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.
curl -O https://raw.githubusercontent.com/marcocavanna/mailbridge/main/CLAUDE.mdgit clone --depth 1 https://github.com/marcocavanna/mailbridgeWrote 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.
[](https://agentmods.dev/instructions/marcocavanna/mailbridge/claude-md)<a href="https://agentmods.dev/instructions/marcocavanna/mailbridge/claude-md"><img src="https://agentmods.dev/badge/instructions/marcocavanna/mailbridge/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01051 | $0.01051 |
| Sonnet 5 | $0.00420 | $0.00420 |
| Haiku 4.5 | $0.00210 | $0.00210 |
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 7d 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.
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>/,notmuchindex) — source of truth for search, becauseIMAP SEARCHis slow and implemented differently by every provider. The mirror is a cache: it holds nothing that cannot be rebuilt from the server.
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.
- 7d ago First seen · 154 lines · 2,102 tokens per session scan A 4c544cc9b663
mailbridge CLAUDE.md is an instructions file published in the GitHub repository marcocavanna/mailbridge (0 stars, last pushed 17d ago), licensed MIT. It adds 2,102 tokens to every session, about $0.0105 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.
Other instructions, from other repositories
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.
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).
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.
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.
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).
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.