practice

A switch for an English practice mode in CVI, a Claude voice-integration tool. When enabled, it asks you to repeat Claude's English instruction before carrying it out.

In plain words
What is it for?
Use it to turn English practice on or off, or to check the current setting.
Why use it?
It lets you practise giving coding instructions in English while still starting from Japanese requests.

Command

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 commands/signalcompose/claude-tools/practice
Clone the repo
git clone --depth 1 https://github.com/signalcompose/claude-tools
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00006 $0.00368
Opus 5 $0.00003 $0.00184
Sonnet 5 $0.00001 $0.00074
Haiku 4.5 $0.00001 $0.00037

Measured 2d ago against content hash f37227dc4ca1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

practice 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 2d 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.

plugins/cvi/commands/practice.md · 50 lines

What it actually says

CVI English Practice Mode

CVI(Claude Voice Integration)の英語練習モードを設定します。

以下のBashコマンドを即座に実行してください(確認ダイアログなし):

bash ${CLAUDE_PLUGIN_ROOT}/scripts/cvi-practice $ARGUMENTS

引数

  • (引数なし) - 現在の状態を表示
  • on - 英語練習モードを有効化
  • off - 英語練習モードを無効化
  • status - 現在の状態を表示

English Practice Modeの動作

有効時 (on):

  1. ユーザーが日本語で指示
  2. Claudeが英語での表現を提示:
    > "English instruction here"
    
    your turn
    
  3. ユーザーが英語でリピート
  4. Claudeが実行

無効時 (off) (デフォルト):

  • 言語に関係なく直接実行

使用例

  • /cvi:practice - 現在の状態を確認
  • /cvi:practice on - 有効化
  • /cvi:practice off - 無効化

注意事項

  • 設定は ~/.cvi/configENGLISH_PRACTICE に保存されます
  • 英語練習用の機能であり、通常の作業効率を優先する場合はオフにしてください

実行後、結果を報告してください。

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. 2d ago First seen · 50 lines · 6 tokens per session scan A f37227dc4ca1

Subscribe to this mod's changes

practice is a command published in the GitHub repository signalcompose/claude-tools (4 stars, last pushed 5d ago), licensed MIT. It adds 6 tokens to every session and 368 once invoked, about $0.0000 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.