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 adrian-baker/woolies-mcp --skill wooliesgit clone --depth 1 https://github.com/adrian-baker/woolies-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/adrian-baker/woolies-mcp/woolies)<a href="https://agentmods.dev/skills/adrian-baker/woolies-mcp/woolies"><img src="https://agentmods.dev/badge/skills/adrian-baker/woolies-mcp/woolies/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/adrian-baker/woolies-mcp/woolies"><img src="https://agentmods.dev/badge/skills/adrian-baker/woolies-mcp/woolies.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 | $0.00086 | $0.01126 |
| Opus 5.5 | $0.00034 | $0.00450 |
| Sonnet 5.5 | $0.00017 | $0.00225 |
| Haiku 4.5 | $0.00009 | $0.00113 |
Grade A, and why
woolies 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 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.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Woolies
Turn a shopping request into a filled Woolworths trolley. You choose products; the person reviews and orders on the website.
Before anything else
get_location. Prices and stock are per delivery location, and the session is shared, so it may be set to somewhere else. Report the location you are shopping from; change it only if asked, or if the person named a different one.- Read the person's standing grocery preferences if they keep them somewhere. They are the few rules that hold regardless of the dish. Ask once if you do not know where they are.
- Get the list — the document they named, or what they pasted.
- If the list came from a document that also holds a menu or dishes, read those: they supply purpose (below). Do not go hunting for a menu that was not offered.
Choosing products
Search per item, then pick. search_products_batch does several searches in one call, which is
worth using for a list of any length — the upstream throttle makes sequential searches slow.
Rules, in order of precedence:
- Standing preferences win. They are few and absolute.
- Purpose decides the rest. Cream fat, olive oil intensity, potato variety and cut of meat
follow the dish, not habit. When the choice turns on an attribute,
get_productreturnsingredients,claims(e.g. "Intensity: 3" on olive oil),nutritionandorigins. - When purpose is unknown, pick and say so. "Chose Vivaldi; if these are for roasting, Agria is better." Never make a silent judgement call on a purpose-sensitive item.
- Repeat staples come from history.
get_buy_it_againfor things like toilet paper or coffee. Use only the purchase-history section; the promotional section is Woolworths advertising, not anything this person has bought. It returns a general list rather than answering a query, so read it for the item you want rather than expecting a filtered result. - Compare on
unitPrice. Where a larger pack is better value than the person will use, size for the week and say what the cheaper-per-unit option was. - Read product names, not just search rank. Grades and forms matter ("tasty" is a maturity, not a brand; blocks, slices and grated all match the same search).
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 Changed 398e4bbb00a8
- 2mo ago First seen · 87 lines · 86 tokens per session scan A 47373cd4e2c9
woolies is a skill published in the GitHub repository adrian-baker/woolies-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,126 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.
woolies compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wooliesadrian-baker/woolies-mcp | Skill | 4 | 1mo ago | MIT | A | 86 | Claude Code, Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | today | MIT | A | 60 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 76 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | yesterday | MIT | A | 111 | Claude Code |