deliveroo

deliveroo is a skill for Claude Code, Codex from withoneai/one-agent-plugin. It costs 113 tokens per session (7,201 once invoked), scanned A, a copy of 2-chat, MIT.

A connection to Deliveroo, an online marketplace for ordering food, groceries, and other goods with delivery tracking.

In plain words
What is it for?
It helps work with Deliveroo data for restaurant, grocery, retail, ordering, and delivery workflows.
Why use it?
It avoids handling marketplace data manually when working with orders and delivery-related information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps work with Deliveroo data for restaurant, grocery, retail, ordering, and delivery workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/withoneai/one-agent-plugin/deliveroo
Install

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.

Any agent
npx skills add withoneai/one-agent-plugin --skill deliveroo
Clone the repo
git clone --depth 1 https://github.com/withoneai/one-agent-plugin

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for deliveroo

README.md
[![agentmods](https://agentmods.dev/badge/skills/withoneai/one-agent-plugin/deliveroo/github.svg)](https://agentmods.dev/skills/withoneai/one-agent-plugin/deliveroo)
Your own site
<a href="https://agentmods.dev/skills/withoneai/one-agent-plugin/deliveroo"><img src="https://agentmods.dev/badge/skills/withoneai/one-agent-plugin/deliveroo/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.

agentmods 80×15 button for deliveroo

Your own site · 80×15
<a href="https://agentmods.dev/skills/withoneai/one-agent-plugin/deliveroo"><img src="https://agentmods.dev/badge/skills/withoneai/one-agent-plugin/deliveroo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 77% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00113 $0.07201
Opus 5 $0.00056 $0.03601
Sonnet 5 $0.00023 $0.01440
Haiku 4.5 $0.00011 $0.00720

Measured 5d ago against content hash f695eced172b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deliveroo 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 5d 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.

Origin

This is a copy

77% identical to 2-chat — 345 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

platforms/one-deliveroo/skills/deliveroo/SKILL.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deliveroo through One

Deliveroo operates a technology-driven online food delivery marketplace that connects consumers with local restaurants, grocery and retail partners through its app, enabling on-demand ordering and real-time delivery tracking by independent riders across multiple countries.

One exposes Deliveroo through four MCP tools. The table below carries real action ids from One's knowledge base, so for a common operation you can skip search and go straight to reading the action's parameters.

How to run an action

  1. Find the action in the table below, or call search_one_platform_actions with platform deliveroo if it is not listed.
  2. Call get_one_action_knowledge with the action id. Do this every time, including for actions in this table. The table gives you the id, not the parameters.
  3. Call execute_one_action with parameters copied from that knowledge.

Never guess a parameter name, a body field, or an enum value. The knowledge has the real schema, and a guessed field is either a 400 or a silent write of the wrong thing.

Before you start

Call list_one_integrations once and confirm Deliveroo is connected. If it is missing, the user has not connected it: say so and point them at https://app.withone.ai rather than reaching for raw HTTP.

Each connection carries an access field. If it reports {"policy": "methods", "methods": ["GET"]} the agent is read-only here, so plan a read-only answer instead of attempting a write that will be refused.

Before a write

Creates, updates, deletes and sends land on a real Deliveroo account and cannot be recalled. State the action and the specific target in one line before the first write in a task, and let the user stop you. Reads need no confirmation.

