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 TheMattBerman/landing-page-factory --skill page-visualsgit clone --depth 1 https://github.com/TheMattBerman/landing-page-factoryWrote 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/themattberman/landing-page-factory/page-visuals)<a href="https://agentmods.dev/skills/themattberman/landing-page-factory/page-visuals"><img src="https://agentmods.dev/badge/skills/themattberman/landing-page-factory/page-visuals/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/themattberman/landing-page-factory/page-visuals"><img src="https://agentmods.dev/badge/skills/themattberman/landing-page-factory/page-visuals.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 | $0.00037 | $0.01653 |
| Opus 5 | $0.00018 | $0.00826 |
| Sonnet 5 | $0.00007 | $0.00331 |
| Haiku 4.5 | $0.00004 | $0.00165 |
Grade A, and why
page-visuals 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 11d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Page Visuals
The job is not "make pretty images." The job is to support conversion without visually lying about the thing being sold.
If the product, packaging, UI, or materials need precision, route accordingly.
Required inputs
workspace/pages/[page-name]/strategy.jsonworkspace/brand/profile.mdworkspace/brand/palette.jsonworkspace/pages/[page-name]/copy.md- any operator-provided product refs, packaging refs, screenshots, or image assets
Provider policy
Use Page Factory brand artifacts as the source of truth.
workspace/brand/extract.mdandworkspace/brand/profile.mddefine the canonical brand understanding- provider-side brand onboarding is support context for image generation, not a substitute for extraction or profiling
- preferred provider order: Bloom first pass, Nano Banana fallback, then manual/operator assets when fidelity is trust-critical
Provider selection is mandatory.
If Bloom is configured or expected for the run, you must check Bloom first. Do not silently substitute Cowork-native image generation, generic built-in image tools, or ad hoc image prompting when Bloom is the intended provider.
If Bloom is not configured, blocked, or cannot be reached:
- say that explicitly
- ask the operator whether to:
- provide/configure Bloom
- use Nano Banana fallback
- supply manual/operator assets
- do not silently continue with a weaker provider on a trust-critical run
If Nano Banana is the fallback path, confirm that the operator has provided the required adapter/command or API-backed workflow. Do not assume Nano Banana exists just because the name appears in docs.
Bloom-specific guidance
When Bloom is available:
- check whether the brand already exists in Bloom
- if not, onboard the brand from the source URL
- if Bloom brand context is weak or incomplete, fill it using the repo's extracted brand facts, profile, and palette
- upload product, packaging, or UI refs before generating exact-product shots
- use Bloom edits/resizes when the base composition is strong and the change request is narrow
What ships with it
3 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.
- 11d ago First seen · 238 lines · 37 tokens per session scan A fe6538fa87b4
page-visuals is a skill published in the GitHub repository TheMattBerman/landing-page-factory (40 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,653 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 2026-08-30.
Other skills, from other repositories
create-openbitfun-cinematic-wallpaper-skin
Apply the cinematic animated-wallpaper style recipe to a OpenBitFun Appearance skin. Use after loading the parent create-openbitfun-skin Skill when the user provides animated character artwork and wants a host-managed video background, source-derived glass materials, image-led cards, illustrated dialogs, reproducible…
pm-brand-motion
A guided process for defining a brand's motion style and making a logo animation demonstration.
qiaomu-mondo-poster-design
An AI-assisted design tool for creating posters, book covers, album covers, and similar images in the Mondo style, known for bold colors, simple compositions, and symbolic imagery.
lark-slides
A tool for creating and editing Feishu slide presentations, including their pages and content. Feishu is a workplace collaboration platform.
baoyu-infographic
A generator for infographics that combines one of 21 information layouts with one of 21 visual styles.
genie-studio
This is a design system extracted from the Genie Studio web app (codename: Creative Cortex), an AI canvas-based image creation tool by Genie Labs. Use these tokens, components, and conventions when designing for or extending the product.