Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DKeken/codex-skills-alternativenpx agentmods add skills/dkeken/codex-skills-alternative/creative-sceneWrote 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/dkeken/codex-skills-alternative/creative-scene)<a href="https://agentmods.dev/skills/dkeken/codex-skills-alternative/creative-scene"><img src="https://agentmods.dev/badge/skills/dkeken/codex-skills-alternative/creative-scene.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 5.1 | $0.00088 | $0.00921 |
| Opus 5 | $0.00044 | $0.00461 |
| Sonnet 5 | $0.00018 | $0.00184 |
| Haiku 4.5 | $0.00009 | $0.00092 |
Grade A, and why
creative-scene 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative — Scene Explorer
Show the product living in the real world — believable usage moments, not floating studio renders. The job is to make a viewer picture themselves using it. Realism and emotional plausibility beat technical perfection.
When to use
- Lifestyle hero images, social content, editorial, "in-context" ecommerce shots.
- Selling the experience or outcome, not just the object.
- You need people, environment, or a moment of use around the product.
When NOT to use
- Clean catalog/PDP angles on a plain background →
creative-shot. - Pushing a discount/bundle →
creative-offer. - No look locked and brand consistency matters →
creative-explorefirst.
Inputs (ask only what's missing)
- Product + how it's actually used (ergonomics matter for believability).
- Target user who appears or is implied in the scene.
- Locked visual direction if available.
- Aspect/medium: web hero (wide), social (square/vertical), gallery.
Workflow
- Define 3-5 usage moments: who + where + when + doing-what. Concrete beats generic ("barista, morning cafe, steaming milk" not "person using product").
- Structure each scene prompt:
backdrop → subject + product → light/lens → constraints. Favor photoreal-natural styling: candid, real texture, natural light, believable depth of field. - Generate with your image tool. Save to
./creative/scene/<moment>.png. - Verify believability + hero: is the product clearly the focus? Are hands/ergonomics plausible? Regenerate weak ones (bad hands, product too small, staged-feeling).
- Present moments; recommend the strongest for the medium.
Worked example
Product: insulated water bottle. Audience: trail runners.
## Moment "Dawn Trail"
who: runner, late 20s, mid-stride where: forest trail, first light
when: cool blue-hour → warming doing: pausing to drink
prompt: "forest trail at dawn -> runner pausing, bottle to lips, breath visible
-> 50mm, shallow DOF, soft directional light -> candid, real sweat/texture,
bottle clearly visible and in focus"
[ref: ./creative/scene/dawn-trail.png]
## Moment "Desk Companion"
who: implied (hand only) where: tidy work desk when: midday
doing: reaching for the bottle beside a laptop
prompt: "minimal wood desk, daylight -> hand reaching for bottle next to laptop
-> 35mm, natural light -> candid, real texture, bottle hero"
[ref: ./creative/scene/desk.png]
Recommendation: "Dawn Trail" for the hero (aspirational, on-audience); "Desk" for broader appeal.
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 First seen · 70 lines · 88 tokens per session scan A bda188a4b222
creative-scene is a skill published in the GitHub repository DKeken/codex-skills-alternative (15 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 921 once invoked, about $0.0004 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
beat-sync-reel
Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.
product-reel-generator
Generates Instagram-ready product reels from any e-commerce product page URL. Scrapes product images, classifies by type, generates AI-animated clips via Higgsfield API, creates text overlays with style presets, and composes a 15-20 second reel with music. Supports model-based and product-only reels.
product-photoshoot
Create faithful studio, lifestyle, and on-model product photography through the GooseWorks Product Photos workflow, then approve selected results for reuse in future creative work.
analyzing-products
Normalizes a product into generation-ready facts — from an e-commerce URL (a clean description plus curated product images) or from a photo alone (category, how it's used, its moving/opening parts, and key visual details). Use when a product URL or photo needs turning into inputs for image/video generation, or when…
extract-product-data-and-generate-listing-image
Extract product details from a supplier data sheet, then generate a branded e-commerce listing image with the product name, price, and key specs.
generate-product-promo-card
Generate a product promotional card with a product photo, sale badge, and pricing text.