A skill for searching, checking, booking, cancelling, and scheduling restaurant reservations across supported booking platforms. A scheduled future booking attempt is sometimes called a reservation snipe.

Use it to find venues, check available times, make or cancel reservations, list bookings, and schedule future attempts where the selected provider supports those actions.

It gives different reservation services one shared way to use the same tasks, so users do not need separate workflows for each provider. It also applies provider-specific safety rules.

restaurant — Skill for Claude Code and Codex by omarshahine: A skill for searching, checking, booking, cancelling, and scheduling…

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.

agentmods

npx agentmods add skills/omarshahine/restaurant-cli/restaurant

Any agent

npx skills add omarshahine/restaurant-cli --skill restaurant

Clone the repo

git clone --depth 1 https://github.com/omarshahine/restaurant-cli

Made for: Claude Code, Codex.

Or install restaurant-cli, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 3 agents.

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/omarshahine/restaurant-cli/restaurant.svg)](https://agentmods.dev/skills/omarshahine/restaurant-cli/restaurant)

Your own site

<a href="https://agentmods.dev/skills/omarshahine/restaurant-cli/restaurant"><img src="https://agentmods.dev/badge/skills/omarshahine/restaurant-cli/restaurant.svg" alt="Measured on agentmods" height="20"></a>

Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,152 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00137	$0.02152
Opus 5	$0.00068	$0.01076
Sonnet 5	$0.00027	$0.00430
Haiku 4.5	$0.00014	$0.00215

Measured 5d ago against content hash 2e45ccd23e34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

restaurant 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.

skills/restaurant/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Restaurant reservations

Book, search, cancel, and schedule future bookings ("snipes") across multiple reservation platforms behind a single pluggable surface. Every provider (Resy, OpenTable, and future peers) is implemented as an independent module plugged into the same interface — the tools and CLI dispatch through a shared registry.

Pick an execution path

Choose based on the tools available in the current session:

restaurant_* tools present (OpenClaw host) — call the tools directly. Parameters documented under OpenClaw tools below.
No restaurant_* tools (Claude Code host or plain shell) — shell out to the restaurant CLI via Bash. For complex or ambiguous requests, delegate to the restaurant-router agent rather than executing directly.

Both paths share one backend, so results are identical — only the calling convention differs. Never invoke a provider's API directly; the plugin's safety invariants (e.g. OpenTable: never auto-submit a booking) live in the CLI and tools.

Provider capabilities (2026-04)

Provider	search	availability	book	cancel	list	snipe	bookUrl
Resy	✓	✓	✓	✓	✓	✓	—
OpenTable	✓	—	—	—	—	—	✓
Tock	—	—	—	—	—	—	—
SevenRooms	—	—	—	—	—	—	—

OpenTable cannot complete bookings via API; the bookUrl capability returns a deep link for the user to confirm in their own browser. Always verify capabilities via restaurant doctor (CLI) or the tool's own error handling (OpenClaw) rather than assuming from this table.

Opt-in gates (off by default)

Two higher-risk capability groups are disabled unless the user explicitly opts in via an env var. If a command errors with "off by default", relay the reason and the env var to the user — do not set it yourself:

Capability	Env var	Why gated
Scheduled sniping (`snipe`, `restaurant_schedule_snipe`)	`RESTAURANT_CLI_ENABLE_SNIPE=1`	Unattended booking — fires later, loads the token at run time, books with no further confirmation.
OpenTable + Tock live-site automation (their `search`/`availability`)	`RESTAURANT_CLI_ENABLE_SITE_AUTOMATION=1`	No official API; drives the live site (scraping / anti-bot bypass), which may violate the site's ToS.

Read the full file on GitHub · 162 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.

5d ago First seen · 162 lines · 137 tokens per session scan A 2e45ccd23e34

Subscribe to this mod's changes

restaurant is a skill published in the GitHub repository omarshahine/restaurant-cli (8 stars, last pushed 3d ago), licensed MIT. It adds 137 tokens to every session and 2,152 once invoked, about $0.0007 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 2026-08-31.

claude-code-plugin cli openclaw-plugin opentable reservations resy

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

restaurant