gurume-cli

A command-line tool for searching Japanese restaurants on Tabelog, a major Japanese restaurant-review website. Searches can use an area, cuisine, or keyword.

In plain words
What is it for?
It is for finding restaurants in Japan, such as ramen shops, sushi restaurants, or izakayas, by location and search criteria.
Why use it?
It provides current, structured restaurant information instead of relying on memory or manually scraping websites.

Skill for Claude CodeCodex

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/narumiruna/gurume/gurume-cli
Any agent
npx skills add narumiruna/gurume --skill gurume-cli
Clone the repo
git clone --depth 1 https://github.com/narumiruna/gurume

Made for: Claude Code, Codex.

Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,442 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.

ModelPer sessionOnce invoked
Fable 5 $0.00127 $0.01442
Opus 5 $0.00063 $0.00721
Sonnet 5 $0.00025 $0.00288
Haiku 4.5 $0.00013 $0.00144

Measured 2d ago against content hash b89d535cab10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gurume-cli 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 2d 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/gurume-cli/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gurume CLI

gurume is a CLI wrapper around Tabelog (Japan's largest restaurant review site). Use it instead of guessing restaurants from memory or scraping the web — its data is current and structured.

When to use

Trigger this skill whenever the user wants to find restaurants in Japan. Typical signals:

  • Mentions a Japanese place name (Tokyo, 大阪, Shibuya, 三重, 京都駅, ...)
  • Mentions Japanese cuisines (ramen, sushi, unagi, yakiniku, izakaya, 寿司, ラーメン, ...)
  • Asks for restaurant recommendations / "where to eat" in Japan
  • Plans a trip to Japan and asks about food

Do not trigger for: non-Japan restaurants, recipes, food delivery apps, or general food trivia.

Workflow

1. Resolve the cuisine (if any)

If the user mentions a specific cuisine, map it to one of Tabelog's supported cuisine names. The full list is in references/cuisines.md — read that file when you need the mapping. Cuisine names must be passed in Japanese (e.g. ラーメン, not ramen).

If the user's request doesn't fit the fixed list (e.g. "tonkotsu ramen", "omakase sushi", "okonomiyaki"), drop --cuisine and put the extra detail into --keyword instead. Cuisine + keyword can be combined in the CLI, but the MCP tool intentionally rejects keyword + cuisine; prefer the shared behavior of either supported cuisine-only search or best-effort keyword search.

2. Resolve the area

Pass the area in Japanese where possible (東京, 大阪, 渋谷, 京都, 三重). Romaji sometimes works, but Japanese is more reliable. Use the most specific area the user gave you — 渋谷 returns better results than 東京 if the user said "Shibuya".

3. Run the search

Default invocation — use JSON output so you can parse results cleanly:

gurume search --area <area> [--cuisine <jp-cuisine>] [--keyword <jp-keyword>] \
              --sort ranking --limit 10 --output json

Flag guidance:

  • --sort ranking (default): good general "best of" results. Use review-count when the user wants popular/famous places, new-open for newly opened spots.
  • --limit: 10 is plenty for a conversational reply. Bump to 20+ only if the user asks for a long list.
  • --output json: preferred for agents. It returns status, items, meta, applied_filters, warnings, and structured error fields. Use legacy --output json-list only if you specifically need the old list-only shape.

Read the full file on GitHub · 110 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 110 lines · 127 tokens per session scan A b89d535cab10

Subscribe to this mod's changes

gurume-cli is a skill published in the GitHub repository narumiruna/gurume (7 stars, last pushed 4d ago), licensed MIT. It adds 127 tokens to every session and 1,442 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

reviewing-code

Review code for quality, maintainability, and correctness. Use when reviewing pull requests, evaluating code changes, or providing feedback on implementations. Focuses on API design, patterns, and actionable feedback.

PrefectHQ/fastmcp · 43 tokens

review-security-report

Review FastMCP vulnerability reports before accepting, rejecting, patching, scoring, or publishing them. Use for security advisories, bug-bounty submissions, OAuth or MCP vulnerability claims, and proposed security fixes.

PrefectHQ/fastmcp · 46 tokens

writing-release-notes

Use when preparing, refreshing, backfilling, or redrafting a release-notes page under docs/releases/ before opening a normal review pull request.

pvliesdonk/markdown-vault-mcp · 35 tokens

skills

Generate a complete SVG file from a natural language description using SEP-1577 multi-step sampling.

sandraschi/inkscape-mcp · 0 tokens

applying-template-updates

Use when asked to work through, apply, resolve or review a template update pull request (the weekly copier/update branch opened by the copier-update workflow), or after running copier update --trust by hand: applies the upgrade notes, resolves conflict markers by the resolution policy, checks the seeded-once files the…

pvliesdonk/markdown-vault-mcp · 81 tokens

logging-standard

Use before adding or changing any logging call in src/: the structlog-based standard, log levels, exception handling, and message format every module follows.

pvliesdonk/markdown-vault-mcp · 33 tokens