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.
git clone --depth 1 https://github.com/lorena-bordonaba-pau/product-studioWrote 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/commands/lorena-bordonaba-pau/product-studio/product-image)<a href="https://agentmods.dev/commands/lorena-bordonaba-pau/product-studio/product-image"><img src="https://agentmods.dev/badge/commands/lorena-bordonaba-pau/product-studio/product-image/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/commands/lorena-bordonaba-pau/product-studio/product-image"><img src="https://agentmods.dev/badge/commands/lorena-bordonaba-pau/product-studio/product-image.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 | $0.00035 | $0.00527 |
| Opus 5 | $0.00017 | $0.00264 |
| Sonnet 5 | $0.00007 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
product-image 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 9d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/product-image — Professional product photography
Generates a set of professional product photos from the user's real photos. Always reply in the user's language.
Source provided by the user: $ARGUMENTS (If empty, ask whether they have a photo folder or their store's URL.)
Instructions
Follow the full flow defined in the product-photography skill (the product-studio plugin's
SKILL.md), section "Workflow: images". In short, skipping none:
- Check the user's config (
~/.claude/product-studio/config.json); if missing, walk them through /product-setup first. - Get the source images (local folder, or URL extraction + quick brand analysis — see
references/store-analysis.md) and confirm the detected products. - Build the strict inventory of each product by reading its photos — only what is clearly visible.
- Ask in ONE AskUserQuestion: style (minimalist / elegant / UGC — see
references/styles.md), quantity (3 or 5) and destination/format (ecommerce, feed, stories, web — seereferences/shot-plans.md). - Load the company's session template (
sessions/<company>.md) or draft one brand-matched to the client and confirm it with the user before generating — all photos for one brand share per-shot settings, light, palette and format. - Check the category-adaptive shot plan (
references/shot-plans.md) and the local learnings (~/.claude/product-studio/learnings.md). - Generate image-to-image with the configured provider (
references/providers.md), always using the original photo as reference (the one whose angle best matches the shot), with realistic photographic prompts (references/styles.md). - Run the consistency QA on every image against the inventory, the session template AND the AI-artifact checklist; fix mismatches (max 3 attempts) and record the learnings.
- Deliver to
output/<product>/with a final summary of what was generated and verified.
Remember the non-negotiable principle: total product fidelity. Never invent or elaborate on what can't be seen; never silently deliver an image that isn't identical to the real product.
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.
- 9d ago First seen · 31 lines · 35 tokens per session scan A 62a3eb14bbc8
product-image is a command published in the GitHub repository lorena-bordonaba-pau/product-studio (6 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 527 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 2026-08-31.
Other commands, from other repositories
pickle-clips
Batch reference→video clips for a store's gen5 SKUs (Veo free + Kling paid), spend-gated.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.