cold-email-onboarding

cold-email-onboarding is a skill for Claude Code from cmj-hub/claude-cold-email. It costs 91 tokens per session (2,031 once invoked), scanned A, original, MIT.

A first-run setup skill for the cold-email writing pack. It guides the operator in creating brand settings and a voice guide, including the target audience, positioning, tone, stories, and email infrastructure.

In plain words
What is it for?
Setting up or updating cold-email brand configuration, defining writing preferences and banned phrases, recording proof stories, and documenting sending infrastructure and operations.
Why use it?
It supplies the business and writing context needed for outreach that is specific rather than generic.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md.

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

Good fit Setting up or updating cold-email brand configuration, defining writing preferences and banned phrases, recording proof stories, and documenting sending infrastructure and operations.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-onboarding"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,031 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 $0.00091 $0.02031
Opus 5 $0.00046 $0.01015
Sonnet 5 $0.00018 $0.00406
Haiku 4.5 $0.00009 $0.00203

Measured 2d ago against content hash 47f75a6573a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cold-email-onboarding 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 2d 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-onboarding/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cold Email Onboarding — first-run setup

Walks the operator through 10 minutes of setup that makes every downstream output 10x more useful than generic framework prose.

Activation

Loaded automatically by cold-email (the orchestrator) on first invocation when brand-config.json and/or SOUL.md are missing from the project root.

Also user-invocable on demand:

  • "Set up brand config"
  • "Configure my voice"
  • "Re-run cold-email onboarding"
  • "Update brand-config"

Why this exists

Generic cold-email output is worse than no output. The framework is generic — your ICP + PSP + voice are specific. Without those, the skill produces vibes-emails that look like every other AI-generated cold email.

This onboarding sub-skill captures the operator's:

  1. ICP precision (specific segment, exclusion criteria)
  2. PSP (signal anchors → felt pain → vocabulary)
  3. EVP (Schwartz tier + the 22-word line + proof)
  4. Voice (phrases used + phrases banned + tone settings)
  5. Stories (case-study reservoir to pull from)
  6. Infrastructure (domain, inbox provider, deliverability state)
  7. Operations (weekly cadence, reply routing, experiment log)

Output: brand-config.json + SOUL.md at the project root, both filled in.

Workflow

Step 0 — Detect prior state

# Pseudo-code logic
exists_brand = file_exists("brand-config.json")
exists_soul = file_exists("SOUL.md")

if exists_brand and exists_soul:
    ask: "Both files exist. Refresh them, or skip onboarding?"
elif exists_brand:
    "I see brand-config.json but no SOUL.md. Let's add the voice piece."
elif exists_soul:
    "I see SOUL.md but no brand-config.json. Let's add the config."
else:
    "Welcome. ~10 minute setup. Ready?"

Step 1 — Operator + company

Ask in one batch:

First, the basics:

1. Your name (for the sign-off line)?
2. Your title?
3. Your company?
4. Your calendar / booking link?

Save to brand-config.operator.

Step 2 — ICP precision check

Now your ICP. Be specific. "B2B SaaS" is too broad.

Tell me:
1. The 1-sentence segment (with stage / size / motion / region)
2. The 3 role-titles you target most
3. The 3 exclusion criteria (who you DON'T sell to)

If you're unsure on any of these, that's a signal you need to
sharpen ICP before launching outreach. Let me know if you want to
talk through it, or use a placeholder for now.

Read the full file on GitHub · 262 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. 2d ago Changed 47f75a6573a7
  2. 11d ago First seen · 262 lines · 91 tokens per session scan A 469db5c9df80

Subscribe to this mod's changes

cold-email-onboarding is a skill published in the GitHub repository cmj-hub/claude-cold-email (2 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 2,031 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.