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 lobu-ai/lobu --skill deliveroo-ordergit clone --depth 1 https://github.com/lobu-ai/lobuWrote 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/lobu-ai/lobu/deliveroo-order)<a href="https://agentmods.dev/skills/lobu-ai/lobu/deliveroo-order"><img src="https://agentmods.dev/badge/skills/lobu-ai/lobu/deliveroo-order/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/lobu-ai/lobu/deliveroo-order"><img src="https://agentmods.dev/badge/skills/lobu-ai/lobu/deliveroo-order.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.00758 |
| Opus 5 | $0.00037 | $0.00379 |
| Sonnet 5 | $0.00015 | $0.00152 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
deliveroo-order 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliveroo lunch order
Deliveroo menus are read on demand by the deliveroo connector, which
drives the office's signed-in Chrome via the paired Owletto extension (no
Playwright, no cookies — see deliveroo.connector.ts). The connector exposes
two on-demand actions, not a feed:
search_restaurants({ query })— restaurants near the office matching the query, each as{ name, url }.read_menu({ restaurant_url })— that restaurant's live menu items ({ name, price, price_minor, description, kcal }).
These actions need the Automation's system context, so the agent does not call
them in-turn — the lobu-team-lunch-finalize reaction does (see
lunch-deliveroo.reaction.ts). After the agent's turn picks a restaurant, the
reaction searches for it, reads the live menu, and posts the menu + Deliveroo
order link back into the channel for a human to place.
This skill is assemble + hand-off only. It does not drive a basket, place an order, or touch payment — a human does the checkout on Deliveroo.
How the agent uses it
- Pick the restaurant for today (from thread suggestions, or a usual spot
in
USER.md), and put its name in the run's extraction (restaurant). The reaction will fetch that restaurant's live menu automatically. - Collect orders in the thread, then write the per-person list into the
lunch-runentity (who ordered what, with notes), and post a clean summary: each person → item → price, plus the subtotal and a per-head check against theUSER.mdbudget. - Hand off to a human:
@heresomeone with the restaurant link and the order list, and ask them to place and pay for it on Deliveroo. Record the restaurant + basket status on thelunch-runentity (basket_url: nulluntil a human shares the group-order link, if they make one).
The reaction's live-menu post (with exact item names + prices straight off Deliveroo) lands in the thread alongside your summary — use it to sanity-check prices, or let people reorder against it.
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 · 60 lines · 75 tokens per session scan A e00059538c1f
deliveroo-order is a skill published in the GitHub repository lobu-ai/lobu (220 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 758 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
build-monetized-app
Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…
eliza-cloud-buy-domain
Use whenever a user wants to register or buy a custom domain for an Eliza Cloud app — including in the same request as building the app ("build me X and put it on Y.com"). Uses Cloudflare as registrar after explicit user confirmation, paid from the user's existing cloud credit balance. Pairs with build-monetized-app…
ordercli
Foodora CLI for checking past orders and active order status. Use when the user asks to check food delivery orders, track a Foodora delivery, view order history, reorder a meal, look up past food orders, check delivery status, or manage Foodora sessions and authentication.
openakita/skills@taobaoke-tool
Taobaoke all-in-one toolkit for Taobao, JD, and Pinduoduo affiliate marketing. Convert product links to affiliate links, cross-platform price comparison, one-click price protection, and commission tracking. Use for e-commerce affiliate operations.
openakita/skills@baidu-ecommerce
Baidu E-commerce skill for cross-platform price comparison, review analysis, and purchase knowledge. Complete workflow from product discovery to purchase decision. Use when user wants to compare prices, read reviews, or make purchase decisions.
minimax-multimodal-toolkit
MiniMax multimodal model skill — use MiniMax Multi-Modal models for speech, music, video, and image. Create voice, music, video, and images with MiniMax AI: TTS (text-to-speech, voice cloning, voice design, multi-segment), music (songs, instrumentals), video (text-to-video, image-to-video, start-end frame, subject…