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 lukedj78/dev-flow --skill screenshot-to-pagegit clone --depth 1 https://github.com/lukedj78/dev-flowWrote 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/lukedj78/dev-flow/screenshot-to-page)<a href="https://agentmods.dev/skills/lukedj78/dev-flow/screenshot-to-page"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/screenshot-to-page/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/lukedj78/dev-flow/screenshot-to-page"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/screenshot-to-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00197 | $0.06309 |
| Opus 5.5 | $0.00079 | $0.02524 |
| Sonnet 5.5 | $0.00039 | $0.01262 |
| Haiku 4.5 | $0.00020 | $0.00631 |
Grade A, and why
screenshot-to-page 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
screenshot-to-page — screenshot → working route
This skill takes one screenshot and one route-name from the user, and produces a working page in the existing scaffolded app. The route renders close to the visual reference, uses only components and tokens already defined by the project's design system, and is reachable in pnpm dev.
What this skill targets
Pixel-perfect on what's reproducible: layout, typography, color, spacing, radii, component states. The skill iterates render → screenshot → pixel-diff → fix until the visual delta is below threshold (default <2% off-tokens).
Placeholder, with explicit flag, on what isn't: photography, illustration, custom illustrations, brand-licensed imagery. These are static raster contents that no skill can synthesize from a screenshot alone.
Componentized aggressively: the skill detects repeated visual patterns in the screenshot (3 cards with the same structure, 4 nav links, a list of testimonials, ...) and extracts each pattern into a reusable component before writing JSX. The page file ends up short and readable; the heavy lifting is in components/<PageName>/.
What this skill is NOT
- Not a Figma-to-code service. The input is a static raster, not a vector.
- Not a layout designer — if the screenshot is ambiguous (e.g., two interpretations of a section break), ask the user.
When this skill applies
- A
<project-root>/exists (phase >= scaffolded). .workflow/screenshots/contains at least one image.- A
.workflow/DESIGN.mdexists with valid tokens. - The user names a route to build (
/,/pricing,/dashboard, etc.) or points at a specific screenshot.
Contract
This skill follows the dev-flow contract — see references/contracts.md. Key facts:
- Reads
<root>/.workflow/screenshots/<filename>,<root>/.workflow/DESIGN.md,<root>/.workflow/meta.json#stack. - Writes the route into the codebase at the project root, at the canonical path for the framework:
- Next App Router:
<project-root>/app/<route>/page.tsx - Vite + React: registers a route in
<project-root>/src/router.tsx(or whatever the scaffold uses) plus a component file<project-root>/src/pages/<Route>.tsx. - Astro:
<project-root>/src/pages/<route>.astro.
- Next App Router:
- Sets
phase = "page_generated"(only if current phase is earlier in the enum).
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.
- 8d ago Changed · +3 lines 8da237cb099a
- 15d ago Changed · +38 lines 2c7e2278fd66
- 1mo ago Changed · +2 lines 0ed251c6e3d8
- 1mo ago First seen · 263 lines · 197 tokens per session scan A d117b2bae345
screenshot-to-page is a skill published in the GitHub repository lukedj78/dev-flow (6 stars, last pushed 5d ago), licensed MIT. It adds 197 tokens to every session and 6,309 once invoked, about $0.0008 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
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
design-craft
Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique. Use for new screens, landing pages, redesigns, typography/layout work, or UI that feels generic or AI-generated. For small fixes, preserve the existing design without starting a…
taiyi-diagram-pipeline
A pipeline that creates and updates architecture diagrams in three stages: a C4 model from the code, an engineering architecture diagram, and an exported PNG image. C4 is a way to describe software architecture at several levels of detail.