Borrowing it
Nothing to install: this file belongs to mrslbt/nankai-trough-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mrslbt/nankai-trough-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/mrslbt/nankai-trough-mcpWrote 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/mrslbt/nankai-trough-mcp/agents-md)<a href="https://agentmods.dev/instructions/mrslbt/nankai-trough-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mrslbt/nankai-trough-mcp/agents-md/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/instructions/mrslbt/nankai-trough-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mrslbt/nankai-trough-mcp/agents-md.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 | $0.02311 | $0.02311 |
| Opus 5.5 | $0.00924 | $0.00924 |
| Sonnet 5.5 | $0.00462 | $0.00462 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
nankai-trough-mcp 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 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: nankai-trough-mcp
Guide for AI coding agents (Claude Code, Cursor, Codex, Copilot…) working in this repo.
What this project is
nankai-trough-mcp is an MCP server that surfaces official Japanese government data on the Nankai Trough (南海トラフ地震) earthquake hazard and Japanese building seismic standards, so an AI assistant can answer "how bad is it, how far does it reach, and what does my build year mean?" with cited figures instead of guesses. It never returns a safety verdict.
- npm:
nankai-trough-mcp· registry name:io.github.mrslbt/nankai-trough - Local stdio server, read-only, bundled data plus official lookups (GSI geocoder, Japan Post postal data via zipcloud, J-SHIS), no API keys.
- Eight tools, two prompts, four resources. Entry tool:
nankai_overview(scale and reach);official_hazard_mapsbridges to the official per-address maps;location_probabilityreports official J-SHIS per-mesh probabilities. - Attitude: assume the worst. Lead with the severe case, treat low probabilities as floors, and resolve ambiguous inputs (boundary years, unknown structure, unknown coast) toward the less favourable reading.
Quick commands
npm install # deps
npm run build # tsc → dist/ (must pass before commit)
npm test # build + node --test test/*.test.mjs (must pass before commit)
npm run smoke # build + a local MCP round-trip (all 8 tools listed, 1975 wood and 1975 RC building checks, resources)
npm run acceptance # build + LIVE J-SHIS / geocoder / postal lookups (needs network)
npm run dev # tsc --watch
Pre-commit: npm run build && npm test && npm run smoke. All must pass.
Architecture (the whole mental model)
src/
├── index.ts # McpServer, registers the 8 tools + 2 prompts + 4 resources + server instructions (the no-verdict rules)
├── meta.ts # READONLY / READONLY_EXTERNAL annotations
├── resources.ts # RESOURCES, reference docs rendered FROM the data below (no second copy, no drift)
├── data/
│ ├── nankai.ts # NANKAI_FACTS, the headline figures, each with source + as-of + a VERIFICATION LOG header
│ ├── building.ts # classifyEra(year, structure); ERA_INFO; KUMAMOTO_WOOD field data (wood-only, never shown for non-wood)
│ ├── jshis.ts # J-SHIS per-mesh 30-year probabilities (MAX + AVR, MAX first), floor-not-ceiling text
│ ├── prepare.ts # preparedness content + 7-day stockpile sizing
│ ├── shindo.ts # JMA 震度 5弱–7 meanings
│ ├── subsidy.ts # 耐震診断/補強 routing (never quotes an amount; varies by municipality)
│ └── sources.ts # SOURCES, DISCLAIMER, ATTRIBUTION: single source of truth, every figure traces here
└── lib/
├── geocode.ts # GSI geocoder with postal-code fallback + parsePrefMuni() (pure, tested)
├── postal.ts # Japan Post postal code → kanji address (zipcloud), extractPostalCode() (pure, tested)
├── maps.ts # hazardMapLinks(), pure builder for the official per-address map URLs (tested)
├── fetch.ts # safeFetch (hard timeout, UA, throws on non-OK)
└── cache.ts # getOrFetch + TTL
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 Changed · +19 lines · +459 tokens per session b4f0ec5ca453
- 2mo ago First seen · 107 lines · 1,852 tokens per session scan A b3c756109c1a
nankai-trough-mcp AGENTS.md is an instructions file published in the GitHub repository mrslbt/nankai-trough-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,311 tokens to every session, about $0.0092 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.
nankai-trough-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nankai-trough-mcp AGENTS.mdmrslbt/nankai-trough-mcp | Instructions file | 0 | 1mo ago | MIT | A | 2,311 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |