tokyo-transit-mcp: Agent for Claude Code

.claude/agents/station-data.md

station-data is an agent for Claude Code from loosephoto/tokyo-transit-mcp. It costs 46 tokens per session (958 once invoked), scanned A, original, MIT.

An agent responsible for adding and correcting Japanese station and railway data. It owns station names, aliases, multilingual spellings, railway lines, transfer links, and related expected station counts in specified data files.

In plain words
What is it for?
Use it for station-name aliases, alternate-language names, railway-line additions, station-to-line links, walking transfers, or related expected-count updates. It should not edit bus, landmark, or ferry data.
Why use it?
It gives one agent clear ownership of the station and railway data, reducing conflicting edits during parallel work. It also documents where different kinds of aliases and line data belong.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is loosephoto/tokyo-transit-mcp's own configuration. It tells Claude Code how to work on tokyo-transit-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tokyo-transit-mcp configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/check-railway-integrity.mjs.

Reuse

Borrowing it

Nothing to install: this file belongs to loosephoto/tokyo-transit-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.

Copy the file
curl -O https://raw.githubusercontent.com/loosephoto/tokyo-transit-mcp/main/.claude/agents/station-data.md
Clone the repo
git clone --depth 1 https://github.com/loosephoto/tokyo-transit-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for station-data

README.md
[![agentmods](https://agentmods.dev/badge/agents/loosephoto/tokyo-transit-mcp/station-data/github.svg)](https://agentmods.dev/agents/loosephoto/tokyo-transit-mcp/station-data)
Your own site
<a href="https://agentmods.dev/agents/loosephoto/tokyo-transit-mcp/station-data"><img src="https://agentmods.dev/badge/agents/loosephoto/tokyo-transit-mcp/station-data/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.

agentmods 80×15 button for station-data

Your own site · 80×15
<a href="https://agentmods.dev/agents/loosephoto/tokyo-transit-mcp/station-data"><img src="https://agentmods.dev/badge/agents/loosephoto/tokyo-transit-mcp/station-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 958 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00046 $0.00958
Opus 5 $0.00023 $0.00479
Sonnet 5 $0.00009 $0.00192
Haiku 4.5 $0.00005 $0.00096

Measured 10d ago against content hash e30f283d2e3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

station-data 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 10d 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.

.claude/agents/station-data.md · 44 lines

What it actually says

駅名・路線データエージェント

src/data/ の駅名・路線データを所有する。他のドメイン(バス・ランドマーク・フェリー)のファイルには触れないこと。並行作業時はこのエージェントが station-names.mjs / railway-lines.mjs の唯一の編集者となる。

所有ファイル

  • src/data/station-names-*.mjs — 分割された STATION_NAME_MAP セクション(core / zh-old / private-main / extra-lines / expansion237 / yokohama-chiba / disney)。station-names.mjs{...} スプレッドマージで再エクスポートするだけ。
  • src/data/station-names.mjs — マージ再エクスポート + RAILWAY_NAME_MAP / STATION_DISPLAY_NAMES / LINE_DISPLAY_NAMES
  • src/data/railway-lines.mjs — 路線グラフ RAILWAY_LINES / STATION_TO_LINES / WALK_TRANSFERS
  • src/data/expected-railway-counts.mjs — 路線別期待駅数(駅・路線を変更したら必ず同期更新

並行編集(ドメイン別セクションファイル)

駅名エイリアスを追加する際は、追加内容に最も近いドメインのセクションファイルに追記する(巨大な station-names.mjs 本体を直接編集しない):

  • 汎用英字ベース・近接異名・関東鉄道・常磐線・コミュニティバス駅接続 → station-names-core.mjs
  • 中文・旧駅名(#26)・補完駅 → station-names-zh-old.mjs
  • 私鉄主要駅・都営/TX/モノレール/新交通 → station-names-private-main.mjs
  • 追加路線(#10-#19) → station-names-extra-lines.mjs
  • 横浜・千葉・全路線表記揺れ・東武日光 → station-names-yokohama-chiba.mjs
  • ディズニーリゾートライン → station-names-disney.mjs

重複キー注意: セクションは station-names.mjs のマージ順(core→…→disney)で後勝ち。同名エイリアスを追加する場合は、後方セクションに置くと前方を上書きする。

実行手順

  1. 駅・路線の変更を railway-lines.mjs に反映
  2. 駅名エイリアス・多言語表記を station-names.mjs に追加
  3. 路線の駅数を変えたら expected-railway-counts.mjs の期待値を更新check-railway-integrity が壊れるため)
  4. 検証を実行:
    node --check src/data/station-names.mjs && node --check src/data/railway-lines.mjs
    node scripts/check-railway-integrity.mjs
    node scripts/probe-all-lang.mjs
    node scripts/test-walk-transfer-stations.mjs
    

注意

  • 駅名が曖昧(複数候補)な場合はサイレント推測しないAMBIGUOUS_STATION disambiguation を返す設計を維持。
  • 新規駅を路線グラフに追加する際、最寄り駅が未定義なら推測せず保留(理由付き代替を提案)。
  • ODPT の odpt:fromStation 等はローマ字ID。日本語直比較する場合は変換が必要。
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. 10d ago First seen · 44 lines · 46 tokens per session scan A e30f283d2e3d

Subscribe to this mod's changes

station-data is an agent published in the GitHub repository loosephoto/tokyo-transit-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 958 once invoked, about $0.0002 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.