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 pen-editor-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/pen-editor-design)<a href="https://agentmods.dev/skills/dan-rozhkov/pen-editor-plugin/pen-editor-design"><img src="https://agentmods.dev/badge/skills/dan-rozhkov/pen-editor-plugin/pen-editor-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/pen-editor-design"><img src="https://agentmods.dev/badge/skills/dan-rozhkov/pen-editor-plugin/pen-editor-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 | $0.01138 |
| Opus 5 | $0.00032 | $0.00569 |
| Sonnet 5 | $0.00013 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
pen-editor-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pen Editor design
You are an external MCP client driving a live Pen Editor document. All of these tools are bridged: they require a connected browser tab and time out after 30s if the tab is unresponsive. If a call errors with "No Pen Editor tab is connected", stop and see the pen-editor-setup skill instead of retrying blindly.
Decision procedure
get_editor_statefirst, always. This is Figma's metadata-first pattern — it gives you the active file, selection, top-level nodes, and available components before you read or write anything else. Passinclude_schema: trueonly if you need the raw node-format schema.get_variablesbefore using any$--vartoken. Variable references must use the exact names this returns, including the leading--and dashes (e.g."$--ck-blue-500"). Never guess a token name.batch_getto inspect the structure you're about to touch — search bytype/namepattern or read specificnodeIds, withreadDepth/searchDepthcontrol. Do this before mutating existing nodes, not after.get_guidelines(topic: "design-system")before any non-trivial layout work (new frames, auto-layout, component reuse). It has the sizing/auto-layout rules and component/variant conventions — don't restate them from memory, call it.get_style_guide_tagsthenget_style_guideare available if you need visual-direction inspiration/tokens for a from-scratch design.batch_designto make the actual changes.- Verify (see bottom).
batch_design DSL — rules you will otherwise get wrong
batch_design takes one operations string: a mini-script of I/C/U/R/M/D/G statements, one per line.
I(parent, nodeData)inserts a new node — this is the only way to add a child to an existing node.U()can update properties but cannot add, remove, or reorder children.- Bindings (
name=I(...)orname=R(...)) let you reference a just-created/replaced node later in the same call (e.g.card=I(...)thenU(card+"/title", {...})). OnlyIandRcan bind —C/U/M/D/Gnever produce a binding. Bindings do not survive across separatebatch_designcalls, and anid/namefield you put insidenodeDatais cosmetic only — never usable as a binding reference. - Use
+to build child paths off a binding or a real id:U(card+"/title", {content: "Hello"}). - No
imagenode type. To apply an image, useG(nodeId, "ai"|"stock", prompt)on a frame/rectangle to generate or find an image and apply it as a fill. - There is a cap on operations per call. If you send more than the cap, the call still succeeds but only the first N run — the result reports
truncated: truewith the skipped operations. Ontruncated: true, your nextbatch_designcall must contain ONLY the skipped operations (never repeat ones that already ran), and you must replace any binding references from the truncated call with the real node ids from that result'sbindingsfield — bindings don't carry over. - Text nodes have no color by default — always set
fill(or afillsstack) explicitly. width/height: "fill_container"is only valid on a child whose parent has a flexboxlayout(vertical/horizontal auto-layout) — never on a child of a plain frame.$--varreferences inside afill/fills/stroke/strokescolor must matchget_variablesoutput exactly.
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 · 42 lines · 63 tokens per session scan A bf6323119d8a
pen-editor-design is a skill published in the GitHub repository dan-rozhkov/pen-editor-plugin (0 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,138 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
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 $ralph 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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.