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.
npx skills add cmj-hub/claude-cold-email --skill cold-email-craftgit clone --depth 1 https://github.com/cmj-hub/claude-cold-emailWrote 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.
[](https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-craft)<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-craft"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-craft/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.
<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-craft"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00084 | $0.01076 |
| Opus 5 | $0.00042 | $0.00538 |
| Sonnet 5 | $0.00017 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
cold-email-craft 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email Craft — sub-skill
Drafts the actual email(s). Loaded by cold-email when the user wants
to write or sequence outreach.
Activation
The main cold-email skill routes here when the user says any of:
- "Write a cold email to..."
- "Draft an outreach to..."
- "Build a 3-touch sequence for..."
- "Follow-up to at "
- "Rewrite this cold email"
Workflow
1. Gather the six framework variables
Required:
| Variable | Source | Ask if missing |
|---|---|---|
firstName |
User-provided | "What's the recipient's first name?" |
role |
User-provided or LinkedIn | "What's their role?" |
company |
User-provided | "Which company?" |
signal |
Public, recent, verifiable | "What did they just do publicly? (Job post, funding, launch, hire, content)" |
pain |
What the signal implies operationally | "What does that signal imply about their pipeline / motion / stack?" |
evp |
One-line value prop | "What's your one-line EVP for this segment? (≤22 words)" |
senderName |
User | "Who are you signing as?" |
Do not fabricate. If any are missing, ask. Never assume role, company, or signal — wrong assumptions kill cold email.
2. Validate the framework
Before generating, validate:
- Signal is something they DID, not who they ARE. If user provides "VP of Marketing at Series B SaaS", push back: "That's a demographic, not a signal. What did they post/announce/ship in the last 30 days?"
- Pain uses their language, not yours. No "synergy" / "optimize" / "leverage".
- EVP is ≤22 words, has one specific outcome, one tradeoff.
3. Generate
Use the canonical template from references/copy-frameworks.md:
Subject: <see references/subject-line-patterns.md>
{firstName} —
<Quote the signal verbatim, 1 sentence.>
<Pain in their language, 1 sentence.>
<EVP, ≤22 words.>
<Binary CTA, time-bound.>
— {senderName}
4. Self-check against constraints
After generating, verify:
- Total word count <90
- No banned openers ("Hope you're well", "Just wanted to")
- No banned closes ("Let me know your thoughts", "Happy to chat")
- Binary CTA (yes/no answerable)
- Signal is quoted verbatim (not paraphrased)
- Pain uses recipient's language
- EVP ≤22 words
- Subject ≤7 words, no clickbait
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.
- 2d ago Changed 8f0e9beec709
- 11d ago First seen · 127 lines · 84 tokens per session scan A 8e6723dbeb2f
cold-email-craft is a skill published in the GitHub repository cmj-hub/claude-cold-email (2 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,076 once invoked, about $0.0004 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.
Other skills, from other repositories
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
graphify
Knowledge graph engine for B2B sales intelligence. Builds queryable graphs from product catalogs, customer conversations, and market research. Powered by graphify.
telegram-toolkit
Register these commands with @BotFather using /setcommands.
lead-discovery
AI-driven lead discovery for B2B export. Searches web for potential buyers matching ICP, evaluates fit, and creates CRM records for follow-up.
b2b-sdr-agent
Open-source B2B AI SDR template. 7-layer context system with 10-stage sales pipeline, 4-layer anti-amnesia memory, 14 automated pipeline checks, WhatsApp IP isolation, multi-channel (WhatsApp+Telegram+Email). Built on OpenClaw.
sdr-humanizer
Transform AI-generated sales messages into natural, human-like conversations that build trust and rapport.