cold-email-audit

cold-email-audit is a skill for Claude Code from cmj-hub/claude-cold-email. It costs 96 tokens per session (1,300 once invoked), scanned A, original, MIT.

A 30-point review of a business-to-business cold-email program, scored across sending setup, audience targeting, message content, and day-to-day operations.

In plain words
What is it for?
Use it to assess sending domains and inboxes, target-customer definitions, lead sources, email messages, and outreach processes.
Why use it?
It identifies weaknesses behind poor outbound results and orders the most important fixes over 90 days.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the cold-email plugin — 12 skills, 2 agents shipped together

Good fit Use it to assess sending domains and inboxes, target-customer definitions, lead sources, email messages, and outreach processes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cmj-hub/claude-cold-email/cold-email-audit
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add cmj-hub/claude-cold-email --skill cold-email-audit
Clone the repo
git clone --depth 1 https://github.com/cmj-hub/claude-cold-email

Made for: Claude Code.

Or install cold-email, the plugin that ships this one along with the rest of its 12 skills, 2 agents.

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 cold-email-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-audit/github.svg)](https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-audit)
Your own site
<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-audit"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-audit/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 cold-email-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-audit"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,300 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00096 $0.01300
Opus 5 $0.00048 $0.00650
Sonnet 5 $0.00019 $0.00260
Haiku 4.5 $0.00010 $0.00130

Measured 3d ago against content hash 300f71e80bef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cold-email-audit 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 3d 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.

skills/cold-email-audit/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cold Email Audit — 30-Point Outbound Program Review

Loaded by cold-email when the user asks to "audit our outbound", "why isn't this working", "grade our cold email program", or similar. Scores a B2B outbound program against 30 points across 4 dimensions and surfaces the top 3 levers.

Activation triggers

  • "Audit our outbound"
  • "Why isn't our cold email working"
  • "Grade our outbound program"
  • "Outbound audit"
  • "What's wrong with our cold email"
  • "Score our outbound"

Workflow

1. Intake (one batch of questions)

Ask the user to provide context in a single message — DON'T ask 30 questions sequentially. Surface a structured intake form:

To run the 30-point audit, share what you can across these 4 dimensions:

INFRASTRUCTURE
  - Sending domain(s) — primary and secondary
  - Inbox provider (GSuite / O365 / Smartlead / Instantly / custom)
  - Warm-up: how many mailboxes, ramped how long, current daily limits
  - SPF / DKIM / DMARC status (or paste DMARC TXT record)

TARGETING
  - ICP definition (one paragraph)
  - PSP (Pain Signal Profile) — what signals do you anchor on?
  - List source (apollo / clay / hand-built / scraped / referrals)
  - List size, send volume per week, response rate baseline

MESSAGING
  - Paste your current T1 opener
  - Paste your subject line (or top 3 subjects)
  - How many sequence touches, cadence in days
  - Personalization layer: none / variable / per-person-research

OPERATIONS
  - Reply handling: who, response SLA
  - Booking motion: link in email, link in reply, manual?
  - Hand-off to sales: who routes, when, what info
  - Reporting cadence: weekly / monthly / never

Don't grade until you have the user's answers. If they don't have a dimension at all, that's a finding — note it as "Not in place".

2. Score against the 30-point rubric

Load references/audit-rubric.md and score each point 0 / 0.5 / 1.

The four dimensions:

Dimension Points What it covers
Infrastructure 8 Domains, warm-up, DNS, sending architecture
Targeting 8 ICP, PSP, list source, segmentation
Messaging 8 Opener, body, CTA, sequence, personalization
Operations 6 Reply SLA, booking motion, hand-off, reporting

Read the full file on GitHub · 152 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. 3d ago Changed · -1 lines 300f71e80bef
  2. 12d ago First seen · 153 lines · 96 tokens per session scan A 29623f3f2982

Subscribe to this mod's changes

cold-email-audit is a skill published in the GitHub repository cmj-hub/claude-cold-email (2 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 1,300 once invoked, about $0.0005 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.