A writing workflow for creating personalized cold emails and outreach messages in a specified person's style. Cold outreach means contacting someone who does not already know the sender.

Use it for job inquiries, client or partnership outreach, investor messages, podcast pitches, networking, referrals, follow-ups, and cold direct messages.

It helps produce short, relevant messages without inventing familiarity, personal details, results, or attribution. It also adapts the message to the purpose and communication channel.

cold-email — Skill for Claude Code and Codex by emSoumik

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 emSoumik/cold-mail-agent-mcp --skill content

Clone the repo

git clone --depth 1 https://github.com/emSoumik/cold-mail-agent-mcp

Made for: Claude Code, Codex.

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/emsoumik/cold-mail-agent-mcp/content/github.svg)](https://agentmods.dev/skills/emsoumik/cold-mail-agent-mcp/content)

Your own site

<a href="https://agentmods.dev/skills/emsoumik/cold-mail-agent-mcp/content"><img src="https://agentmods.dev/badge/skills/emsoumik/cold-mail-agent-mcp/content/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/emsoumik/cold-mail-agent-mcp/content"><img src="https://agentmods.dev/badge/skills/emsoumik/cold-mail-agent-mcp/content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 824 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	$0.00057	$0.00824
Opus 5.5	$0.00023	$0.00330
Sonnet 5.5	$0.00011	$0.00165
Haiku 4.5	$0.00006	$0.00082

Measured 2mo ago against content hash 158414c8fc08, 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.

content/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cold Email

Write the shortest truthful message that gives one specific person a reason to care and an easy way to reply. Preserve the voice established by the WhatsApp-derived Hall of Fame corpus. Do not replace it with generic sales-copy advice.

Source hierarchy

Use these sources in order:

User-supplied preferences and verified recipient and sender facts for this message.
references/style-corpus.md for voice and proven patterns.
The matching workflow references below.

This public MCP does not include private memory or lead records. Apply those only when the connected client supplies them.

Never invent familiarity, attribution, numbers, results, or personalization. If a reference is unavailable, do not pretend to have read it.

References

references/style-corpus.md: read first to calibrate voice and ambition.
references/channels-and-followups.md: read for email, LinkedIn, X, Instagram, WhatsApp, follow-up, or re-engagement behavior.
references/use-cases.md: read only the matching use case.
references/voices.md: choose the recipient-appropriate register.
references/writing-engine.md: draft the subject and message.
references/humanizer.md: required final anti-slop and readability pass.

Workflow

1. Ground the message

Apply any preferences the connected client provides. This public MCP cannot access private lead records.

Identify internally:

recipient, channel, and relationship stage;
one verified detail that explains why this person;
why Soumik is writing now;
the minimum proof needed to trust him;
one desired response;
any work, sample, idea, or useful artifact Soumik can show first.

Ask only for information that materially blocks a truthful draft. If enough context exists, proceed without an intake questionnaire. Research links when tools are available. Distinguish observed facts from inferences.

2. Choose the interaction

Read channels-and-followups.md, then choose the use case and voice. A DM starts a conversation; an email usually carries more context. The first contact should normally earn the next reply, not force the final decision.

Read the full file on GitHub · 81 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 81 lines · 57 tokens per session scan A 158414c8fc08

Subscribe to this mod's changes

cold-email is a skill published in the GitHub repository emSoumik/cold-mail-agent-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 824 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 ai-writing cloudflare-workers cold-email mcp model-context-protocol

cold-email next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cold-emailemSoumik/cold-mail-agent-mcp	Skill	0	3mo ago	MIT	A	57	Claude Code, Codex
add-providercyanheads/mcp-ts-core	Skill	153	today	Apache-2.0	A	47	Claude Code, Codex
add-exportcyanheads/mcp-ts-core	Skill	153	today	Apache-2.0	A	50	Claude Code, Codex
contextSupa-Media/context	Skill	3	today	MIT	A	64	Claude Code
how-we-define-chaosSupa-Media/context	Skill	3	today	MIT	A	61	Claude Code
syncSupa-Media/context	Skill	3	today	MIT	A	52	Claude Code
context-saveSupa-Media/context	Skill	3	today	MIT	A	36	Claude Code