claude-code-imessage-channel: Instructions file for Claude Code

CLAUDE.md

claude-code-imessage-channel CLAUDE.md is an instructions file for Claude Code from linq-team/claude-code-imessage-channel. It costs 521 tokens per session, scanned A, original, MIT.

Repository instructions for a Claude Code plugin that connects Claude Code to iMessage through Linq. It describes receiving messages and sending replies, reactions, edits, and attachments, with SMS/RCS fallback.

In plain words
What is it for?
Building or maintaining an iMessage channel for Claude Code, including message polling, photo handling, replies, reactions, edits, and file attachments.
Why use it?
They explain how messages enter the coding-agent session and how the agent should use the channel’s communication tools.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is linq-team/claude-code-imessage-channel's own configuration. It tells Claude Code how to work on claude-code-imessage-channel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-imessage-channel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to linq-team/claude-code-imessage-channel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/linq-team/claude-code-imessage-channel/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/linq-team/claude-code-imessage-channel

Made for: Claude Code.

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 claude-code-imessage-channel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/linq-team/claude-code-imessage-channel/claude-md.svg)](https://agentmods.dev/instructions/linq-team/claude-code-imessage-channel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/linq-team/claude-code-imessage-channel/claude-md"><img src="https://agentmods.dev/badge/instructions/linq-team/claude-code-imessage-channel/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 521 This file is loaded in full into every session.
When invoked 521 The same file — it is already loaded in full.
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 5.1 $0.00521 $0.00521
Opus 5 $0.00260 $0.00260
Sonnet 5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured 6d ago against content hash d11db3fc87b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-code-imessage-channel CLAUDE.md 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 6d 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.

CLAUDE.md · 51 lines

What it actually says

CLAUDE.md

This is the iMessage channel plugin for Claude Code, powered by Linq.

What This Plugin Does

When enabled as a channel, this plugin bridges iMessage and your Claude Code session:

  • Polls the Linq API for new inbound iMessages every 3 seconds
  • Pushes them into the Claude Code session as <channel> events
  • Downloads inbound photos to ~/.claude/channels/imessage/inbox/
  • Exposes tools for Claude to reply, send, react, edit, and attach files via iMessage
  • Auto-sends read receipts and typing indicators
  • Tries iMessage first, falls back to SMS/RCS automatically

Channel Events

Messages arrive as:

<channel source="imessage" sender="+1..." chat_id="...">message text</channel>

If the message has a photo, image_path is included in the meta — use Read to view it.

Tools

Tool Description
reply Reply to an inbound iMessage. Optional: effect, reply_to, files, text_decorations.
send Send to any phone number. Optional: effect, files, text_decorations. Returns chat_id + message_id.
react Tapback reaction: like, love, laugh, dislike, emphasize, question.
edit_message Edit a previously sent message (for streaming progress updates).
send_link Send a URL with a rich link preview card.
check_capability Check if a phone number supports iMessage or RCS.

Configuration

Credentials are stored in ~/.claude/channels/imessage/.env:

  • LINQ_TOKEN - Linq API token (required)
  • LINQ_FROM_PHONE - Your Linq phone number (required)

Access control is in ~/.claude/channels/imessage/access.json. Use /imessage:access to manage.

Setup

  1. Add marketplace: /plugin marketplace add linq-team/claude-code-imessage-channel
  2. Install: /plugin install imessage@linq
  3. Configure: /imessage:configure <token> then /imessage:configure <phone>
  4. Launch: claude --dangerously-load-development-channels plugin:imessage@linq
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. 6d ago First seen · 51 lines · 521 tokens per session scan A d11db3fc87b8

Subscribe to this mod's changes

claude-code-imessage-channel CLAUDE.md is an instructions file published in the GitHub repository linq-team/claude-code-imessage-channel (24 stars, last pushed 1mo ago), licensed MIT. It adds 521 tokens to every session, about $0.0026 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens