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 abracadabra50/open-supermarkets --skill apigit clone --depth 1 https://github.com/abracadabra50/open-supermarketsWrote 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/abracadabra50/open-supermarkets/api)<a href="https://agentmods.dev/skills/abracadabra50/open-supermarkets/api"><img src="https://agentmods.dev/badge/skills/abracadabra50/open-supermarkets/api/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/abracadabra50/open-supermarkets/api"><img src="https://agentmods.dev/badge/skills/abracadabra50/open-supermarkets/api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 89 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 90 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00606 |
| Opus 5.5 | $0.00013 | $0.00242 |
| Sonnet 5.5 | $0.00006 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
grocery-api 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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grocery API Skill
Use this skill when the user asks about Sainsbury's groceries, favourites, searching products, adding/updating/removing basket items, or viewing the basket.
The local API must already be running on port 7876:
GROC_API_PORT=7876 npm run api
Commands
Run from the repo root:
node skills/api/wrapper.js fav-search "milk"
node skills/api/wrapper.js search "milk"
node skills/api/wrapper.js favourites
node skills/api/wrapper.js basket
node skills/api/wrapper.js add <product-id> [qty]
node skills/api/wrapper.js remove <item-id>
node skills/api/wrapper.js update <item-id> <qty>
All commands return JSON from the local API.
Add-to-basket workflow
When the user asks to add an item to the basket:
-
First search favourites:
node skills/api/wrapper.js fav-search "USER ITEM" -
If there is a clear favourite result that matches the user's intent, add it directly:
node skills/api/wrapper.js add <product-id> [qty] -
If there are multiple plausible favourite results, ask the user which one to add. Include names, prices, and product IDs.
-
If there are no good favourite matches, or if the user explicitly asks to look outside favourites, use regular search:
node skills/api/wrapper.js search "USER ITEM" -
For regular search results, always confirm with the user before adding anything to the basket.
-
After adding, show or summarize the basket:
node skills/api/wrapper.js basket
Remove/update workflow
When the user asks to remove or update an item:
-
First inspect the basket to get basket item IDs:
node skills/api/wrapper.js basket -
Use the basket
item_id, not the product ID:node skills/api/wrapper.js remove <item-id> node skills/api/wrapper.js update <item-id> <qty> -
If the item to change is ambiguous, ask the user which basket item they mean.
-
After removing or updating, show or summarize the basket.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 93 lines · 32 tokens per session scan A 4bf97079d11f
grocery-api is a skill published in the GitHub repository abracadabra50/open-supermarkets (126 stars, last pushed 25d ago), licensed MIT. It adds 32 tokens to every session and 606 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
d1-cli
Shop Tiendas D1 (Colombia, d1.com.co) from the command line — search the catalogue, resolve your nearest physical store, price a basket against that store's real stock, and quote delivery. D1 runs VTEX IO (account d1tiendas), so this drives its public storefront API with no admin key at all — catalogue and cart work…
ckjia-shopping
A shopping search and price-comparison tool for Taobao, JD.com, Tmall, and Pinduoduo, with image-based product recognition. It requires the ckjia-shopping service and its access key to be enabled.
moonpay-commerce
Browse Shopify stores, search products, manage a cart, and checkout with crypto via Solana Pay. No login required.
google-ads-ecommerce
Build and optimize Google Ads campaigns for ecommerce with Performance Max, Shopping feeds, conversion tracking, and Smart Bidding strategies for ROAS.
skills
Skill "skills" from TheBestCo/bestprice-mcp, covering bestprice, route by shopper intent, preserve evidence and price semantics, optional price-drop events and boundaries.
filtmall-shopping
A Chinese e-commerce shopping tool for finding and buying cost-effective products on Filtmall, also called Filtalgo.