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 pandysp/claude-plugins --skill excalidrawgit clone --depth 1 https://github.com/pandysp/claude-pluginsWrote 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/pandysp/claude-plugins/excalidraw)<a href="https://agentmods.dev/skills/pandysp/claude-plugins/excalidraw"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/excalidraw/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/pandysp/claude-plugins/excalidraw"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/excalidraw.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 | $0.00067 | $0.01142 |
| Opus 5.5 | $0.00027 | $0.00457 |
| Sonnet 5.5 | $0.00013 | $0.00228 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
excalidraw 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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excalidraw
You write a short JavaScript file that uses the Excalidraw plugin's drawing commands (ea). The helper draw.mjs (in this skill's folder) runs it inside Obsidian, opens the drawing and takes a screenshot. You look at the screenshot and fix what is wrong.
Before you start
- Obsidian must be running with the vault open and the Excalidraw plugin installed. The Obsidian command line tool (
obsidian) must be turned on: Settings → General → Command line interface. - Quick check:
obsidian eval code="typeof ExcalidrawAutomate"must print=> object. - If the user did not say what to draw, ask. If they did not say where to save it, leave out
foldername: the plugin then uses the user's own drawing folder.
Steps
- Write the drawing file (for example
drawing.js) in a scratch folder, not in the vault. - Run
node <this skill's folder>/draw.mjs drawing.js. It uses the vault that is open in front and prints its name, the path of the new drawing and the path of the screenshot. If that is the wrong vault, ask the user to bring the right one to the front. - Look at the screenshot. Check for overlaps you did not intend, text sitting on lines, anything cut off, and text that is hard to read.
- To fix something, edit
drawing.js. Before running again, delete the drawing your last run made (only that one, never a drawing you did not create):obsidian vault="<vault>" delete path="<drawing path>". - Tell the user where the drawing is and show the screenshot path.
The drawing file
Write plain lines of JavaScript, with no function around them. ea is ready to use, and await works. The last line creates the drawing and returns its path.
ea.style.fontFamily = 5; // hand-drawn font
ea.style.fillStyle = "solid";
ea.style.roundness = { type: 3 }; // rounded corners
ea.style.backgroundColor = "#a5d8ff";
const a = ea.addText(0, 0, "Idea", { box: "box", textAlign: "center", textVerticalAlign: "middle" });
ea.style.backgroundColor = "#b2f2bb";
const b = ea.addText(250, 0, "Done", { box: "box", textAlign: "center", textVerticalAlign: "middle" });
ea.style.backgroundColor = "transparent";
ea.connectObjects(a, "right", b, "left", { endArrowHead: "arrow" });
return ea.create({ filename: "my-drawing", silent: true }); // add foldername: "..." to pick a folder
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.
- 1mo ago First seen · 64 lines · 67 tokens per session scan A eccb7a7fca64
excalidraw is a skill published in the GitHub repository pandysp/claude-plugins (6 stars, last pushed 7d ago), licensed MIT. It adds 67 tokens to every session and 1,142 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 2026-09-27.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.