agentmods.dev

airmail-mcp: Instructions file for Claude Code

CLAUDE.md

airmail-mcp CLAUDE.md is an instructions file for Claude Code from Airmail/airmail-mcp. It costs 891 tokens per session, scanned A, original, MIT.

Repository instructions for a Node.js bridge that passes messages between AI coding tools and Airmail's local Swift server. The bridge handles communication, while the Swift application contains the tool logic.

In plain words
What is it for?
Use them when building the TypeScript bridge, syncing tools from Swift source, running the project, or preparing a release.
Why use it?
They explain the unusual connection design, project files, build commands, release process, and how tool definitions are kept in sync.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is Airmail/airmail-mcp's own configuration. It tells Claude Code how to work on airmail-mcp 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 airmail-mcp configures →

not rated 6repo 1mo ago A scan 891 tokens original MIT
View source ↗ Airmail/airmail-mcp airmailapp.com
Reuse

Borrowing it

Nothing to install: this file belongs to Airmail/airmail-mcp. 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/Airmail/airmail-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Airmail/airmail-mcp

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 airmail-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/airmail/airmail-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/airmail/airmail-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/airmail/airmail-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/airmail/airmail-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for airmail-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/airmail/airmail-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/airmail/airmail-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 891 This file is loaded in full into every session.
When invoked 891 The same file — it is already loaded in full.
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 $0.00891 $0.00891
Opus 5 $0.00445 $0.00445
Sonnet 5 $0.00178 $0.00178
Haiku 4.5 $0.00089 $0.00089

Measured 9d ago against content hash 354ff7fe9e6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

airmail-mcp 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 9d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 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.

Overview

Node.js stdio bridge that forwards JSON-RPC between AI clients (Claude, Gemini, Codex) and Airmail's native MCP server on localhost:9876. All tool logic lives in Airmail's Swift code — this package is just the transport layer.

Architecture

AI Client ←stdio→ src/index.ts (Node.js) ←HTTP→ Airmail.app (localhost:9876)
  • src/index.ts — the bridge. Uses raw TCP sockets (not http module) because Airmail's NWListener closes connections immediately after sending.
  • scripts/sync-tools.mjs — parses Swift source files to extract tool definitions into manifest.json. By default it reads ../PostinoNG191/PostinoNG/SwiftCore/MCP; pass a path argument or set AIRMAIL_MCP_SWIFT_DIR for a different checkout layout.
  • manifest.json — tool definitions used by the MCPB extension format.

Commands

npm run build          # compile TypeScript → dist/
npm run watch          # tsc --watch
npm run sync-tools     # sync tool defs from Swift source → manifest.json
./scripts/release.sh [patch|minor|major]   # full release; must be on main branch

There is no test suite and no linter configured. Don't invent npm test / npm run lint invocations.

Release flow

./scripts/release.sh [patch|minor|major] does everything:

  1. Syncs tools from Swift source
  2. Builds TypeScript
  3. Bumps version in package.json
  4. Commits and pushes to main
  5. Creates a GitHub Release
  6. GitHub Actions publishes to npm via OIDC (no token needed)

Tool architecture (Swift side)

Tools are statically compiled into Airmail's binary. There is no plugin system or config file — adding a tool requires Swift code changes.

Two independent access control layers:

  • Capability groups — control visibility in tools/list. Toggled at runtime via manage_capabilities. Disabling a group hides tools but does NOT block execution.
  • Permissions — control execution. Three levels: allow (immediate), ask (macOS alert), blocked (rejected). Configured in Airmail Preferences → MCP.

Read the full file on GitHub · 66 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. 9d ago First seen · 66 lines · 891 tokens per session scan A 354ff7fe9e6a

Subscribe to this mod's changes

airmail-mcp CLAUDE.md is an instructions file published in the GitHub repository Airmail/airmail-mcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 891 tokens to every session, about $0.0045 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.

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 · 5,153 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens