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 dan-rozhkov/pen-editor-plugin --skill sideform-designgit clone --depth 1 https://github.com/dan-rozhkov/pen-editor-pluginWrote 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/dan-rozhkov/pen-editor-plugin/sideform-design)<a href="https://agentmods.dev/skills/dan-rozhkov/pen-editor-plugin/sideform-design"><img src="https://agentmods.dev/badge/skills/dan-rozhkov/pen-editor-plugin/sideform-design/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/dan-rozhkov/pen-editor-plugin/sideform-design"><img src="https://agentmods.dev/badge/skills/dan-rozhkov/pen-editor-plugin/sideform-design.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 | $0.00063 | $0.01535 |
| Opus 5.5 | $0.00025 | $0.00614 |
| Sonnet 5.5 | $0.00013 | $0.00307 |
| Haiku 4.5 | $0.00006 | $0.00153 |
Grade A, and why
sideform-design 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sideform design
You are driving a live Sideform document through the sideform MCP server. Design tools run against the user's editor. Start with open_canvas when your client supports MCP Apps: it shows the live canvas in the chat and connects the design tools to it. In clients without MCP Apps, the user must have https://app.sideform.pro/app open and signed in in a browser tab. If a call errors because no editor is open, stop and use the sideform-connect skill instead of retrying blindly. Calls time out after 30s if the editor is unresponsive.
Decision procedure
open_canvasfirst in apps-capable clients (once per conversation).- New screen, page, app or deck:
load_skill("prototype")(orload_skill("slides")for a presentation) and follow it. It holds the full rules for fonts, icons, photos, sizing and taste. Do not rebuild those rules from memory. Load the skill before the firstbatch_designcall. get_editor_state— active file, selection, top-level nodes, variables.find_empty_space_on_canvasfor the first screen's position, then place each next screen atx = previous x + previous width + ~120.batch_design— one screen per call. Then verify (see bottom).
New screens are ONE top-level embed
The server rejects top-level native creates (frame, rect, text, ...) on /mcp. Every NEW screen or page is exactly one top-level embed node whose htmlContent is a complete, self-contained HTML document:
- Sizes: mobile 390×844, tablet 768×1024, desktop 1440×1024 (slides: see the
slidesskill). - Fonts through
@importin<style>. Icons: Phosphor through@importfrom unpkg. Photos: picsum.photos URLs. No JavaScript. - Fit to canvas: all content must fit the declared width and height. The embed does not scroll.
- One screen per
batch_designcall. Several screens: one call each, in order.
Example (the HTML is shortened here; write the full markup as one string):
screen=I(document, {type:"embed", name:"Login", x:0, y:0, width:390, height:844, htmlContent:"<!doctype html><html>…</html>"})
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.
- 8d ago First seen · 66 lines · 63 tokens per session scan A 4d7a9c95d9b9
sideform-design is a skill published in the GitHub repository dan-rozhkov/pen-editor-plugin (0 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 1,535 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 2026-10-06.
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.
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.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.