xcomet-mcp-server: Instructions file for Claude Code

CLAUDE.md

xcomet-mcp-server CLAUDE.md is an instructions file for Claude Code from shuji-bonji/xcomet-mcp-server. It costs 1,585 tokens per session, scanned A, original, MIT.

A set of instructions for working on the xCOMET MCP Server, a Node and Python service that lets AI clients communicate with an xCOMET model. It also defines rules for writing and maintaining Japanese documentation.

In plain words
What is it for?
Use it when editing the server, its tests, or Japanese README and changelog files. It covers repository structure, JSON-RPC communication, Python worker setup, and Japanese writing checks.
Why use it?
It helps contributors follow the repository's conventions instead of changing formats, translations, or runtime assumptions inconsistently.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is shuji-bonji/xcomet-mcp-server's own configuration. It tells Claude Code how to work on xcomet-mcp-server 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 xcomet-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shuji-bonji/xcomet-mcp-server. 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/shuji-bonji/xcomet-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shuji-bonji/xcomet-mcp-server

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 xcomet-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shuji-bonji/xcomet-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/shuji-bonji/xcomet-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shuji-bonji/xcomet-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/xcomet-mcp-server/claude-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.

agentmods 80×15 button for xcomet-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shuji-bonji/xcomet-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/xcomet-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,585 This file is loaded in full into every session.
When invoked 1,585 The same file — it is already loaded in full.
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 $0.01585 $0.01585
Opus 5 $0.00792 $0.00792
Sonnet 5 $0.00317 $0.00317
Haiku 4.5 $0.00159 $0.00159

Measured 8d ago against content hash c430c41853e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

xcomet-mcp-server CLAUDE.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 8d 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.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

xCOMET MCP Server を触るときの指針。Claude Code / Cowork から読まれる。

日本語を書くとき

ja-writing-guide.md を先に読む。 書き終えたら用語集の左列を検索し、残っていたら右列に 置き換える。対象は README.ja.mdtests/README.mdCHANGELOG.md、および会話の回答文。

  • 書く前の 3 つの確認(逆翻訳 / 錨 / 名前)を段落ごとに行う。
  • 英語版の事実(バージョン、パス、環境変数名、数値)は変えない。変えるのは日本語の形だけ。
  • 英語版に無い倍率・評価・推奨を足さない。
  • 見出しの絵文字を英語版から日本語版へ機械コピーしない。
  • 範囲は波ダッシュで書く(3.9〜3.12)。ハイフンと混在させない。
  • 注記ラベルは 重要 / 注意 / 注記 / 補足 の 4 種。NoteTip は使わない。

日付は JST で書く。実行環境の時計が UTC のことがあるため、TZ=Asia/Tokyo date +%F で 確認してから書く。CHANGELOG.md は npm の tarball にも入るので、publish 後は次の バージョンまで直せない。

この repo の形

  • stdio 専用の MCP server。HTTP transport は v0.6.0 で削除した。
  • Node(TypeScript)と Python の 2 層。両者は stdin / stdout 上の行区切り JSON-RPC で話す。
  • 実行時依存は @modelcontextprotocol/serverzod の 2 つだけ。
  • Python 側(python/server.py)は xCOMET モデルを読み込む常駐ワーカー。npm パッケージには このスクリプトしか入らない。Python 本体と unbabel-comet は利用者が用意する。
パス 役割
src/index.ts stdio の入口。serveStdio(factory)
src/server.ts createServer()。入口とテストが共用する factory
src/tools/index.ts ツール登録
src/schemas/index.ts 入出力スキーマ(zod)
src/services/python-server.ts Python ワーカーの起動と監視
python/server.py 常駐ワーカー
ja-writing-guide.md 日本語の用語と点検
tests/README.md 各テストスイートの対象

触る前に知っておくこと

  • Python ワーカーの stdout は JSON-RPC の通り道。 print() を stdout に出さない。ログは log()(stderr)を使う。Node 側も同じで、console.logno-console で禁止している。
  • model.predict() には num_workers に 1 以上を渡す。 COMET は MPS 環境で multiprocessing_context="fork" を渡す一方、既定の num_workers2 * gpus で CPU 推論では 0 になる。torch はこの組み合わせを拒否する。_num_workers() の下限 1 がそれを避けている。
  • 戻り値は outputSchema で検証されてから返る。 python/server.py が返すフィールドを 増減したら src/schemas/index.ts も直す。食い違うとツール呼び出しそのものが失敗する。 tests/output-schemas.test.ts がこの境界を見ている。
  • zod は 4.2.0 以上が必要。 それ未満だと npm installtsc も通り、server は起動して 接続まで成功し、最初の tools/list だけがエラーを返す。
  • モデルの重みは venv の中には入らない。 ~/.cache/huggingface/hub/ に入る。venv を 作り直しても再度ダウンロードする必要はない。
  • COMET の Prediction は自前の ModelOutput を継承していて、__getitem__ は str 以外の キーで値の側を引く。metadata[0] はサンプル 0 のデータではない。metadata["error_spans"] を使う(python/server.py_error_spans())。

Read the full file on GitHub · 89 lines

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. 8d ago First seen · 89 lines · 1,585 tokens per session scan A c430c41853e7

Subscribe to this mod's changes

xcomet-mcp-server CLAUDE.md is an instructions file published in the GitHub repository shuji-bonji/xcomet-mcp-server (2 stars, last pushed 10d ago), licensed MIT. It adds 1,585 tokens to every session, about $0.0079 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 2026-09-04.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens