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 canvora/canvora-mcp --skill product-photo-visualsgit clone --depth 1 https://github.com/canvora/canvora-mcpWrote 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/canvora/canvora-mcp/product-photo-visuals)<a href="https://agentmods.dev/skills/canvora/canvora-mcp/product-photo-visuals"><img src="https://agentmods.dev/badge/skills/canvora/canvora-mcp/product-photo-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/canvora/canvora-mcp/product-photo-visuals"><img src="https://agentmods.dev/badge/skills/canvora/canvora-mcp/product-photo-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 | $0.00065 | $0.01071 |
| Opus 5.5 | $0.00026 | $0.00428 |
| Sonnet 5.5 | $0.00013 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
product-photo-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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visuals built around the user's own photos
The difference between a generic AI visual and a usable one is usually whether the actual product is in it. Canvora composes the user's real photos into a generated design: the layout, typography and brand styling are generated around the photo, not pasted on top of it.
The generate loop and credits: see the canvora skill.
Getting the photos to Canvora (up to 5)
Pick the first route that fits:
- The photo is already online (their website, a product page, a CDN): put
its public
https://URL straight intoembedding_photosonconfirm_generation. Nothing to upload. - The photo is a file you can read (Claude Code, a local folder): shrink it
first (about 1600px on the long edge, JPEG), then send it to
upload_photoas adata:image/jpeg;base64,...URL. It returns a CDN URL forembedding_photos. JPEG, PNG, WebP and HEIC are accepted, up to 8 MB. - The photo only exists as an attachment in this chat and you can't read its file: don't describe it, redraw it or generate a look-alike. Tell the user to upload it at https://canvora.ai/create, where the same request takes their photo directly.
Then the normal loop: chat (describe the visual and say the photos are the
subject) → show the plan → confirm_generation with embedding_photos →
poll get_generation. Never fire a second confirm_generation for the same
job; poll instead.
State the cost in the same message as the run: 10 credits per single visual, 15 per carousel slide. If you chose the slide count rather than the user, confirm that number first.
Intake
- How many photos, and what's in each? Tell the pipeline what it's looking at ("the blue jar, front label visible", "our head chef in the kitchen"). A photo with no description gets used generically.
- Which photo is the hero? With multiple photos and multiple slides, say which is the cover.
- Format and brand: as normal (
instagram_post,ad_square, a carousel…) plus the brand kit. - Must the photo be untouched? Say so explicitly in the brief. Otherwise the model may crop, relight or restyle it to fit the composition.
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.
- 3d ago Changed 1d4f9584ce07
- 2mo ago First seen · 95 lines · 65 tokens per session scan A 206321b0b959
product-photo-visuals is a skill published in the GitHub repository canvora/canvora-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 1,071 once invoked, about $0.0003 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
anatomy
Explain an idea as an interactive isometric machine figure.
canva
Create and edit Canva designs, generate images, remove backgrounds, recover editable layers, and work with Canva libraries. Use for branded presentations and slide decks, campaign artwork, flyers and banners, applying saved brand kits and templates, and resizing designs for social posts and stories through Canva's…
hi-fi-design
The design process for high-fidelity, polished work — the system prompt tells Claude to invoke it before starting any design.
options
Present multiple design options as a vertical stack of anchored turns.
wireframe
Explore many ideas with wireframes and storyboards.
archify
Validated interactive HTML diagrams, upstream-maintained.