A framework for writing personalised business-to-business outreach emails to people who have not asked to hear from you. It uses research, a clear benefit, and a specific next step to start a conversation.

Use it to research prospects and draft subject lines, cold emails, follow-ups, and calls to action for business prospecting.

It helps avoid generic bulk messages by matching the email to the recipient, their company, and a relevant problem or event.

cold-email — Skill for Claude Code by classicchins

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 classicchins/compounding-marketing --skill cold-email

Clone the repo

git clone --depth 1 https://github.com/classicchins/compounding-marketing

Made for: Claude Code.

Or install compounding-marketing, the plugin that ships this one along with the rest of its 39 skills, 16 commands.

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/classicchins/compounding-marketing/cold-email/github.svg)](https://agentmods.dev/skills/classicchins/compounding-marketing/cold-email)

Your own site

<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/cold-email"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/cold-email/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/classicchins/compounding-marketing/cold-email"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/cold-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,482 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	$0.00046	$0.03482
Opus 5.5	$0.00018	$0.01393
Sonnet 5.5	$0.00009	$0.00696
Haiku 4.5	$0.00005	$0.00348

Measured 2mo ago against content hash 755cef9f1ec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cold-email 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 2mo 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/SKILL.md · 360 lines

How it starts

The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cold Email Outreach

You are a B2B cold outreach specialist. Your goal is to write personalized, high-converting cold emails that start conversations with qualified prospects. You combine direct-response copywriting with deep prospect research to craft emails that feel one-to-one, not one-to-many.

Initial Assessment

Before writing any cold email, check for:

.agents/product-marketing-context.md — product details, positioning, audience. If missing, run cm-context first.
ICP research — who exactly are we targeting? Check for icp-research output.
Positioning — what makes us different? Check for positioning output.
Existing outreach — any prior cold email campaigns, reply rates, or learnings?

Ask the user for: target prospect role, company type, the specific pain point to lead with, and any known trigger events.

Prior Learnings Consulted

Before drafting subject lines or body copy, consult .agents/learnings/cold-email.md. Cold outreach is unusually high-signal — reply rate, positive-reply rate, and meeting-booked rate from prior campaigns are direct evidence of what works on this product's ICP. Apply those learnings before writing. The full consumption contract is defined in skills/_LEARNINGS_SCHEMA.md.

Sequence (do not skip):

Resolve the file. Look for .agents/learnings/cold-email.md. If it does not exist or has zero entries, state No prior learnings in this category yet — proceeding from first principles. and continue.
Parse the schema. Confirm YAML frontmatter and entries_count match. If malformed, surface and continue without applying.
Select up to 3 relevant entries in reverse-chronological order. For cold email, "relevant" means the entry's Implication would meaningfully change this campaign. Match against:
- Prospect role (founder, VP, IC, ops, eng) — what worked on this persona before?
- Company stage / segment (SMB vs. mid-market vs. enterprise; vertical)
- Framework chosen (PAS, BAB, Question-led, Trigger-event)
- Subject-line pattern (short / specific / question / referral / curiosity) and prior open rates
- Personalization tier (none / role / company / individual) and its measured lift
- Sequence shape (number of steps, day cadence, channels) and reply distribution
- CTA type (interest check, calendar link, soft ask, hard ask) and prior conversion

Read the full file on GitHub · 360 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.

2mo ago First seen · 360 lines · 46 tokens per session scan A 755cef9f1ec2

Subscribe to this mod's changes

cold-email is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 3,482 once invoked, about $0.0002 per session on Opus 5.5. 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.

Marketing and SEO Writing and docs

cold-email next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cold-emailclassicchins/compounding-marketing	Skill	8	5mo ago	MIT	A	46	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code