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 Gekkos-tech/agency-os --skill imagegen-webgit clone --depth 1 https://github.com/Gekkos-tech/agency-osWrote 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/gekkos-tech/agency-os/imagegen-web)<a href="https://agentmods.dev/skills/gekkos-tech/agency-os/imagegen-web"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/imagegen-web/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/gekkos-tech/agency-os/imagegen-web"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/imagegen-web.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 | $0.00138 | $0.01326 |
| Opus 5 | $0.00069 | $0.00663 |
| Sonnet 5 | $0.00028 | $0.00265 |
| Haiku 4.5 | $0.00014 | $0.00133 |
Grade A, and why
imagegen-web 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 12d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Design Reference Images
Generate image-model comps that a developer (or coding model) can rebuild section by section with high fidelity. The output of this skill is a SET of images — one per page section — that together read as one coherent website.
The one law: one section = one image
Never generate a full-page board. A single tall image containing hero + features + pricing + footer compresses every section into unreadable postage stamps and the model invents mush. Instead:
- List the page's sections first. A landing page with 8 sections produces 8 separate horizontal images.
- Each image shows exactly ONE section at full width, as if screenshotted from a real site — roughly 16:9 or 3:2, landscape.
- If a section is genuinely tall (long pricing table), it may get a 4:3 image, never portrait.
- If the user asks for "the design" of a whole page, translate that into the section list and confirm it before generating.
Workflow
1. Plan the page
Write the section list with one line of purpose each. Typical marketing page:
1. Hero — value prop + primary CTA
2. Social proof — logo strip / one metric
3. Feature A — core capability, visual-led
4. Feature B — secondary capability
5. How it works — 3-step process
6. Testimonial — one strong quote
7. Pricing — 2–3 tiers
8. Final CTA + footer
4–10 sections is normal. Fewer than 4: probably fine to design; more than 10: cut.
2. Define the style-token block (before any image)
One consistent palette and type feel across ALL images is what makes the set look like one website. Write this block ONCE and paste it verbatim into every prompt:
STYLE TOKENS: [Site name / vibe in 5 words].
Background: [hex]. Surface: [hex]. Text: [hex]. Accent: [hex] (used for CTAs and highlights only).
Type: [display feel, e.g. "large tight grotesque headlines"] + [body feel].
Corners: [sharp | 8px rounded | pill buttons]. Density: [airy | balanced | compact].
Lighting/texture: [flat | soft gradients on background only | grain | glass].
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.
- 12d ago First seen · 96 lines · 138 tokens per session scan A f2de81a8a5cb
imagegen-web is a skill published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 1,326 once invoked, about $0.0007 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
design-mobile-apps
Use when the user wants to design a mobile app or UI screens, when they mention their Sleek (sleek.design) projects, or when implementing Sleek designs in code (HTML, React Native, SwiftUI).
diagram-design
Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, treemap, bar, line, Gantt and scatter charts, high-level…
dengguang-zhaoming-bikeng-zhinan
A Chinese-language knowledge guide about home lighting, including ceiling lights, light strips, color temperature, color rendering, and room zoning.
appllama-app-design-skill
Build native-feeling, benchmark-quality mobile app screens (Expo / React Native). Use when designing or implementing any mobile UI — screens, flows, onboarding, paywalls, tab bars, sheets, settings, empty states — or when polishing motion, navigation, typography, dark mode, or perceived performance. Enforces Apple HIG…
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
landing-page-design
Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section…