating annotations are better than boxing everything
Color mode
- Dark (
viewBackgroundColor: "#14141c") — internal docs, LinkedIn content, agent diagrams - Light (
viewBackgroundColor: "#f0edee") — client deliverables, onboarding, proposals - Ask or infer from context. Default = dark.
- Colors come from
references/color-palette.md.
Brand
Periwinkle #8182C1 is the accent. Never use generic blue #3b82f6 or any purple #7c3aed.
Output path: 008_Builds/excalidraw/output/{slug}.excalidraw
Render path: 008_Builds/excalidraw/output/{slug}.png
Render command:
cd .claude/skills/excalidraw-diagram/references && uv run python render_excalidraw.py ../../../008_Builds/excalidraw/output/{slug}.excalidraw
Common use cases:
- Agent architecture maps (Claude → n8n → Supabase → client)
- Client onboarding flows (what we build, in what order)
- AI pipeline explainers (for LinkedIn content)
- Internal system diagrams (for engineers on client projects)
- Ralph loop / agentic flow diagrams
- Competitor / comparison maps
- GTM funnel visualizations
What ships with it
8 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.
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.
- 2mo ago First seen · 606 lines · 87 tokens per session scan B f675e969268e
excalidraw-diagram is a skill published in the GitHub repository walidboulanouar/Ay-Skills (93 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 6,073 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). It is 94% identical to excalidraw-diagram, differing in 57 lines, and is treated as a copy.
excalidraw-diagram compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| excalidraw-diagramwalidboulanouar/Ay-Skills | Skill | 93 | 1mo ago | MIT | B | 87 | Claude Code, Codex |
| component-family-consistencydembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 38 | Claude Code |
| extract-designdembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 43 | Claude Code |
| modular-scale-typographydembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 34 | Claude Code |
| data-display-and-selectiondembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 37 | Claude Code |
| information-architecturedembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 33 | Claude Code |
| modal-and-overlay-patternsdembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 38 | Claude Code |