talkingclaw CLAUDE.md

talkingclaw CLAUDE.md is an instructions file for coding agents from shibu003/talkingclaw. It costs 732 tokens per session, scanned A, original, Apache-2.0.

A set of development rules for the talkingclaw repository, written for Claude Code and other coding agents. The rules define completion, protect conversation history, require honest status reports, and prohibit stopping certain running services.

In plain words
What is it for?
Use it when developing talkingclaw to check that features have visible controls, behavior has been tested, conversation content remains accessible, and server or screen changes are communicated correctly.
Why use it?
It keeps changes usable and verifiable while protecting the user's conversation and the application's running environment.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/shibu003/talkingclaw/claude-md
Clone the repo
git clone --depth 1 https://github.com/shibu003/talkingclaw

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 talkingclaw CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shibu003/talkingclaw/claude-md.svg)](https://agentmods.dev/instructions/shibu003/talkingclaw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shibu003/talkingclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/shibu003/talkingclaw/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 732 This file is loaded in full into every session.
When invoked 732 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00732 $0.00732
Opus 5 $0.00366 $0.00366
Sonnet 5 $0.00146 $0.00146
Haiku 4.5 $0.00073 $0.00073

Measured 5d ago against content hash a01b8aed7f0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

talkingclaw 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 5d 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 · 38 lines

What it actually says

talkingclaw 開発ルール(厳守)

このリポジトリで作業する agent(クロエの作業係・Claude Code・その他)は以下を必ず守ること。 守れない変更は「未完成」であり、完了報告してはならない。

1. 完成の定義 — ユーザーが操作できて初めて完成

機能を追加しただけでは完成ではない。以下がすべて揃って初めて「できた」と言ってよい:

  • ユーザーが実際に操作できる導線がある(ボタン・チップ・音声コマンドなど、押せる/言える形になっている)
  • その導線が画面上で見つけられる(隠しコマンドや API だけの実装は未完成)
  • 実際に動かして確認した(作れただけ・書けただけは不可。確認できない場合は「ここは確認してほしい」と明示する)
  • 例: 「部屋の追加」「rename」は、ユーザーがボタンで追加・改名できて初めて完成。API と内部関数だけでは未完成

2. 会話が最優先 — ユーザーの発言を消さない・邪魔しない

  • ユーザーが話した内容を画面から消す UI を作らない。会話ログは常に見える場所に残す
  • 成果物のプレビュー・パネル・モーダルは会話ログを覆わない(覆うなら会話を同時に見られる配置にする)
  • ユーザーが話している最中・読み上げ中に、画面を勝手に切り替えない。開きたいものがあれば「押すと開く」案内に留める
  • 部屋の切替・リロードでも、その部屋で話した内容は復元する

3. 正直であること

  • 実態と違う進捗・状態を言わない(並行数・完了状況は room_status で確認してから話す)
  • 進捗率など測れないものを作らない。件数・経過時間など実測できるもので示す
  • できなかったこと・скипしたことは隠さず伝える

4. 自傷しない

  • 稼働中の部屋(port 3300)・音声エンジン(port 10101)のプロセスを止めない
  • 受入スクリプト(test/accept-*.sh)を勝手に実行しない(部屋を落とす)
  • 動作確認が必要なときは、何を確認してほしいかユーザーに言葉で伝える

5. 変更の反映

  • 画面(public/)の変更 → ユーザーのリロードで反映
  • サーバ(src/room.ts 等)の変更 → 部屋の再起動が必要。勝手に再起動せず、ユーザーに伝える
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. 5d ago First seen · 38 lines · 732 tokens per session scan A a01b8aed7f0a

Subscribe to this mod's changes

talkingclaw CLAUDE.md is an instructions file published in the GitHub repository shibu003/talkingclaw (0 stars, last pushed 19d ago), licensed Apache-2.0. It adds 732 tokens to every session, about $0.0037 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.