What is cold-email-spam-lint?

A rule-based scanner for unsolicited business-email drafts that checks wording and layout for signs commonly associated with spam. It returns a 0–100 delivery-risk score and points to specific problems.

Use it to review an email subject and body, find spam-trigger words, check formatting, and receive line-by-line warnings.

It catches attention-grabbing language, excessive links or images, fake reply subjects, capital letters, and other issues before an email is sent. This helps reduce avoidable delivery risks.

cold-email-spam-lint — Skill for Claude Code by cmj-hub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/cmj-hub/claude-cold-email

agentmods

npx agentmods add skills/cmj-hub/claude-cold-email/cold-email-spam-lint

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-spam-lint/github.svg)](https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-spam-lint)

Your own site

<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-spam-lint"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-spam-lint/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/skills/cmj-hub/claude-cold-email/cold-email-spam-lint"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-spam-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,062 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.

Model	Per session	Once invoked
Fable 5.1	$0.00106	$0.01062
Opus 5	$0.00053	$0.00531
Sonnet 5	$0.00021	$0.00212
Haiku 4.5	$0.00011	$0.00106

Measured 3d ago against content hash 41b53501adc4, 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-spam-lint 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-spam-lint/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cold Email Spam Lint — deterministic spam-trigger scanner

A real scanner, not vibes. Backs onto scripts/spam_word_lint.py for deterministic scoring against a maintained 200-word spam-trigger lexicon.

Activation

Loaded by:

cold-email-craft — final self-check before delivering a draft
cold-email-weekly-rhythm — Wednesday ship-day batch lint
User invocation: "spam-lint this email"

How it scores

Each draft gets a 0-100 deliverability-risk score across 6 axes:

Axis	Weight	What it catches
Spam-trigger words	25	"URGENT", "ACT NOW", "Limited time", "free money", "guaranteed" — 200+ patterns
ALL CAPS	15	Subject or body lines in caps
Emoji	10	Emoji in subject (high B2B spam signal)
Clickbait patterns	15	"You won't believe...", "This one trick...", "Doctors hate..."
Fake threading	10	"Re:" / "Fwd:" in subject when there's no prior thread
Link / image ratio	25	>1 link or image-to-text >40% — B2B threshold

Output:

# Spam Lint — <subject>

## Deliverability risk score: <0-100>/100

| Axis | Score | Issues |
|---|---|---|
| Spam-trigger words | <0-25>/25 | Found: <words> |
| ALL CAPS | <0-15>/15 | Caps in: <lines> |
| Emoji | <0-10>/10 | Subject has 🚀 |
| Clickbait | <0-15>/15 | "You won't believe..." in line 2 |
| Fake threading | <0-10>/10 | Subject starts with "Re:" |
| Link/image ratio | <0-25>/25 | 3 links found |

## Line-by-line flags

[Line 1 — Subject] "Re: URGENT — pipeline update 🚀"
  - Fake threading: subject begins with "Re:"
  - Spam-trigger: "URGENT"
  - ALL CAPS in subject
  - Emoji in subject

[Line 5 — Body] "You won't believe what we shipped this quarter."
  - Clickbait pattern: "You won't believe"

## Verdict
| Score | Verdict |
|---|---|
| 90-100 | Ship |
| 75-89 | Ship after fixes — flagged items have alternatives below |
| 60-74 | Rewrite — too many deliverability flags |
| <60 | Do not send — will land in spam |

Implementation

The skill shells out to a Python script:

Read the full file on GitHub · 119 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.

3d ago Changed 41b53501adc4
12d ago First seen · 119 lines · 106 tokens per session scan A 3f335ce7a837

Subscribe to this mod's changes

cold-email-spam-lint is a skill published in the GitHub repository cmj-hub/claude-cold-email (2 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 1,062 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.

Claude Code Marketing and SEO agent-skills b2b cold-email outbound spam-detection

cold-email-spam-lint

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Cold Email Spam Lint — deterministic spam-trigger scanner

Activation

How it scores

Implementation

What this file has done since we first saw it

Other skills, from other repositories

afrexai-lead-hunter

graphify

telegram-toolkit

lead-discovery

b2b-sdr-agent

sdr-humanizer