What is say?
say is a Claude Code mod by whilestevego that claude Code speaks through murmur (Kokoro on the Apple Neural Engine): turn summaries, needs-you alerts, background tasks, progress check-ins and rate-limit warnings, each session in its. It is listed under Context & memory and has no public popularity data yet.
| Type | Claude code mod |
|---|---|
| Author | whilestevego |
| Repository | whilestevego/claude-mods |
| Popularity | no public popularity data yet |
| Category | Context & memory |
| Security | High risk (52/100) |
| Rank | #5,118 of 5,272 Claude Code mods; #476 in Context & memory |
| Last commit | 2026-10-15 |
| Hooks | 8 events |
| Sees | AskUserQuestion calls, TodoWrite calls, every prompt, every tool call |
| Draws on | Pane |
Is say safe to install?
say scores 52/100 on the MCPMods security check: High risk. Things to review: starts processes outside the sandbox; writes files or config; watches every prompt or event. It passed 2 of 8 checks.
Mod footprints come from claude plugin validate, which lists every event a mod hooks and every API call it makes without running it.
| Check | Result |
|---|---|
| No network access | Pass |
| Starts processes outside the sandbox | Review |
| Writes files or config | Review |
| Doesn't read environment variables | Pass |
| Watches every prompt or event | Review |
| Drives Claude (model calls, prompts) | Note |
| Validator reported problems | Note |
| No license detected | Note |
API calls in its code
| Call | What it means |
|---|---|
$.clock.every | |
$.clock.sleep | |
$.command.register | |
$.config.list | |
$.fs.read | reads files |
$.fs.write | writes files |
$.model.complete | drives Claude |
$.model.fork | drives Claude |
$.process.run | runs processes |
$.session.id | |
$.state.get | |
$.ui.close | draws interface |
$.ui.open | draws interface |
$.ui.resolve | draws interface |
$.ui.toast | draws interface |
How do I install say?
- Check your Claude Code version. Mods need Claude Code 2.1.287 or later and are on by default.
claude --version
- Read its footprint. This lists every event it hooks and every API call it makes, without running it.
git clone https://github.com/whilestevego/claude-mods claude plugin validate ./claude-mods/say
- Install it. Run this in your terminal, then /reload-plugins in an open session.
git clone https://github.com/whilestevego/claude-mods && claude --plugin-dir ./claude-mods/say
Or ask Claude to set it up
Paste this into Claude Code and it installs say for you:
Install the "say" Claude Code mod from https://github.com/whilestevego/claude-mods/tree/main/say. Run claude plugin validate on it first and show me what it can access before you enable it.
More from whilestevego/claude-mods
This repository has 8 Claude Code mods on MCPMods.
- context-bar: Context window as a stacked bar above the prompt, toggled with /context-bar (Low risk)
- ghostty: Ghostty integration: a 4-word summary as the tab title (/title for a new one now), a tab progress bar, ❓ and a notificat (High risk)
- previews: Images Claude reads get a 🖼 preview line in the transcript; hover it to see the picture inline (terminals with image sup (Low risk)
- rate-limits: 5-hour and weekly rate-limit gauges above the prompt, with a warning at 90% (Low risk)
- session-id: Shows the session id in the prompt footer; click to copy (Low risk)
- tldr: A one-line TL;DR under Claude's long replies, written by Claude Haiku; the say mod speaks the same line (Review before installing)
- turn-receipt: A receipt row above the prompt after each turn: time, tools, files edited, cost (Low risk)