What is mailbridge CLAUDE.md?

A set of project instructions for mailbridge, a personal email tool that connects an AI assistant to mailboxes using standard IMAP and SMTP protocols. IMAP is used to read and manage mail, while SMTP is used to send it.

Use it when developing mailbridge features such as reading, searching, organising, drafting, or sending email, and when building or testing the project.

It gives development and language rules for keeping the mail tool's code, documentation, commands, and namespace consistent.

How marcocavanna/mailbridge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to marcocavanna/mailbridge. 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/marcocavanna/mailbridge/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/marcocavanna/mailbridge

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/marcocavanna/mailbridge/claude-md/github.svg)](https://agentmods.dev/instructions/marcocavanna/mailbridge/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/marcocavanna/mailbridge/claude-md"><img src="https://agentmods.dev/badge/instructions/marcocavanna/mailbridge/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/marcocavanna/mailbridge/claude-md"><img src="https://agentmods.dev/badge/instructions/marcocavanna/mailbridge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,102 This file is loaded in full into every session.

When invoked 2,102 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.

Model	Per session	Once invoked
Fable 5.1	$0.02102	$0.02102
Opus 5.5	$0.00841	$0.00841
Sonnet 5.5	$0.00420	$0.00420
Haiku 4.5	$0.00210	$0.00210

Measured 2mo ago against content hash 4c544cc9b663, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mailbridge 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 2mo 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 · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mailbridge

An MCP server that gives an AI assistant access to IMAP/SMTP mailboxes: reading, searching, organizing, drafting and sending. No proprietary provider in the middle — plain IMAP and SMTP only.

A personal project by Marco Cavanna, not a product and not company software. No identifier, namespace or reference should tie it to an organization — the namespace is com.marcocavanna.*.

Language: English everywhere — code, comments, user-facing strings, documentation, commit messages. The exceptions are data rather than prose, and both are marked in place: localized folder names in src/imap/folders.ts and the deliberately non-ASCII test fixture.

Commands

Command	What it does
`pnpm build`	Cleans `dist/` and compiles. The clean matters: without it, renamed or split modules leave dead files behind that would ship in the published package
`pnpm typecheck`	`tsc --noEmit` over sources, tests and config
`pnpm test`	Vitest, only the tests that earn their place
`pnpm dev`	MCP server in watch mode over stdio
`pnpm cli`	The CLI (`mailbridge`) — bare, it opens the menu
`pnpm cli:dev`	The CLI from sources, through tsx
`pnpm serve`	MCP server from `dist/`

The CLI is one single entry: mailbridge. Subcommands account (list/status/test/add/edit/remove), sync, schedule (status/enable/disable/run/logs) and serve. Launched bare it opens an interactive menu; with arguments it is non-interactive, which is the form launchd and scripts need — both modes call the same functions in src/cli/*-actions.ts, never duplicated logic.

Architecture

Two halves that only meet through the search layer:

MCP server (src/) — speaks IMAP and SMTP live. Source of truth for writes.
Local mirror (mbsync → Maildir in ~/Mail/<account>/, notmuch index) — source of truth for search, because IMAP SEARCH is slow and implemented differently by every provider. The mirror is a cache: it holds nothing that cannot be rebuilt from the server.

Read the full file on GitHub · 154 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.

2mo ago First seen · 154 lines · 2,102 tokens per session scan A 4c544cc9b663

Subscribe to this mod's changes

mailbridge CLAUDE.md is an instructions file published in the GitHub repository marcocavanna/mailbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,102 tokens to every session, about $0.0084 per session on Opus 5.5. 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.

Building agents claude cli email imap isync keychain

mailbridge CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mailbridge CLAUDE.mdmarcocavanna/mailbridge	Instructions file	0	1mo ago	MIT	A	2,102	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mailbridge: Instructions file for Claude Code