Actions

Orders

Action Method Path Action id
Get an Order's Location and Rider Details GET /signature/v2/orders/{{id}}/location conn_mod_def::GJEDaD5pROA::psppXUchRJayABHKknzudQ
Get Order Information GET /signature/v1/orders/{{id}} conn_mod_def::GJEDPCxzCIg::G-79ogPKSlKKhB-hWesLdw
Get Single Order Details GET /order/v2/orders/{{order_id}} conn_mod_def::GJEDXUfF7Ng::jhGDnwx8QIaKT3O0o4gLDg
List a Restaurant’s Active Orders GET /picking/v1/sites/{{restaurant_id}}/orders/active conn_mod_def::GJEDl9gmJJg::U2CAoJLvS4WiTkkeCfI6Ig
List a Restaurant's Orders for a Brand GET /order/v2/brand/{{brand_id}}/restaurant/{{restaurant_id}}/orders conn_mod_def::GJEDXfE9ttg::BSbRRig3RwejZLYY9jya8Q
Accept an Order PUT /picking/v1/orders/{{order_id}}/accept conn_mod_def::GJEDlU1JdhA::PSe7IwdQRE-QQfzNhKdlUA
Amend Items in an Order POST /picking/v1/orders/{{order_id}}/amendments conn_mod_def::GJEDlptSgeg::sbOVvkccQ2y3EX-aVn-m3Q
Create a New Order POST /signature/v2/orders conn_mod_def::GJEDZ2KqIHg::SJ6fGR1zSemQNSezoK214Q
Reject an Order PUT /picking/v1/orders/{{order_id}}/reject conn_mod_def::GJEDlg9pw_g::N9BIqeGpQbWSYpj2KwHM0g
Start Picking Process for an Order PUT /picking/v1/orders/{{order_id}}/start_picking conn_mod_def::GJEDlO-hsTA::HQB8XYZHQ4Sx3gjNyMkQHA
Update an Order's Items Quantities PUT /picking/v2/orders/{{order_id}} conn_mod_def::GJEDXnh8Dyg::HO5A_Q62TRq9rP9fi-LBmQ
Update an Order's Status PATCH /order/v1/orders/{{order_id}} conn_mod_def::GJEDkQ6mQxA::PNNE5iv4Qlq-4GYqaW0Jbw

Read the full file on GitHub · 422 lines

Changes

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.

  1. 5d ago First seen · 422 lines · 0 tokens per session scan A f695eced172b

Subscribe to this mod's changes

deliveroo is a skill published in the GitHub repository withoneai/one-agent-plugin (1 stars, last pushed 19d ago), licensed MIT. It adds 113 tokens to every session and 7,201 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 77% identical to 2-chat, differing in 345 lines, and is treated as a copy.

Related

Other skills, from other repositories

p-image-try-on

Use when someone wants virtual try-on — dress a person in clothes from reference photos for fashion or ecommerce.

PrunaAI/pruna-skills · 27 tokens

building-b2b

Build Celigo B2B Manager EDI integrations -- trading partner onboarding, EDI profiles, file definitions, X12/EDIFACT flow patterns, and transaction monitoring. Use when onboarding partners, editing EDI flows, setting up parsing rules, or monitoring document exchange.

celigo/ai · 60 tokens

ada-diamonds-api

Reference for the Ada Diamonds public REST API (https://www.adadiamonds.com/api/v1) covering every endpoint, self-serve API keys and OAuth 2.1 scopes, the public sandbox key, rate limits, error shapes, versioning, and working curl examples. Use when integrating with Ada Diamonds over HTTP, generating client code…

adadiamonds/agent-tools · 101 tokens

ada-diamonds-commerce

Overview of agentic checkout at Ada Diamonds, covering OpenAI Agentic Commerce Protocol (ACP) checkout sessions at https://www.adadiamonds.com/api/acp/checkoutsessions, the ACP product feed, Google Universal Commerce Protocol (UCP) discovery at /.well-known/ucp, sandbox behaviour, and the delegated Stripe…

adadiamonds/agent-tools · 110 tokens

ada-diamonds-mcp

Connect to the Ada Diamonds MCP servers (catalog at https://www.adadiamonds.com/mcp, documentation at https://www.adadiamonds.com/mcp/docs) from Claude Code, Claude Desktop, Cursor, ChatGPT, or any Streamable HTTP MCP client, and use their tools and resources well. Use when setting up an MCP connection to Ada…

adadiamonds/agent-tools · 98 tokens

ada-diamonds-shopping

Search Ada Diamonds' live lab grown diamond inventory, engagement ring settings, and fine jewelry, and quote a complete ring correctly (a setting plus a loose diamond, priced separately, in US dollars). Use when a shopper asks what a budget buys, wants a specific shape, carat, color, or clarity, asks for a ring or…

adadiamonds/agent-tools · 93 tokens