Borrowing it
Nothing to install: this file belongs to ishizakahiroshi/many-ai-cli. 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/ishizakahiroshi/many-ai-cli/main/CLAUDE.mdgit clone --depth 1 https://github.com/ishizakahiroshi/many-ai-cliWrote 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/ishizakahiroshi/many-ai-cli/claude-md)<a href="https://agentmods.dev/instructions/ishizakahiroshi/many-ai-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/ishizakahiroshi/many-ai-cli/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/ishizakahiroshi/many-ai-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/ishizakahiroshi/many-ai-cli/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 | $0.05792 | $0.05792 |
| Opus 5.5 | $0.02317 | $0.02317 |
| Sonnet 5.5 | $0.01158 | $0.01158 |
| Haiku 4.5 | $0.00579 | $0.00579 |
Grade A, and why
many-ai-cli 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 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
many-ai-cli 開発ガイド
最終更新: 2026-09-26(土) 01:08:47 — 引き継ぎメモの表示を、記録済みパスに対する明示的な Markdown プレビューとして設計原則の索引へ反映。索引化の経緯（2026-08-19）: 常時ロード分が 5 週間で 129 → 269 行に倍増したため「制定」節の本文を正本へ移した。再肥大は
scripts/check-claude-md.mjsが CI で止める
このファイルは索引であって本文ではない。 全 AI セッションで全文がロードされるので、本文を置くと全員のコンテキストを毎回消費する。詳細は各行が指す正本を読む。タスク別の詳細は
CLAUDE/*.md。
On translations / 翻訳について
This development guide is maintained in Japanese only — the Japanese text above and below is the authoritative version. There is no English edition of this file. (The user-facing README is available in English: README.md, with README.ja.md and README.vi.md.)
CLAUDE.vi.md, docs/vi/README.md and the
docs/vi/manual_*.vi.mdfiles are a point-in-time snapshot (2026-08-15) kindly contributed by a community translator. They are no longer kept in sync with this guide, so please read them as background rather than as current rules, and check the Japanese original before acting on anything. This does not apply to the Vietnamese UI locale (web/src/i18n/vi.json), which is a shipped feature and is maintained normally.If you work in another language, we're sorry to ask — please translate as needed on your side (a machine translation of this file is usually enough). Translation contributions are genuinely welcome; we just can't promise to keep them in step with the Japanese original, so anything merged will be treated the same way: a dated snapshot.
プロジェクト概要
many-ai-cli — 複数のAIコーディングCLI（Claude Code / Codex CLI）を並列で動かすときの 承認操作・進捗監視を 1 画面の Web ダッシュボードで一元管理 するツール。単一 Go バイナリ（Hub 常駐 + ラッパー機能）+ ブラウザ UI（xterm.js / TypeScript）。
仕様の正本は README（公開仕様）とソースコード（実装仕様）。v0.3.x の設計書は docs/local/archive/v0.3.x/v0.3.x-many-ai-cli-design.md へ退避した（非公開・履歴）。リリースごとの変更は CHANGELOG.md。実装状況をここに書き写さない（すぐ古くなり、二重管理になる）。
v0.8.0 まで出荷済み。v0.4.0 で Workbench と Hub 内蔵チャットプロキシを撤去、v0.5.0 で setup / doctor / autoapproval、v0.6.0 で transcript ベースのチャット本文、v0.7.0 で承認同一性の一本化とトレイ常駐、v0.8.0 で引き継ぎ看板・複数サブスクリプション・relay ループ・Command Code provider を追加した。
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 · +2 lines · +631 tokens per session 476f55106ea1
- 1mo ago Changed · +70 tokens per session d6c275464c4e
- 1mo ago Changed · -71 lines · -1,870 tokens per session 7efd9edc3904
- 1mo ago First seen · 231 lines · 6,961 tokens per session scan A 5f4e8eae5939
many-ai-cli CLAUDE.md is an instructions file published in the GitHub repository ishizakahiroshi/many-ai-cli (9 stars, last pushed yesterday), licensed MIT. It adds 5,792 tokens to every session, about $0.0232 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.