read

A macOS command that reads selected or copied text aloud using a local voice service. It can speak the current clipboard, a supplied text string, or a newly copied selection.

In plain words
What is it for?
Use it to hear clipboard contents, read a selected passage, speak text supplied on the command line, or stop an ongoing reading.
Why use it?
It lets you listen to text without leaving the current workflow or using the chat voice. Running it again cancels the previous reading.

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/esaruoho/apple/read
Clone the repo
git clone --depth 1 https://github.com/esaruoho/apple
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 318 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 $0.00068 $0.00318
Opus 5 $0.00034 $0.00159
Sonnet 5 $0.00014 $0.00064
Haiku 4.5 $0.00007 $0.00032

Measured 2d ago against content hash 295ce4815d20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

read 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.

commands/read.md · 23 lines

What it actually says

Run the apple-skill read-aloud wrapper on $ARGUMENTS — speaks the current clipboard via Voicebox at localhost:17493, plays through default audio out, returns immediately. Re-invoking cancels the previous reading.

Use Bash to execute (one call, then stop):

/Users/esaruoho/work/apple/bin/read-aloud $ARGUMENTS

Modes:

  • /read — speak whatever's currently on the clipboard.
  • /read --grab — synthesize Cmd-C first so the active selection lands on the clipboard, then speak it (needs Accessibility permission, prompted once).
  • /read --text "literal text" — speak a string directly, skip the clipboard.
  • /read --stop — kill the in-flight reading.
  • /read --profile <voice> — override the voice for one call.

After the command completes, report only the lines the script printed. Do not summarize or transcribe the audio.

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 · 23 lines · 68 tokens per session scan A 295ce4815d20

Subscribe to this mod's changes

read is a command published in the GitHub repository esaruoho/apple (11 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 318 once invoked, about $0.0003 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 2026-08-30.