Free, read-only, runs in your own AI agent

Your cold email isn't a copy problem.
It's an infrastructure problem.

Point your agent at whatever you already run and get a plain-English deliverability audit in two minutes. It reads your real numbers, tells you exactly why you land in spam, and never touches a thing.

No card. No migration. 100% read-only, and nothing you connect is ever stored.

deliverability_report, smartlead 4 critical
Sent
40,000
Bounce
6.1%
Mailboxes
20
Avg / day
28
Send volume critical
2 mailboxes at ~28/day, the safe cold ceiling is ~15.
throttle & spread across more inboxes
Authentication critical
acme-sales.com is missing a DMARC record.
set DMARC (start p=none)
Placement critical
sam@ is landing in spam on a shared IP.
move to a dedicated IP
Warmup warning
3 mailboxes never warmed before real sending.
warm 2 to 4 weeks first
The blind spot

Everyone tweaks subject lines. Almost nobody checks the infrastructure.

Broken DMARC. Mailboxes quietly over-sending. Inboxes stuck on a shared IP. Accounts that never warmed up. That's what kills deliverability, and it's invisible from every dashboard you already look at.

You see the symptom

"Replies dropped." "We're in spam." "Bounces spiked." The dashboard shows the outcome, never the cause.

The Doctor sees the cause

It reads the real signals: send volume, auth records, warmup age, IP type, and grades them against what actually works.

And hands you the fix

Every finding comes with the concrete next step, and it tells you when the fix is free and takes five minutes.

What it can do

Connect a platform, and it goes to work.

Example: connect your Smartlead account and the Doctor runs this whole flow, entirely read-only. The same pattern works for any connected tool.

Step 1

Connect what you use

A domain, an inbox, or your sequencer. Read-only.

Step 2

Fetch all mailboxes

Every inbox on the account, with its domain and status.

Step 3

Read volume, patterns & logs

Daily send counts, ramp patterns, and activity per mailbox.

Step 4

Check health signals

Warmup age, SPF/DKIM/DMARC, shared vs dedicated IP, placement.

Step 5

Flag & monitor

Anything over the safe thresholds, with the exact fix.

Every mailboxPull the full inbox list on any connected account.
Volume & patternsDaily sends per mailbox, ramp shape, over-sending.
Activity & logsWhat is happening on each inbox, read in the moment.
Warmup stateWhether each mailbox is warmed, and for how long.
Auth & IPSPF, DKIM, DMARC, and shared vs dedicated IP.
PlacementInbox, spam, or promotions, plus bounce and blacklist signals.
The honest part

Stop paying deliverability consultants $100 to $500 an hour.

They bill you that to say what this tells you for free, the moment you connect Claude to your sequencer. Same diagnosis. Same fixes. No invoice.

Reads your stack

Sending tools and the infrastructure underneath.

It audits the platform you send from and the infrastructure your inboxes actually run on. No migration, no new account, just connect a key or point it at your domain.

Sending & sequencing
Smartlead logo Smartlead Instantly logo Instantly PlusVibe logo PlusVibe lemlist logo lemlist Woodpecker logo Woodpecker SendKit logo SendKit EmailBison logo EmailBison
Email infrastructure
InboxKit logo InboxKit Zapmail logo Zapmail Icemail logo Icemail

Plus any mailbox over IMAP and any domain over DNS, no API key needed. New platform? One JSON file adds it, and the adaptive mapper learns the response shape on first contact.

How it works

Diagnose in four steps.

01

Connect what you use

Point it at a domain, an inbox, or a platform you already send from. It picks up your domains and runs the whole audit itself, read-only. You never touch a command.

02

It teaches itself your API

Every platform returns a different shape. The adaptive mapper reads the real response, figures out the fields, and caches it, so it works even on APIs it has never seen.

03

Grade against what works

~15 sends per mailbox per day, bounce under 3%, warmup 2 to 4 weeks, SPF/DKIM/DMARC, dedicated vs shared IP, the thresholds practitioners actually use.

04

Get a plain-English audit

Severity-ranked findings, each with the exact fix, and an honest "you're fine" when you are.

Read-only & private by design

Nothing changed. Nothing stored.

It runs entirely inside your own agent. There is no server on our side to send your data to. Whatever it reads is used for the audit in the moment, then it is gone.

  • We never receive or store your data. There is no backend, no database, no logs of your inboxes or lists, nothing to leak.
  • Whatever it reads is destroyed after the audit. The data is analyzed on the spot and discarded, nothing persists once it is done.
  • Every connector is GET-only, so it cannot send, delete, change a setting, or spend a cent.
  • Your credentials stay in your environment, never written to disk, never printed into a report.
From diagnosis to fixed

Found problems? Fix them fast.

We navigate you to the right set of tools and products for any kind of issue, matched to the exact problems the audit identifies.

Pinpoint the cause

Each finding names the real root cause, auth, warmup, volume, IP, or list hygiene, not just the symptom.

Match the right fix

For every issue, we point you to the tool or product that solves it best, whichever fits your stack.

Fix it, free or paid

Some fixes are free and take five minutes. Where a product genuinely helps, we say so, and only there.

Get started in 30 seconds

Two ways to run it.

No signup. You never run a command. Connect what you use and it does the rest.

In Claude Code

Install once, then just ask.

Paste this one-time install into Claude Code, on desktop or CLI.

git clone https://github.com/sakshamj15/cold-email-doctor ~/.claude/skills/cold-email-doctor

Then just say:

Audit my cold email setup
In Claude web

Download, upload, ask.

Download the skill file, upload it to a new chat at claude.ai, and let Claude run the audit from there.

# after uploading the file, say: Use the Cold-Email Doctor instructions I just uploaded, then audit my cold email setup.
Stop guessing

Find out exactly why you're in spam.

Free, open-source, and read-only. Run it on a live account without a second thought.