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 agentmods add skills/dan-rozhkov/pen-editor-plugin/pen-editor-dev-modenpx skills add dan-rozhkov/pen-editor-plugin --skill pen-editor-dev-modegit 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-dev-mode)<a href="https://agentmods.dev/skills/dan-rozhkov/pen-editor-plugin/pen-editor-dev-mode"><img src="https://agentmods.dev/badge/skills/dan-rozhkov/pen-editor-plugin/pen-editor-dev-mode.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.00916 |
| Opus 5 | $0.00034 | $0.00458 |
| Sonnet 5 | $0.00014 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
pen-editor-dev-mode 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 5d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pen Editor dev mode
You are translating a live Pen Editor design into code. This is a read-only task against the design: gather everything you need, then write code in the target codebase. Do not call batch_design or set_variables — reading a design in order to implement it is not a license to edit it. If the user actually wants the design itself changed, that's the pen-editor-design skill, not this one.
All Pen Editor tools below are bridged and require a connected browser tab (30s timeout). If a call errors with "No Pen Editor tab is connected", see pen-editor-setup.
Workflow
get_editor_state— active file, selection, top-level nodes, available components. Establishes what you're implementing and its scope.batch_get— pull the actual subtree you're implementing (bynodeIdsor a searchpatternsmatch), with enoughreadDepth/searchDepthto see every descendant that matters. This is the node model: types,layout/fills/strokes/effects/cornerRadius, text content, etc.snapshot_layout— the fidelity-critical step. This returns computed rectangles (positions/sizes) after Pen Editor's layout engine has run — not the raw authored properties. Use these numbers, not eyeballed guesses, for spacing, sizing, and any absolutely-positioned children.problemsOnly: truesurfaces clipping/overflow you should account for in the implementation.get_variables— read the design's tokens and map them onto the codebase's own design tokens (CSS variables, Tailwind theme values, etc.) rather than hardcoding hex values pulled off a node. If a fill/stroke references$--some-token, your code should reference the codebase's equivalent token, not a literal color.get_screenshot— visual reference while translating, and again afterward to compare your built component against the design.
Translating the node model to code
- An auto-layout frame (
layout: "vertical"or"horizontal") → a flex container in that direction; itsgap/padding→gap/paddingin CSS. width/height: "fill_container"→ flex-grow / stretch sizing;"fit_content"→ hug/auto sizing (e.g.width: fit-contentor an unset flex-basis).constraints: {horizontal, vertical}on a node without auto-layout → non-flex positioning (absolute/pinned edges) —min/max/center/stretch/scalemap to how that node should reposition/resize as its container resizes.cornerRadius— either a single number (uniform) or a 4-entry array[topLeft, topRight, bottomRight, bottomLeft]— maps directly toborder-radius(shorthand or per-corner).- The
fills/strokes/effectsarrays are paint/effect stacks, bottom-to-top (last entry renders on top): solid → background-color/border-color, gradient → CSS gradient, image → background-image/<img>, shadow (outer/inner) →box-shadow, blur →filter: blur(), background-blur →backdrop-filter: blur(). Reproduce stack order and blend modes if the design uses more than one layer.
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.
- 5d ago First seen · 33 lines · 68 tokens per session scan A 80457f54e4a2
pen-editor-dev-mode is a skill published in the GitHub repository dan-rozhkov/pen-editor-plugin (0 stars, last pushed 28d ago), licensed MIT. It adds 68 tokens to every session and 916 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…