Borrowing it
Nothing to install: this file belongs to nakashima-takeo/wezterm-ai-agents. 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/nakashima-takeo/wezterm-ai-agents/main/CLAUDE.mdgit clone --depth 1 https://github.com/nakashima-takeo/wezterm-ai-agentsWrote 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/nakashima-takeo/wezterm-ai-agents/claude-md)<a href="https://agentmods.dev/instructions/nakashima-takeo/wezterm-ai-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/nakashima-takeo/wezterm-ai-agents/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.
<a href="https://agentmods.dev/instructions/nakashima-takeo/wezterm-ai-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/nakashima-takeo/wezterm-ai-agents/claude-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 | $0.01655 | $0.01655 |
| Opus 5 | $0.00827 | $0.00827 |
| Sonnet 5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
wezterm-ai-agents 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 11d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
概要
WezTerm プラグイン。並列 AI コーディングエージェントセッションを管理する。WezTerm の Lua 5.4 サンドボックス上で動作する (テスト/lint は LuaJIT で実行)。永続ワークスペース、git worktree 連携、タブ/ペイン UI によるエージェント状態追跡を提供。
コマンド
# Lint
luacheck .
# フォーマットチェック
stylua --check .
# フォーマット修正
stylua .
# 全テスト実行 (luajit 必須)
bash test/run.sh
# 単体テスト実行
luajit test/test_agent.lua
アーキテクチャ
plugin/init.lua がエントリポイント。dofile() で全モジュールをロードする。WezTerm サンドボックスは wezterm / mux グローバルを提供するが、debug ライブラリは使用不可。
ディレクトリ構成(レイヤ別。init.lua がロード順=依存階層で全体を接続):
plugin/
├── init.lua — エントリポイント、apply() で層順にロード+結線
├── ui/ — 上位層: 描画・操作
│ ├── ui.lua — タブタイトル、右ステータスバーの描画
│ └── selector/ — InputSelector ベースの UI + キーバインド
│ ├── init.lua — coordinator (build_keybinds / agent選択 / pin)
│ ├── workspace.lua — ワークスペース選択/登録/削除 UI
│ ├── worktree.lua — worktree/PR/Issue 選択 UI + prefetch
│ └── ui.lua — フォーマット共通ヘルパー (setup で両UIに注入)
├── state/ — 中位層: 永続化・配置 (循環は agent_mod/layout_mod 注入で回避)
│ ├── workspace/
│ │ ├── init.lua — JSON永続化 + CRUD
│ │ └── session.lua — タブ状態のスナップショット/同期/ワークスペース生成
│ └── layout.lua — ペイン分割レイアウトのスナップショット/復元
├── service/ — 下位層: 外部I/O・検出 (UI に依存しない)
│ ├── agent.lua — エージェントレジストリ、検出、状態集約、JSON リーダー
│ ├── agents/ — 各エージェント実装 (claude/codex/cursor/gemini)
│ ├── worktree/
│ │ ├── init.lua — ローカル git worktree 操作 (list/add/remove/prune) + 命名/パス展開
│ │ └── github.lua — PR/Issue 連携 (gh 取得・キャッシュ・パース・フィルタ・worktree生成)
│ ├── editor.lua — エディタ検出・起動引数
│ └── links.lua — ターミナル出力パスの editor:// リンク化
└── resource/ — 下位層: 静的データ
├── labels.lua — i18n ラベル (en/ja)
└── icons.lua — アイコンセット (unicode / nerd)、opts.nerd_font で切替
主要パターン:
- エージェント状態は hooks が pane ごとに JSON ファイルを書き込む push 方式:
$XDG_STATE_HOME/wezterm-ai-agents/<gui_pid>/wezterm-agent-<pane_id>(GUI プロセス PID 名前空間配下。フォールバック~/.local/state) hooks/agent_status.shが書き込み側 (全エージェント共通)。Lua 側はwezterm.json_parse()で読み取り- PID 名前空間は書き込み側
WEZTERM_UNIX_SOCKETのgui-sock-<pid>と読み取り側wezterm.procinfo.pid()が同一 GUI プロセス PID に合意する前提 (mux 内蔵の既定構成のみ。分離 mux 構成は非対応) - JSON 形式:
{"agent":"<id>","state":"<state>","ts":<unix>,"session_id":"<sid>"} - ワークスペースデータは
$XDG_STATE_HOME/wezterm-ai-agents/workspaces.json(PID 名前空間なし) にアトミック書き込み (tmp + rename) - 循環依存は関数引数でモジュールを渡して回避 (
agent_mod,layout_mod) - 非同期/外部コマンド実行の方針は docs/async.md を参照 (UI ブロック回避、背景取得 + キャッシュ等)
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.
- 11d ago First seen · 90 lines · 1,655 tokens per session scan A dd9a6db12571
wezterm-ai-agents CLAUDE.md is an instructions file published in the GitHub repository nakashima-takeo/wezterm-ai-agents (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,655 tokens to every session, about $0.0083 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
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.
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.
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).
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.
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).
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.