agentmods.dev

summary-say

summary-say is a command for Claude Code from aperepel/claude-mlx-tts. It costs 8 tokens per session (408 once invoked), scanned A, original, MIT.

A command that summarizes the assistant's previous response and reads the summary aloud.

In plain words
What is it for?
Use it after interviews, specification work, or updates when you want a short spoken recap.
Why use it?
It gives you the main decisions or outcomes without requiring you to reread the full response.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-mlx-tts plugin — 7 commands, 2 hooks shipped together

not rated 10repo 7mo ago A scan 8 tokens original MIT

Good fit Use it after interviews, specification work, or updates when you want a short spoken recap.

Compare 6 commands from other repositories ↓
View source ↗ aperepel/claude-mlx-tts
Install

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.

Claude Code
/plugin marketplace add aperepel/claude-mlx-tts
Claude Code
/plugin install claude-mlx-tts

Made for: Claude Code.

Or install claude-mlx-tts, the plugin that ships this one along with the rest of its 7 commands, 2 hooks.

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 summary-say

README.md
[![agentmods](https://agentmods.dev/badge/commands/aperepel/claude-mlx-tts/summary-say/github.svg)](https://agentmods.dev/commands/aperepel/claude-mlx-tts/summary-say)
Your own site
<a href="https://agentmods.dev/commands/aperepel/claude-mlx-tts/summary-say"><img src="https://agentmods.dev/badge/commands/aperepel/claude-mlx-tts/summary-say/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.

agentmods 80×15 button for summary-say

Your own site · 80×15
<a href="https://agentmods.dev/commands/aperepel/claude-mlx-tts/summary-say"><img src="https://agentmods.dev/badge/commands/aperepel/claude-mlx-tts/summary-say.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00008 $0.00408
Opus 5 $0.00004 $0.00204
Sonnet 5 $0.00002 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured 9d ago against content hash 5acf948fdd95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

summary-say 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 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.

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.

commands/summary-say.md · 52 lines

What it actually says

Summary-Say Command

Summarize the last assistant response and speak it aloud.

Instructions

  1. Read the last assistant response (the message immediately before this command was invoked)

  2. Create a substantive summary (1-2 sentences, max 30 words):

    • For interview endings: Highlight 2-3 key decisions or outcomes, not just "interview complete"
    • For spec generation: Mention the main trade-offs or scope decisions
    • For bead updates: Summarize what was clarified or changed
    • Use natural, conversational language

  3. Speak it using the Bash tool:

    ${CLAUDE_PLUGIN_ROOT}/scripts/say.sh "Attention on deck... <your substantive summary>"

Examples

Interview ending (GOOD - mentions decisions):

${CLAUDE_PLUGIN_ROOT}/scripts/say.sh "Attention on deck... We settled on JWT auth with refresh tokens, scoped to internal users only, targeting a two-week MVP."

Interview ending (BAD - too generic):

# DON'T do this:
${CLAUDE_PLUGIN_ROOT}/scripts/say.sh "Attention on deck... The interview is complete."

Blitz completion:

${CLAUDE_PLUGIN_ROOT}/scripts/say.sh "Attention on deck... Clarified the caching strategy: Redis for sessions, in-memory for config. Added dependency on the auth task."

Spec generation:

${CLAUDE_PLUGIN_ROOT}/scripts/say.sh "Attention on deck... Spec saved with twelve requirements. Key decisions: eventual consistency over strong, and mobile deferred to phase two."

Key Principle

The summary should tell the listener what was decided, not just what happened. Extract the substance.

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. 9d ago First seen · 52 lines · 8 tokens per session scan A 5acf948fdd95

Subscribe to this mod's changes

summary-say is a command published in the GitHub repository aperepel/claude-mlx-tts (10 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 408 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.

Apple SiliconClaude CodeProductivitychatterboxclaude-code-pluginmlxtext-to-speech
Related

Other commands, from other repositories

start-talking

Start talking with Cadence Code.

michael-L-i/cadence-code · 6 tokens

voice-settings

Choose Cadence Code speech models.

michael-L-i/cadence-code · 6 tokens

jump-in

Jump In and add spoken guidance.

michael-L-i/cadence-code · 6 tokens

wrap-up

End the active Cadence Code conversation.

michael-L-i/cadence-code · 7 tokens

ponytail-help

Quick reference for ponytail levels, skills, and commands.

DietrichGebert/ponytail · 11 tokens

memo

Search, save, inspect, and maintain memo persistent memory.

jagoff/memo · 12 tokens