texting-listen

texting-listen is a skill for Claude Code from bowlofarugula/texting. It costs 92 tokens per session (893 once invoked), scanned A, original, Apache-2.0.

A session-only listener that watches an iMessage conversation for new messages from a chosen contact and can notify you or prepare a reply for approval.

In plain words
What is it for?
Use it to monitor an open conversation during the session, report incoming messages, and draft—but not send—possible replies.
Why use it?
It avoids repeatedly checking the conversation yourself while keeping replies under your control; it does not automatically send them.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the texting plugin — 5 skills, 1 MCP server shipped together

Good fit Use it to monitor an open conversation during the session, report incoming messages, and draft—but not send—possible replies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bowlofarugula/texting/texting-listen
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.

Any agent
npx skills add bowlofarugula/texting --skill texting-listen
Clone the repo
git clone --depth 1 https://github.com/bowlofarugula/texting

Made for: Claude Code.

Or install texting, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

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 texting-listen

README.md
[![agentmods](https://agentmods.dev/badge/skills/bowlofarugula/texting/texting-listen.svg)](https://agentmods.dev/skills/bowlofarugula/texting/texting-listen)
Your own site
<a href="https://agentmods.dev/skills/bowlofarugula/texting/texting-listen"><img src="https://agentmods.dev/badge/skills/bowlofarugula/texting/texting-listen.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 893 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 $0.00092 $0.00893
Opus 5 $0.00046 $0.00447
Sonnet 5 $0.00018 $0.00179
Haiku 4.5 $0.00009 $0.00089

Measured 7d ago against content hash 0e66a88510b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

texting-listen 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 7d 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.

skills/texting-listen/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/texting-listen — watch a thread for new messages

Arguments passed: $ARGUMENTS (e.g. "alex", "sam until she confirms")

This is a session-bound listener: it works only while this session is open and the Mac is awake. Say so up front in one line when starting. For true 24/7 unattended response, this is the wrong tool — see docs/AUTOREPLY.md and its tradeoffs.

Start

  1. Resolve the contact from list_chats output — rows carry contact and display names next to the handle/chat_id (no manual Contacts lookup; the engine labels chats itself). Ambiguous or missing → ask.
  2. Establish a baseline: read_messages for that chat (pass the handle as chat); note the ISO timestamp and content of the latest message. Report the baseline to the user.
  3. Ask (or infer from the request) what to do on arrival: just notify, or notify + draft a reply for approval.

Poll loop

For long-running, across-turn monitoring this skill polls with ScheduleWakeup (below) — that's the primary loop, because it doesn't hold a turn open. The watch MCP tool is the other option: it blocks up to ~60s waiting for the next message and is the right pick only for a short, active wait inside one turn ("hold on for her reply"), not for monitoring that should span minutes or hours. Pass the cursor it returns back as since_rowid to avoid missing anything between waits.

Schedule a wakeup (ScheduleWakeup) carrying a self-contained prompt: contact name, handle, baseline timestamp, and the on-arrival behavior. Cadence:

  • Actively waiting on a specific reply ("tell me when she confirms") → ~270s, staying inside the prompt-cache window.
  • Casual monitoring ("keep an eye on the thread") → 1200–1800s; don't burn a cache miss every 5 minutes for a thread that moves hourly.

On each wakeup: read_messages with since set to the baseline timestamp (returns only messages at/after it), diff against the baseline, and:

  • Nothing new → reschedule silently. Do not re-summarize the thread.
  • New inbound message → surface it (sender, time, text). Send a PushNotification if the user is likely away — a new message from the watched contact is exactly the "they'd act on it now" case. Then follow the agreed on-arrival behavior. Update the baseline and reschedule (unless the goal is met, e.g. "until she confirms" — then stop and say the watch is done).

Read the full file on GitHub · 75 lines

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. 7d ago First seen · 75 lines · 92 tokens per session scan A 0e66a88510b8

Subscribe to this mod's changes

texting-listen is a skill published in the GitHub repository bowlofarugula/texting (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 893 once invoked, about $0.0005 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.