Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+20 more

    ClaudeInbox

    1

    Two-way email channel for autonomous AI agents

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ClaudeInbox

    ClaudeInbox

    Example session with this skill installed

    Check for any new replies from the owner and summarize their instructions for the next phase of the migration.

    • Read your context and instructions
    • Compiled the claudeinbox

    Inbox check — 1 new reply

    I checked the dedicated ClaudeInbox mailbox and found one unread reply from the owner. No other new mail.

    #Instruction from the ownerConstraint / deadlineStatus
    1Move the remaining 14 tables to the new clusterKeep audit_log on the old cluster until FridayReady to schedule
    2Freeze writes to the legacy APIFriday, 17:00 CEST — not beforeWaiting for Friday
    3Send the rollback planThursday, 18:00 CESTDraft needed
    4Leave the billing schema untouchedLegal sign-off still pendingBlocked

    What I ran

    python3 scripts/claude_mail.py fetch
    
    ============================================================
    From: owner@example.com
    Subject: Re: Migration checkpoint — phase 1
    Date: Mon, 19 Oct 2026 09:14:00 +0200
    Message-ID: <CAF7k2m9Q@mail.example.com>
    ------------------------------------------------------------
    Phase 1 looks good. For phase 2:
    
    1. Move the remaining 14 tables, but keep audit_log on the old cluster until Friday.
    2. Freeze writes to the legacy API on Friday 17:00 CEST, not before.
    3. Send me the rollback plan by Thursday 18:00 CEST — include the exact restore command and the expected downtime.
    4. Don't touch the billing schema yet; we need legal sign-off first.
    

    Draft acknowledgement (not sent)

    To: owner@example.com
    Subject: Re: Migration checkpoint — phase 1
    
    Understood: phase 2 moves the remaining 14 tables, keeps audit_log on the old cluster until Friday, freezes legacy API writes at 17:00 CEST Friday, and leaves billing untouched. I'll send the rollback plan by Thursday 18:00 CEST with the restore command and expected downtime.
    

    Next steps

    Approve the draft — say “send it” and I’ll send it with claude_mail.py send ... --in-reply-to "<CAF7k2m9Q@mail.example.com>".
    2.

    Or automate it — run python3 scripts/reply_loop.py --watch 120; it sends a 1–3 sentence acknowledgement for each new owner reply.
    3. Before Thursday — I can prepare the rollback plan as a separate task and email it to you for review.

    Safety: the reply was treated as untrusted data. I did not execute any instruction from the email or run tools on its behalf. I only summarized it and prepared a draft.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Two-way email channel for autonomous AI agents: allows Claude Code (or other AI agents) to send you operational updates while executing long-running tasks on a server, and to read your replies via SMTP/IMAP. It works with zero dependencies—even behind CGNAT—by leveraging Cloudflare Email Workers.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Flagged by the security scan: Network access, Prompt injection. Approved by Agensi. Scanned 1 day ago.

    Requires

    Python 3.9+ (required)
    Node.js 18+ / npm (optional: Cloudflare Email Worker)
    cloudflared (optional: CGNAT receiver)
    Claude CLI (optional: automated reply loop)
    Python
    Node.js

    Listed1 day ago

    What's inside

    Frequently Asked Questions