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-setup)<a href="https://agentmods.dev/commands/lorena-bordonaba-pau/product-studio/product-setup"><img src="https://agentmods.dev/badge/commands/lorena-bordonaba-pau/product-studio/product-setup/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-setup"><img src="https://agentmods.dev/badge/commands/lorena-bordonaba-pau/product-studio/product-setup.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 | $0.00032 | $0.00580 |
| Opus 5.5 | $0.00013 | $0.00232 |
| Sonnet 5.5 | $0.00006 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
product-setup scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s -o /dev/null -w "%{http_code}" -H "Authorization: Key <KEY>" https://fal.ai/api/models` — How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/product-setup — Product Studio initial setup
Guide the user through Product Studio's initial setup. It's a short, friendly process: each team member runs it once. Always reply in the user's language.
Steps
-
Greet briefly and explain you're going to configure their image/video generation provider.
-
Detect Higgsfield: check whether the Higgsfield MCP tools (
generate_image,generate_video) are available in the session. Mention it when asking ("I can see you have Higgsfield connected" / "I don't see Higgsfield connected in this session"). -
Ask for the provider with AskUserQuestion:
- Higgsfield (MCP) — recommended if already connected; no API key needed.
- Fal.ai — needs an API key (created free at https://fal.ai/dashboard/keys); pay per use.
- Another tool with an API — for anyone already using a different generation platform.
-
Depending on the answer:
- Higgsfield: if not connected, explain how to connect it (Higgsfield MCP connector in Claude's connector settings) and wait until they do.
- Fal.ai: ask for the API key. Validate it with a cheap test call:
curl -s -o /dev/null -w "%{http_code}" -H "Authorization: Key <KEY>" https://fal.ai/api/models— a 401 means the key is invalid; ask again. Don't print the key on screen and don't write it into any project file. - Another tool: ask which tool it is, its endpoint, auth type and how it receives a reference image. Save those notes in the config.
-
Save the configuration to
~/.claude/product-studio/config.json(create the folder if needed):
{
"provider": "higgsfield | fal | custom",
"fal_api_key": "...only if applicable...",
"custom": { "description": "...", "notes": "..." },
"configured": "2026-07-09"
}
- Create the learnings file
~/.claude/product-studio/learnings.mdif it doesn't exist:
# Product Studio learnings
Corrections that worked, to be applied automatically in future generations.
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.
- 2mo ago First seen · 53 lines · 32 tokens per session scan A a70b4b18a51c
product-setup is a command published in the GitHub repository lorena-bordonaba-pau/product-studio (6 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 580 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
product-setup compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-setuplorena-bordonaba-pau/product-studio | Command | 6 | 4mo ago | MIT | A | 32 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | today | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| convergegithub/spec-kit | Command | 148k | today | MIT | A | 35 | Claude Code |
| speckit.bug.testgithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | today | MIT | A | 26 | Claude Code |