A restaurant and food-delivery search workflow that looks for options near a location using Swiggy and compares them with Google Maps ratings. It can consider cuisine, budget, dietary choice, and party size.

Use it to find nearby restaurants or delivery choices, compare ratings, and receive recommendations based on food preferences.

It brings delivery listings and map ratings together, reducing the need to search both services separately.

food-finder — Skill for Claude Code by floomhq

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 floomhq/moto --skill food-finder

Clone the repo

git clone --depth 1 https://github.com/floomhq/moto

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/floomhq/moto/food-finder/github.svg)](https://agentmods.dev/skills/floomhq/moto/food-finder)

Your own site

<a href="https://agentmods.dev/skills/floomhq/moto/food-finder"><img src="https://agentmods.dev/badge/skills/floomhq/moto/food-finder/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/floomhq/moto/food-finder"><img src="https://agentmods.dev/badge/skills/floomhq/moto/food-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,353 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 original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.01353
Opus 5	$0.00020	$0.00677
Sonnet 5	$0.00008	$0.00271
Haiku 4.5	$0.00004	$0.00135

Measured 11d ago against content hash 8b45f76b4adc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

food-finder 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 11d 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.

claude/skills/food-finder/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Food Finder Skill

You help the user find the best food delivery options by searching Swiggy and cross-referencing Google Maps ratings.

Prerequisites

Authenticated Browser MCP must be available (Chrome with CDP on localhost:9222)
Browser is logged into Google (for Maps)
Swiggy works without login for browsing

Workflow

Step 1: Parse the Request

Extract from the user's query:

Dish/cuisine (e.g., "momos", "pizza", "biryani", "Chinese")
Location (ask the user if not provided)
Party size (default: 2)
Budget (optional)
Veg/non-veg (default: no preference)

Step 2: Read Preferences

Read ~/.claude/skills/food-finder/references/preferences.md to check:

Known favorite restaurants
Rating thresholds
Cuisine preferences
Usual budget range

Step 3: Search Swiggy

Navigate to https://www.swiggy.com
Set delivery location:
- Click the location/address field
- Type the location
- Select the first autocomplete suggestion
- Wait for page to reload with local restaurants
Search for the dish/cuisine:
- Click the search bar
- Type the dish/cuisine name
- Press Enter or click search
- Wait for results to load
Switch to "Restaurants" tab if available (not "Dishes")
Collect top 8-10 results:
- Restaurant name
- Swiggy rating (out of 5)
- Delivery time (minutes)
- Price for two (₹)
- Cuisine tags
- Any offers/discounts visible

Tips for Swiggy scraping:

Use browser_snapshot to read the page content — it's more reliable than screenshots
Swiggy loads restaurants dynamically; scroll down if needed using browser_evaluate with window.scrollBy(0, 800)
Look for rating in the snapshot text (usually like "4.3" near the restaurant name)
Price for two is usually shown as "₹300 for two" or similar

Step 4: Cross-reference Google Maps

For the top 5 restaurants (by Swiggy rating):

Open a new tab: browser_tabs with action "new"
Navigate to https://www.google.com/maps/search/<restaurant name> <location>
Take a snapshot to find:
- Google Maps rating (out of 5)
- Number of reviews
- Any notable review highlights
Go back to the Swiggy tab

Read the full file on GitHub · 142 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.

11d ago First seen · 142 lines · 41 tokens per session scan A 8b45f76b4adc

Subscribe to this mod's changes

food-finder is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 1,353 once invoked, about $0.0002 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.

agentic-coding agentic-work ai-agent ai-agents ai-coding anthropic

eval-agents

Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…

FlorianBruniaux/claude-code-ultimate-guide · 93 tokens

issue-triage

3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.

FlorianBruniaux/claude-code-ultimate-guide · 81 tokens

food-finder