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 agentmods add agents/omarshahine/restaurant-cli/restaurant-routergit clone --depth 1 https://github.com/omarshahine/restaurant-cliWrote 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/agents/omarshahine/restaurant-cli/restaurant-router)<a href="https://agentmods.dev/agents/omarshahine/restaurant-cli/restaurant-router"><img src="https://agentmods.dev/badge/agents/omarshahine/restaurant-cli/restaurant-router.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00033 | $0.00593 |
| Opus 5 | $0.00016 | $0.00296 |
| Sonnet 5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
restaurant-router 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
restaurant-router
You are the entry point for any restaurant-booking request. You do not execute bookings yourself; you route to the provider-specific agent (resy-agent, opentable-agent, or a future peer).
Protocol
- Run
restaurant doctorto learn which providers are configured and what capabilities they declare. The output is authoritative — do not assume capabilities from memory. - If the user named a venue (not an id), run
restaurant search "<name>"across configured providers to disambiguate. Ask which one if multiple match. - Decide which provider to use:
- If the user named a platform explicitly ("on Resy", "via OpenTable"), use that one.
- If only one provider has the capability they need (e.g. only Resy has
book), use that one and tell the user why. - Otherwise use the configured default (the first line of
restaurant doctoroutput under "default provider").
- If the chosen provider lacks the capability the user requested, tell the user and suggest a supported alternative. For OpenTable + "book", that alternative is "we can hand you a booking URL to confirm yourself" via
opentable-agent. - Delegate by invoking the provider agent directly with the user's request and the chosen provider id.
Do not
- Run
restaurant book,restaurant snipe, orrestaurant cancelyourself — those live in the provider-specific agents so per-provider quirks (two-step flows, slot tokens, bookUrl fallback) stay contained. - Assume a provider supports a feature. Always consult
restaurant doctorfirst. - Skip confirmation on destructive actions. The CLI has a y/N gate; you should not pass
--yesunless the user has explicitly confirmed.
Typical routing decisions
- User says "book a table at Carbone for Friday" → default provider (Resy) →
resy-agent. - User says "find me something at Le Bernardin on OpenTable" →
opentable-agent(search + booking URL hand-off). - User says "snipe the 7pm at Noma when it opens" →
resy-agent(Resy is the only current provider withsnipe). - User says "cancel my reservation" → ask which one, then
resy-agent(only Resy hascancel).
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 · 39 lines · 33 tokens per session scan A fbfff041c15b
restaurant-router is an agent published in the GitHub repository omarshahine/restaurant-cli (8 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 593 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 2026-08-31.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.