What is messages CLAUDE.md?

Repository instructions for cardmagic/messages, a command-line and MCP tool for searching Apple Messages stored on a Mac. They describe its commands, TypeScript structure, indexing process, and fuzzy search.

Use them to build, type-check, lint, test, install, or modify the message indexer, searcher, command-line interface, or MCP server.

They help coding agents understand how the project is organised and which commands to run when changing or checking it.

messages CLAUDE.md — Instructions file by cardmagic

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/cardmagic/messages/claude-md

Clone the repo

git clone --depth 1 https://github.com/cardmagic/messages

Per session 653 This file is loaded in full into every session.

When invoked 653 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.

Model	Per session	Once invoked
Fable 5	$0.00653	$0.00653
Opus 5	$0.00327	$0.00327
Sonnet 5	$0.00131	$0.00131
Haiku 4.5	$0.00065	$0.00065

Measured 3d ago against content hash 32c4c667380b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

messages 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 3d 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 · 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.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

pnpm build          # Compile TypeScript to dist/
pnpm dev            # Watch mode for development
pnpm typecheck      # Type check without emitting
pnpm lint           # Run oxlint
pnpm test           # Run tests
pnpm test:watch     # Run tests in watch mode

make install        # Build and link globally
make clean          # Remove dist/ and node_modules/

Architecture

Dual-mode CLI/MCP tool for searching Apple Messages:

src/
├── index.ts      # Entry point - routes to CLI or MCP mode based on --mcp flag
├── cli.ts        # Commander-based CLI (search, index, stats commands)
├── mcp.ts        # MCP server exposing tools via @modelcontextprotocol/sdk
├── indexer.ts    # Builds search indexes from ~/Library/Messages/chat.db
├── searcher.ts   # Queries indexes with fuzzy matching via MiniSearch
├── formatter.ts  # Terminal output formatting with chalk
└── types.ts      # Shared types and Apple date conversion utilities

Data flow:

indexer.ts reads Apple's chat.db SQLite database and AddressBook for contact resolution
Creates two indexes in ~/.messages/: FTS5 SQLite for exact search, MiniSearch JSON for fuzzy matching
searcher.ts queries MiniSearch for fuzzy results, then fetches context from SQLite

Key dependencies:

better-sqlite3: Read Apple Messages DB and create FTS5 index
minisearch: Fuzzy search with typo tolerance
node-typedstream: Extract text from NSAttributedString blobs (messages with null text field)
@modelcontextprotocol/sdk: MCP server for Claude Code integration

Claude Code Plugin

This repo is also a Claude Code plugin with skills and slash commands:

.claude-plugin/
├── plugin.json       # Plugin manifest
└── marketplace.json  # Marketplace definition (name: cardmagic)

skills/messages/SKILL.md    # Auto-invoked skill for message queries
commands/
├── search.md               # /messages:search slash command
└── browse.md               # /messages:browse slash command

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.

3d ago First seen · 75 lines · 653 tokens per session scan A 32c4c667380b

Subscribe to this mod's changes

messages CLAUDE.md is an instructions file published in the GitHub repository cardmagic/messages (19 stars, last pushed 7d ago), licensed MIT. It adds 653 tokens to every session, about $0.0033 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.

Databases Languages TypeScript

messages CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Commands

Architecture

Claude Code Plugin

What this file has done since we first saw it

Other instructions, from other repositories

prisma-class-generator CLAUDE.md

read-only-local-postgres-mcp-server CLAUDE.md

baerly-storage AGENTS.md

mcp-postgres CLAUDE.md

tevm CLAUDE.md

moss AGENTS.md