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 skills add narumiruna/gurume --skill gurume-cligit clone --depth 1 https://github.com/narumiruna/gurumeWrote 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/skills/narumiruna/gurume/gurume-cli)<a href="https://agentmods.dev/skills/narumiruna/gurume/gurume-cli"><img src="https://agentmods.dev/badge/skills/narumiruna/gurume/gurume-cli/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/skills/narumiruna/gurume/gurume-cli"><img src="https://agentmods.dev/badge/skills/narumiruna/gurume/gurume-cli.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 | $0.00127 | $0.01442 |
| Opus 5.5 | $0.00051 | $0.00577 |
| Sonnet 5.5 | $0.00025 | $0.00288 |
| Haiku 4.5 | $0.00013 | $0.00144 |
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 1mo 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 — 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. Usereview-countwhen the user wants popular/famous places,new-openfor 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 returnsstatus,items,meta,applied_filters,warnings, and structurederrorfields. Use legacy--output json-listonly if you specifically need the old list-only shape.
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.
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.
- 1mo ago First seen · 110 lines · 127 tokens per session scan A b89d535cab10
gurume-cli is a skill published in the GitHub repository narumiruna/gurume (9 stars, last pushed 9d ago), licensed MIT. It adds 127 tokens to every session and 1,442 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
telegram
Telegram Bot skill for sending and editing Telegram messages via Bot API. Use when Bub needs to: (1) Send a message to a Telegram user/group/channel, (2) Reply to a specific Telegram message with replytomessageid, (3) Edit an existing Telegram message, or (4) Push proactive Telegram notifications. Prefer rich…
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
modern-python-toolchain
Modern Python project setup with uv, ruff, and pyright. Use when initializing a new Python project, configuring the Python environment, setting up linting/formatting, or when a project needs uv (the fast Python package manager). Trigger on: 'set up Python', 'new Python project', 'configure uv', 'install uv', 'ruff'…
sync-check
Walks the documentation dependency web after a CLI code change and reports which downstream files (skills, SOPs, READMEs, plugin references) are out of sync. Use after fixing a bug, adding a command, changing auth behavior, refactoring, or before committing — and when the user says "sync check", "update docs"…
gap-analyzer
Compares a CLI's implemented commands against its APP.md API map and traffic-analysis.json to find missing endpoints, incomplete CRUD, dead client methods, and priority gaps. Runs as the mandatory first step of /cli-anything-web:refine and as an optional pre-review scan in standards.