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 instructions/narumiruna/gurume/agents-mdgit 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/instructions/narumiruna/gurume/agents-md)<a href="https://agentmods.dev/instructions/narumiruna/gurume/agents-md"><img src="https://agentmods.dev/badge/instructions/narumiruna/gurume/agents-md.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 | $0.01026 | $0.01026 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
gurume AGENTS.md 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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/gurume/ contains the library, CLI, TUI, and MCP server. Key modules:
restaurant.py: core scraping request/response logic.search.py: higher-level search API with metadata and pagination.detail.py: restaurant detail fetching and parsing.suggest.py: area and keyword suggestion API integration.server.py: FastMCP server tools.cli.py: Typer CLI entrypoints.tui.py: Textual terminal UI.cache.py,retry.py: resilience helpers.area_mapping.py,genre_mapping.py: mapping helpers for precise filtering.
Tests are in tests/ and generally mirror module names, for example tests/test_search.py and tests/test_server.py. Runnable usage examples live in examples/.
Build, Test, and Development Commands
Use uv for all local Python workflows.
uv sync --dev: install runtime and development dependencies.make lintoruv run ruff check .: run lint and import-order checks.make typeoruv run ty check .: run static type checks. Run this after code changes.make testoruv run pytest -v -s --cov=src tests: run the full test suite with coverage.uv run python examples/basic_search.py: run a basic example locally.uv run gurume mcp: start the MCP server for local integration testing.uv run gurume tui: launch the Textual TUI for interactive search.
Coding Style & Naming Conventions
Target Python 3.12 and keep code type-annotated, using built-in generic syntax such as list[str] and X | None rather than typing aliases. Follow Ruff settings in pyproject.toml: 120-character line length, single-line imports where isort rewrites them, and standard snake_case for functions/modules, PascalCase for classes, and UPPER_CASE for constants and enums. Keep modules focused; split files before they become difficult to navigate. Reuse existing request, parsing, cache, retry, and mapping helpers before introducing new ones, and avoid adding dependencies or abstractions unless the current code clearly needs them.
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.
- 4d ago First seen · 65 lines · 1,026 tokens per session scan A ebaee614c0bc
gurume AGENTS.md is an instructions file published in the GitHub repository narumiruna/gurume (7 stars, last pushed 5d ago), licensed MIT. It adds 1,026 tokens to every session, about $0.0051 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 instructions, from other repositories
RivalSearchMCP AGENTS.md
Instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.
markdown-vault-mcp AGENTS.md
AGENTS.md instructions for pvliesdonk/markdown-vault-mcp, covering markdown vault mcp, design, project structure, conventions and skills.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
ocr-mcp AGENTS.md
AGENTS.md instructions for sandraschi/ocr-mcp, covering ocr-mcp — agent guide, entry points, quick ref, standards and key files.
sagemath-mcp CLAUDE.md
Instructions for XBP-Europe/sagemath-mcp, covering claude.md, project, commands, linting and testing.
calibremcp AGENTS.md
AGENTS.md instructions for sandraschi/calibremcp, covering calibremcp — agent guide, entry points, standards, key files and http daemon + stdio proxy.