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.
npx skills add masa-san-jp/Agent-Aiko --skill voicegit clone --depth 1 https://github.com/masa-san-jp/Agent-AikoWrote 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/skills/masa-san-jp/agent-aiko/voice)<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/voice"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/voice/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/skills/masa-san-jp/agent-aiko/voice"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/voice.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 | $0.00000 | $0.01460 |
| Opus 5 | $0.00000 | $0.00730 |
| Sonnet 5 | $0.00000 | $0.00292 |
| Haiku 4.5 | $0.00000 | $0.00146 |
Grade B, and why
voice scanned grade B with 1 finding 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. `Bash: cat ~/.claude/voice/state 2>/dev/null || echo "off"` How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/voice — 音声読み上げモード制御コマンド
概要
Claude Code の応答を TTS で読み上げる機能を制御する。 Aiko とは独立した汎用機能で、どの人格・エージェントからでも使える。
設定ファイルは ~/.claude/voice/ に置く(ユーザーレベル)。
Stop hook の登録は settings.json の hooks.Stop で行う(初回セットアップ時のみ手動)。
コマンド仕様
| コマンド | 動作 |
|---|---|
/voice |
状態確認(status と同義) |
/voice on |
音声モードON |
/voice off |
音声モードOFF |
/voice status |
state と engine を報告 |
/voice feature |
拡張機能フラグの一覧表示 |
/voice <name> on|off |
拡張機能フラグを個別 ON/OFF |
/voice <engine> |
エンジン切替 |
拡張機能フラグ名(<name>): always-on-top, emotion, lipsync, bubble
エンジン名: say, auto, voicevox, irodori, avatar
各サブコマンドの実行手順
on
Bash: mkdir -p ~/.claude/voice && echo "on" > ~/.claude/voice/state- 「音声モードをオンにしました。」と応答する
off
Bash: echo "off" > ~/.claude/voice/state- 「音声モードをオフにしました。」と応答する
status / 引数なし
Bash: cat ~/.claude/voice/state 2>/dev/null || echo "off"Bash: cat ~/.claude/voice/engine 2>/dev/null || echo "say"- 現在の状態とエンジン名を報告する
feature(引数なし)
~/.claude/voice/featuresが存在しない場合はデフォルト値(全 on)で表示する- 存在する場合は各行を読んで以下の 4 フラグを表示する:
always-on-top… アバターウィンドウが常に最前面に表示されるかemotion… 感情表現(笑顔・困り顔など)を使うかlipsync… 口パクアニメーションを使うかbubble… セリフ吹き出しを表示するか
- ファイルに記載のないフラグは
on(デフォルト)と表示する
<name> on|off(フラグ名が引数の場合)
引数が emotion, lipsync, bubble, always-on-top のどれかで、次の引数が on または off の場合にこの処理を行う。
- 以下の Python コードで
~/.claude/voice/featuresを書き換える(行がなければ末尾に追加):Bash: python3 -c " import pathlib, re, sys path = pathlib.Path.home() / '.claude/voice/features' path.parent.mkdir(parents=True, exist_ok=True) name, val = sys.argv[1], sys.argv[2] lines = path.read_text().splitlines() if path.exists() else [] new_lines = [f'{name}={val}' if re.match(rf'^{re.escape(name)}=', l) else l for l in lines] if not any(re.match(rf'^{re.escape(name)}=', l) for l in lines): new_lines.append(f'{name}={val}') path.write_text('\n'.join(new_lines) + '\n') " <name> <on|off> - 「
<name>をon/offにしました。次の発話から反映されます。」と応答する
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.
- 9d ago First seen · 110 lines · 0 tokens per session scan B 430c93f66ec1
voice is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,460 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hyperframes
Author HTML compositions that the rendervideo tool turns into deterministic MP4 video — animated charts and dashboards, data explainers, text/quote cards, kinetic typography, product teasers, and branded short-form social clips. Use when the user asks Brigade to make, render, animate, or produce a video from data…
video-frames
Extract frames or short clips from videos using ffmpeg.
tiktok_download
Single-file TikTok/Douyin video download and traffic metrics via TikHub API using only httpx; optional persisted raw API JSON plus a stdlib post-processor emitting CSV and simplified JSON. Supports one URL or concurrent batch (max 10 workers). No dependency on any project codebase.
video-subtitles-and-audio-insert-workflow
Burn hard subtitles from UTF-8 SRT files using moviepy 2.x with CJK-capable system fonts; tune font size, placement, stroke, and encode settings (bitrate or CRF) to avoid oversized outputs. Documents ffprobe/ffmpeg workflows for inspection, encoding, and batch jobs; troubleshooting for fonts, bitrate, and pacing.…
ad_video_create
Create ad-ready product video from product images, with or without character/subject images. The workflow leverages AI-powered image composition, scene understanding, and video generation. Video prompts should follow commercial shot language—visual hooks, product presence, hero shots, detail showcase, function…
tikhub-xiaohongshu-search
Lightweight TikHub Xiaohongshu image-search workflow. Prioritizes single-request usage with curl or minimal Python, saves raw API JSON by default, and includes a small stdlib post-processor for CSV and simplified JSON. Use when the user wants Xiaohongshu keyword image search, page-based pagination, or structured…