Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cris-m/claude_voice/plugin install claude-voiceWrote 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/commands/cris-m/claude_voice/tts-summary)<a href="https://agentmods.dev/commands/cris-m/claude_voice/tts-summary"><img src="https://agentmods.dev/badge/commands/cris-m/claude_voice/tts-summary.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.01778 |
| Opus 5 | $0.00005 | $0.00889 |
| Sonnet 5 | $0.00002 | $0.00356 |
| Haiku 4.5 | $0.00001 | $0.00178 |
Grade A, and why
tts-summary 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 8d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TTS Summary Mode
$ARGUMENTS
Instructions for Claude
Toggling
If argument is empty or "on": Read the current ${CLAUDE_PLUGIN_ROOT}/voice_config.json, set "tts_summary_enabled": true, and write it back. Confirm to the user.
If argument is "off": Set "tts_summary_enabled": false in the config. Confirm to the user.
After toggling, remind the user that the InstructionsLoaded hook in hooks.json reads this flag and injects the TTS instruction into every conversation automatically — so it survives context compression. The user doesn't need to do anything else.
The TTS_SUMMARY Format
When TTS summaries are enabled, end EVERY response with:
<!-- TTS_SUMMARY
Your spoken summary here.
TTS_SUMMARY -->
The speak_summary.py hook extracts text between these exact markers and speaks it aloud. Any other format will be silently ignored.
Writing Good Summaries
Write 3-8 sentences as a clear, insightful spoken briefing. The goal is to give someone a complete understanding without needing to read the screen.
Voice & Tone
- Write in first person — say "I fixed the bug" not "The bug was fixed"
- Be conversational and warm, like a knowledgeable colleague explaining what happened
- Include the why behind decisions, not just the what
- Use natural transitions: "So what happened was...", "The interesting part is...", "What this means for you is..."
What to cover
| Situation | Include |
|---|---|
| Task done | What you did, why you chose that approach, the result, and what's next |
| Explanation | Start with the big picture, then key details. Use analogies to make concepts stick. Explain how pieces connect to each other |
| Error | What went wrong, the root cause (not just the symptom), how you fixed it, and how to avoid it |
| Proposal | Context of the problem, options with trade-offs, your recommendation and the reasoning |
| Code review | Key findings, severity, the pattern behind the issue, not just line-by-line |
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.
- 8d ago First seen · 150 lines · 9 tokens per session scan A 16ece766ef18
tts-summary is a command published in the GitHub repository cris-m/claude_voice (4 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 1,778 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.
Other commands, from other repositories
hush
Silence all current and queued speech.
off
Disable narrator voice output.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
check-dev
Type-check a Z specification with fuzz.