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/int2t05/engineering-skills/image-to-codenpx skills add int2t05/engineering-skills --skill image-to-codegit clone --depth 1 https://github.com/int2t05/engineering-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/int2t05/engineering-skills/image-to-code)<a href="https://agentmods.dev/skills/int2t05/engineering-skills/image-to-code"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/image-to-code.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 | $0.00000 | $0.01588 |
| Opus 5 | $0.00000 | $0.00794 |
| Sonnet 5 | $0.00000 | $0.00318 |
| Haiku 4.5 | $0.00000 | $0.00159 |
Grade A, and why
image-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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image to Code
For visually important web work, generate the design reference images yourself first, deeply analyze them, then implement frontend code that faithfully matches. The images are the primary visual source of truth; the code is the translation layer. Do not start with freeform coding when image generation is available.
When to use
- Hero sections, landing pages, marketing sites, product pages, portfolio sites — visually important web tasks
- Multi-section website concepts where image-first beats code-first
- Redesigns where visual quality matters heavily
- Requests described mainly in visual terms ("beautiful hero", "premium landing page", "creative website")
- Triggers on "image to code", "设计图转代码", "图片实现", "从设计图实现"
Not for: pure code implementation without image reference (use frontend-design); brand/web/mobile design reference images only, without code (use imagegen).
Tool note: use an available image-generation tool — do not bind to a specific product.
Steps
1. Plan sections and visual direction
If docs/design/references.md exists (produced by design-research), load it first — real
references inform the section count and visual-direction picks before images are generated.
Infer the section count from the request. Pick a coherent visual combination and commit to it
consistently — do not mash everything into chaos.
- Load ${CLAUDE_PLUGIN_ROOT}/skills/03-design/frontend-design/references/visual-direction.md for the combinatorial variation engine (9 axes: theme paradigm, background, typography, hero architecture, section system, signature components, motion-implied, narrative spine, second-read moment), hero-scale mapping, and the anti-slop ban list. The narrative-spine and second-read axes are optional for image-to-code.
- Default section packs if unspecified: 4-section (hero, features, social proof, CTA); 8-section (hero, trust bar, features, product showcase, benefits, testimonials, pricing, CTA); 12-section (adds workflow, metrics, FAQ, footer).
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.
- 4d ago First seen · 101 lines · 0 tokens per session scan A e749808ff160
image-to-code is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,588 tokens. 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
sheet-music-publisher
Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.
import-art
Places album art files in the correct audio and content directory locations. Use when the user has generated or downloaded album artwork that needs to be saved.
capcut-edit
Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts. Use when the user mentions capcut, jianying, subtitles, video editing, draftcontent.json, draftinfo.json, or cutting videos.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
nano-banana
This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation…
about
Provides information about the bitwize-music plugin, its version, and its creator. Use when the user asks about the plugin, its purpose, version, or capabilities.