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 JohnWayneeee/ai-agent-skills --skill pencil-to-codegit clone --depth 1 https://github.com/JohnWayneeee/ai-agent-skillsWrote 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/johnwayneeee/ai-agent-skills/pencil-to-code)<a href="https://agentmods.dev/skills/johnwayneeee/ai-agent-skills/pencil-to-code"><img src="https://agentmods.dev/badge/skills/johnwayneeee/ai-agent-skills/pencil-to-code/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/johnwayneeee/ai-agent-skills/pencil-to-code"><img src="https://agentmods.dev/badge/skills/johnwayneeee/ai-agent-skills/pencil-to-code.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 | $0.00073 | $0.00726 |
| Opus 5.5 | $0.00029 | $0.00290 |
| Sonnet 5.5 | $0.00015 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
pencil-to-code 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pencil To Code
Use this skill to transfer a Pencil design into maintainable frontend code without losing layout, typography, background treatment, or responsive intent.
Workflow
-
Read the design contract first
- Use Pencil MCP to inspect all user-provided artboards and handoff/spec nodes.
- Read variables with
get_variables. - Capture screenshots of each target artboard before coding.
- If a handoff node exists, treat it as source-of-truth for responsive behavior.
-
Extract implementation facts
- Record artboard sizes, foreground stack width, stack x/y, section gaps, spacer heights, radii, stroke colors, blur radii, shadows, and image fill modes.
- Read repeated components deeply enough to capture exact text, font family, font size, font weight, line height, letter spacing, icon size, and touch target dimensions.
- Distinguish fixed foreground layout from decorative absolute layers.
-
Map design to code deliberately
- Use semantic, reusable components for repeated rows/cards/actions.
- Keep foreground layout in flex/grid.
- Keep background image, veil, mist, vignette, wires, particles, and similar decorative layers absolute/fixed and non-interactive.
- Preserve design tokens as CSS variables or framework theme tokens.
- Copy or reference real assets from the Pencil export rather than approximating logos/photos.
-
Handle responsive artboards literally
- Foreground dimensions must follow the handoff, not viewport convenience.
- If the design says a column is fixed, do not stretch cards/buttons on tablet/desktop.
- Only expand the outer scene when the handoff says so.
- Re-check artboard node IDs after the user says the design changed.
-
Verify visually and numerically
- Run the project checks required by the repo.
- Use browser screenshots at every artboard size.
- Use browser
getComputedStylefor text that looks wrong; verify actualfont-family,font-size,font-weight,line-height, andletter-spacing. - Compare rendered screenshots against Pencil screenshots before finalizing.
What ships with it
2 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.
- 1mo ago First seen · 55 lines · 73 tokens per session scan A 9a94188aac8b
pencil-to-code is a skill published in the GitHub repository JohnWayneeee/ai-agent-skills (1 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 726 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 2026-08-31.
Other skills, from other repositories
etsy-shop-branding
Shop branding — banner design, logo, brand story, cohesive listing photography, packaging.
wireframing
Create text-based wireframes at low, mid, and high fidelity with component inventories, interaction annotations, and responsive breakpoint specifications. Use when the user requests wireframing or provides relevant inputs for this workflow.
frontend-design
Design and build production-ready frontend interfaces with design systems, responsive layouts, accessible components, and dark mode support. Use when the user requests frontend design or provides relevant inputs for this workflow.
user-flow-mapping
Visualize and map user flows with Mermaid diagrams, decision points, error states, and conversion metrics to optimize user journeys. Use when the user requests user flow mapping or provides relevant inputs for this workflow.
chatbot-conversation-design
Design structured, engaging chatbot conversations with robust intent handling, slot filling, disambiguation, error recovery, and graceful fallback strategies. Use when the user requests chatbot conversation design or provides relevant inputs for this workflow.
logo-design
Design professional, scalable logos with complete brand identity deliverables including color palettes, typography, format variations, and usage guidelines. Use when the user requests logo design or provides relevant inputs for this workflow.