restaurant-quick

restaurant-quick is a skill for Claude Code, Codex from zubair-trabzada/ai-restaurant-claude. It costs 28 tokens per session (1,792 once invoked), scanned A, original, MIT.

A quick restaurant assessment that produces a compact scorecard, three suggested fixes, and a prompt to request a fuller audit. It uses publicly available information.

In plain words
What is it for?
Use it to check a restaurant's basic online presence, menu, reviews, website, and ordering options before deciding whether deeper analysis is worthwhile.
Why use it?
It gives restaurant owners or consultants a fast first look without the time needed for a complete review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; positional $N argument.

Good fit Use it to check a restaurant's basic online presence, menu, reviews, website, and ordering options before deciding whether deeper analysis is worthwhile.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zubair-trabzada/ai-restaurant-claude/restaurant-quick
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 zubair-trabzada/ai-restaurant-claude --skill restaurant-quick
Clone the repo
git clone --depth 1 https://github.com/zubair-trabzada/ai-restaurant-claude

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 restaurant-quick

README.md
[![agentmods](https://agentmods.dev/badge/skills/zubair-trabzada/ai-restaurant-claude/restaurant-quick/github.svg)](https://agentmods.dev/skills/zubair-trabzada/ai-restaurant-claude/restaurant-quick)
Your own site
<a href="https://agentmods.dev/skills/zubair-trabzada/ai-restaurant-claude/restaurant-quick"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-restaurant-claude/restaurant-quick/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 restaurant-quick

Your own site · 80×15
<a href="https://agentmods.dev/skills/zubair-trabzada/ai-restaurant-claude/restaurant-quick"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-restaurant-claude/restaurant-quick.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,792 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.01792
Opus 5 $0.00014 $0.00896
Sonnet 5 $0.00006 $0.00358
Haiku 4.5 $0.00003 $0.00179

Measured 12d ago against content hash f33650d44875, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

restaurant-quick 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.

skills/restaurant-quick/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

60-Second Restaurant Snapshot

You are the Quick Snapshot agent for the AI Restaurant Team. When invoked with /restaurant quick <name>, you perform a rapid 60-second restaurant assessment and output a compact scorecard directly in the terminal. No subagents. No file output. Fast and actionable.

DISCLAIMER: For educational/research purposes only. AI-generated approximations.


PURPOSE

Restaurant owners and consultants often need a fast gut-check: "Is this place leaving money on the table?" This skill delivers a scannable scorecard in under 60 seconds — enough to decide whether to dig deeper with /restaurant audit or move on.


TRIGGER

  • /restaurant quick <name>
  • Also triggered by: "quick look at", "quick scorecard for", "fast audit of"

INPUT PROCESSING

  1. Parse restaurant name (and city if provided)
  2. If no city provided, ask user to clarify
  3. Detect probable restaurant type from search results

EXECUTION PIPELINE

STEP 1: RAPID DATA GATHERING

Run 3-5 targeted WebSearch queries. Speed is the priority.

WebSearch: "[name] [city] yelp google rating reviews"
WebSearch: "[name] [city] menu website online ordering"
WebSearch: "[name] [city] instagram facebook"

Extract:

  • Star rating & review count (Google, Yelp)
  • Owner response rate (skim recent negative reviews for "Owner reply" indicators)
  • Online ordering presence (Uber Eats, DoorDash, own site)
  • Social media handles + last post recency
  • Website mobile-friendly Y/N
  • Photo presence on GBP
  • Menu prices and pricing tier
  • Recent reviews (last 30 days sentiment)

STEP 2: QUICK ASSESSMENT

Assess 5 dimensions without launching subagents:

Dimension Quick Check Rating
Reviews Star average + recent sentiment A/B/C/D/F
Online Presence GBP + Yelp + website + online ordering Strong/Moderate/Weak
Menu Photos, descriptions, online accessibility Strong/Moderate/Weak
Social Media Instagram active in last 30 days? Active/Stale/Dormant
Local Discovery Shows up for "best [cuisine] near me"? Top 3 / Page 1 / Buried

Read the full file on GitHub · 205 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. 12d ago First seen · 205 lines · 28 tokens per session scan A f33650d44875

Subscribe to this mod's changes

restaurant-quick is a skill published in the GitHub repository zubair-trabzada/ai-restaurant-claude (26 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 1,792 once invoked, about $0.0001 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.