imessage

imessage is a skill for Claude Code from linq-team/claude-code-imessage-channel. It costs 31 tokens per session (542 once invoked), scanned A, original, MIT.

A skill for sending and receiving iMessages through the Linq service. It supports conversations, reactions, message edits, effects, threaded replies, and file attachments.

In plain words
What is it for?
Use it to reply to incoming messages, send new texts, add tapbacks or effects, edit progress updates, reply to specific messages, and share files.
Why use it?
It lets a coding agent handle iMessage conversations directly instead of requiring separate manual messaging steps.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the imessage plugin — 3 skills, 1 hook, 1 MCP server shipped together

Good fit Use it to reply to incoming messages, send new texts, add tapbacks…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/linq-team/claude-code-imessage-channel/imessage
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 linq-team/claude-code-imessage-channel --skill imessage
Clone the repo
git clone --depth 1 https://github.com/linq-team/claude-code-imessage-channel

Made for: Claude Code.

Or install imessage, the plugin that ships this one along with the rest of its 3 skills, 1 hook, 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 imessage

README.md
[![agentmods](https://agentmods.dev/badge/skills/linq-team/claude-code-imessage-channel/imessage.svg)](https://agentmods.dev/skills/linq-team/claude-code-imessage-channel/imessage)
Your own site
<a href="https://agentmods.dev/skills/linq-team/claude-code-imessage-channel/imessage"><img src="https://agentmods.dev/badge/skills/linq-team/claude-code-imessage-channel/imessage.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 542 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 $0.00031 $0.00542
Opus 5 $0.00015 $0.00271
Sonnet 5 $0.00006 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured 7d ago against content hash 543627d72646, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

imessage 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/imessage/SKILL.md · 28 lines

What it actually says

You have access to iMessage via the Linq API. You can:

  1. Reply to inbound messages using the reply tool with the chat_id from the channel event
  2. Send new messages to any phone number using the send tool
  3. React to messages with tapbacks (like, love, laugh, dislike, emphasize, question) using the react tool
  4. Edit a previously sent message using edit_message for streaming progress updates
  5. Effects — add iMessage effects to reply or send with the optional effect parameter:
    • Screen: confetti, fireworks, lasers, sparkles, celebration, hearts, love, balloons, happy_birthday, echo, spotlight
    • Bubble: slam, loud, gentle, invisible
  6. Threading — reply to a specific message by passing reply_to (message ID) in the reply tool. The message_id is available in the channel event metadata.
  7. Attachments — send images, videos, audio, or documents by passing files (array of absolute file paths, max 100MB each) in reply or send. Files are uploaded automatically via the Linq API. Inbound attachments show as download URLs in the channel event.
  8. Text decorations — style text with text_decorations on reply or send. Each decoration has range: [start, end) and either style (bold, italic, strikethrough, underline) or animation (big, small, shake, nod, explode, ripple, bloom, jitter). iMessage only.
  9. Rich links — send a URL with a preview card using send_link with chat_id and url. The link must be the only content in the message.
  10. Capability check — use check_capability to check if a phone number supports iMessage or RCS before sending.

When channel events arrive as <channel source="imessage">, respond naturally and concisely - this is iMessage, keep it brief.

Read receipts and typing indicators are handled automatically.

Configuration

Credentials are stored in ~/.claude/channels/imessage/.env. Run /imessage:configure to manage them.

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 · 28 lines · 31 tokens per session scan A 543627d72646

Subscribe to this mod's changes

imessage is a skill published in the GitHub repository linq-team/claude-code-imessage-channel (24 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 542 once invoked, about $0.0002 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.