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.
git 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/commands/omarshahine/restaurant-cli/restaurant-jobs)<a href="https://agentmods.dev/commands/omarshahine/restaurant-cli/restaurant-jobs"><img src="https://agentmods.dev/badge/commands/omarshahine/restaurant-cli/restaurant-jobs/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.
<a href="https://agentmods.dev/commands/omarshahine/restaurant-cli/restaurant-jobs"><img src="https://agentmods.dev/badge/commands/omarshahine/restaurant-cli/restaurant-jobs.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00015 | $0.00231 |
| Opus 5 | $0.00008 | $0.00115 |
| Sonnet 5 | $0.00003 | $0.00046 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
restaurant-jobs 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 9d 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.
What it actually says
Restaurant Jobs
Invoke the CLI's jobs subcommand:
restaurant jobs list # show all queued snipes
restaurant jobs cancel <job-id> # cancel a queued snipe (prompts y/N)
restaurant jobs logs <job-id> # show the fire-time log (JSONL + book output)
Parse $ARGUMENTS to decide which sub-action:
- If it looks like
list/cancel X/logs X, run that directly. - If it's empty, default to
list. - If it's a bare job id, default to
logs <id>.
For cancel, use --yes only if the user has explicitly confirmed cancellation in chat. Otherwise let the CLI's y/N gate fire.
Logs live at ~/.local/state/restaurant-cli/logs/<job-id>.log and contain JSONL snipe.start / snipe.end events plus the restaurant book output from when the at-job fired.
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.
- 9d ago First seen · 23 lines · 15 tokens per session scan A e99877e94764
restaurant-jobs is a command published in the GitHub repository omarshahine/restaurant-cli (8 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 231 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 2026-08-31.
Other commands, from other repositories
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
battle
Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line.
zh
A short command that switches Claude Code to Simplified Chinese. It is handled locally by a command hook.
cli-anything-web:list
List all available CLI-Anything-Web CLIs (installed and generated).
done
Finish a task - document, create PR or merge, close.
note
Add a note to the active task - progress, decisions, context. --session (aliases --snapshot, --pre-compact, --compact) writes a resume-grade session snapshot without ending the session.