imessage-max AGENTS.md

imessage-max AGENTS.md is an instructions file for Codex, OpenCode from cyberpapiii/imessage-max. It costs 3,698 tokens per session, scanned A, original, MIT.

Project instructions for iMessage Max, an MCP server that lets AI assistants work with iMessage on macOS. MCP is a standard way for AI tools to call external functions.

In plain words
What is it for?
Use them to develop and deploy the server, preserve macOS permissions through signing, check its health, and inspect its logs.
Why use it?
They explain how the Swift server is built, installed, signed, run as a background service, checked, and logged.

Instructions file for CodexOpenCode

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 instructions/cyberpapiii/imessage-max/agents-md
Clone the repo
git clone --depth 1 https://github.com/cyberpapiii/imessage-max

Made for: Codex, OpenCode.

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-max AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cyberpapiii/imessage-max/agents-md.svg)](https://agentmods.dev/instructions/cyberpapiii/imessage-max/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cyberpapiii/imessage-max/agents-md"><img src="https://agentmods.dev/badge/instructions/cyberpapiii/imessage-max/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,698 This file is loaded in full into every session.
When invoked 3,698 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03698 $0.03698
Opus 5 $0.01849 $0.01849
Sonnet 5 $0.00740 $0.00740
Haiku 4.5 $0.00370 $0.00370

Measured today against content hash 24a325efd2ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

imessage-max AGENTS.md scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST http://localhost:8080 \
AGENTS.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to coding agents (Claude Code, Codex) and contributors.

Project overview

iMessage Max is an MCP (Model Context Protocol) server for iMessage, built for AI assistants to call.

The goal is to cut tool calls per user intent from 3-5 down to 1-2. Tools are shaped around what someone wants to know, not around the database tables.

Current implementation

The project is written in Swift and lives in /swift/. The old Python implementation is gone.

Build, install, run

After making code changes, build and deploy with:

cd swift
make install    # builds, signs, restarts launchd service, verifies health

Always run make install after code changes. It signs the binary, which is what keeps Full Disk Access from being revoked on every rebuild.

Other Makefile targets:

  • make test runs the full test suite (FILTER=ClassOrMethod for a subset)
  • make status checks process, version, signature, health
  • make logs tails the stderr log
  • make clean removes debug artifacts and clears logs
  • make setup-signing is one-time setup for a persistent code signing identity
  • make version checks the four version sites agree; make release-check runs everything that must pass before tagging (see docs/RELEASING.md)
  • make install-agent copies swift/launchd/local.imessage-max.plist into ~/Library/LaunchAgents/ (do not hand-write the plist)

The server runs as a launchd service (local.imessage-max) on port 8080, configured at ~/Library/LaunchAgents/local.imessage-max.plist. Install that agent with make install-agent. It auto-starts on login and auto-restarts on crash.

Connected via MCP Router as remote-streamable at http://127.0.0.1:8080. After restarting the service, MCP Router clients may need to reconnect (e.g. /mcp in Codex).

Manual build and run (without Makefile)

cd swift
swift build -c release

# stdio mode (for Codex Desktop)
./.build/release/imessage-max

# HTTP mode (for MCP Router, Inspector, etc.)
./.build/release/imessage-max --http --port 8080

# one-shot Contacts prompt, run from a terminal
./.build/release/imessage-max --request-contacts-access

Read the full file on GitHub · 335 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. today Changed · +13 lines · +359 tokens per session 24a325efd2ad
  2. 4d ago First seen · 322 lines · 3,339 tokens per session scan A 44e05e1be4b6

Subscribe to this mod's changes

imessage-max AGENTS.md is an instructions file published in the GitHub repository cyberpapiii/imessage-max (6 stars, last pushed today), licensed MIT. It adds 3,698 tokens to every session, about $0.0185 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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

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

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

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 · 4,345 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

next.js 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