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 | $0.01047 |
| Opus 5 | $0.00032 | $0.00524 |
| Sonnet 5 | $0.00013 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00105 |
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 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 — 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 can compose 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.
This is an MCP-path capability
Photo embedding runs through the MCP server (https://api.canvora.ai/mcp)
or the Canvora web app. The canvora CLI cannot send photos today — if the
user is CLI-only, say so and point them at the MCP connector or the dashboard.
Don't fake it with --url.
The flow, in MCP tools:
upload_photo({ data, filename })→ returns a CDN URL. Repeat per photo, maximum 5.chat({ message })— describe the visual, mentioning that the photos are the subject.confirm_generation({ conversation_id, formats, embedding_photos: [urls], brand_id, ... })— the photo URLs go here.get_generation({ generation_id })to poll and collect outputs.
Step 4 is a poll loop by design, so the CLI's shell-timeout consideration
doesn't apply here — but the same rule does: a generation that hasn't come back
yet is still running. Never fire a second confirm_generation for the same
job; that starts a second, separate generation. State the cost in the same message as
step 3 — 10 credits per single visual, 15 per carousel slide — announcing it
rather than asking permission. 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.
- 12d 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 (0 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,047 once invoked, about $0.0003 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
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.
dxf
Generate, regenerate, and validate 2D DXF drawings from Python build123d sources. Use for DXF files, .py drawing scripts, @dxf models, 2D profiles, outlines, templates, gaskets, panels, flat patterns, laser/plasma/waterjet cut layouts, and 2D drawing exports of CAD geometry.
visual-artifact-design
A general workflow for creating, editing, diagnosing, or checking things people will see, read, or use. It defines the intended medium, audience, required outcome, evidence, and final consumer before work begins.