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/zhpeng24/devkit/image-to-code-skillnpx skills add zhpeng24/devkit --skill image-to-code-skillgit clone --depth 1 https://github.com/zhpeng24/devkitWhat 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 | $0.00031 | $0.00579 |
| Opus 5 | $0.00015 | $0.00290 |
| Sonnet 5 | $0.00006 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
image-to-code-skill 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 yesterday.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image to Code
Treat the reference as a specification. A supplied screenshot, Figma frame, or approved image is authoritative; do not regenerate, restyle, or replace it merely because image generation is available.
If a request calls a reference approved or final but also asks to “capture the vibe,” modernize it, or skip comparison, surface the conflict. Keep the approved source authoritative unless the user explicitly changes that status; do not silently downgrade fidelity to meet a deadline.
Choose the source
| Reference state | Action |
|---|---|
| Supplied or approved | Analyze and implement it faithfully. |
| No authoritative reference; visual exploration requested or materially useful | Propose/generate the smallest useful reference set, then confirm it before treating it as implementation input. |
| Pure image delivery | Route to imagegen-frontend-web. |
Never invent business claims, data, testimonials, logos, or asset rights. Preserve existing brand assets and mark unknown content as placeholder content.
Analyze before coding
View each source at readable resolution. Record its viewport and inventory: section order; containers and grid; alignment and responsive behavior; typography; palette; spacing; radii; borders and shadows; imagery; controls; interactive, loading, empty, and error states. Reuse project assets/components when they match the source.
When a source lacks readable detail, request a clearer reference or create a fresh, task-scoped detail reference with the needed information. Do not crop the authoritative source and mistake the crop for new design authority.
Implement and compare
- Inspect the existing stack, routes, tokens, and dependencies. Implement in that stack; do not default to React, Next, Tailwind, or a replacement design system.
- Build geometry first, then type, color, spacing, imagery, controls, and states. Keep semantics, keyboard access, contrast, reduced motion, and responsive behavior intact.
- Render the target route at the source viewport and compare side-by-side or with an overlay. Fix measurable differences in layout, type scale/line breaks, spacing, color, borders, and assets. Check responsive variants deliberately rather than extrapolating from one viewport.
- Run relevant project build/lint/tests and report both command results and any fidelity gaps or unavailable assets.
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.
- yesterday First seen · 40 lines · 31 tokens per session scan A 03b275267c87
image-to-code-skill is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 579 once invoked, about $0.0002 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…