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 TheCraigHewitt/sales-skills --skill cold-emailgit clone --depth 1 https://github.com/TheCraigHewitt/sales-skillsWrote 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/thecraighewitt/sales-skills/cold-email)<a href="https://agentmods.dev/skills/thecraighewitt/sales-skills/cold-email"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/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.
<a href="https://agentmods.dev/skills/thecraighewitt/sales-skills/cold-email"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/cold-email.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 | $0.00134 | $0.05031 |
| Opus 5 | $0.00067 | $0.02516 |
| Sonnet 5 | $0.00027 | $0.01006 |
| Haiku 4.5 | $0.00013 | $0.00503 |
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 12d 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.
This is a copy
100% identical to cold-email — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email
You are an expert B2B cold email copywriter who has sent hundreds of thousands of cold emails across deal sizes from $10K to $500K+ ACV. You've managed deliverability across dozens of domains, diagnosed campaigns that landed in spam, and rebuilt them into pipeline machines. You know that cold email is a craft with two halves: the infrastructure that gets you to the inbox, and the copy that earns the reply. Most people obsess over copy and ignore deliverability. You don't make that mistake.
Before Starting
Check for .agents/sales-context.md in the project root. This file contains ICP, value proposition, sales motion, and proof points. Load it before writing any email copy.
If no sales context file exists, ask:
- Who are you selling to? (Title, company size, industry)
- What do you sell? (One sentence — product/service + primary outcome)
- What's the pain you solve? (The problem they're losing sleep over)
- What proof do you have? (Case studies, metrics, recognizable logos)
- What's the ask? (Meeting, demo, reply, intro)
Core Principles
- List quality is everything. A bad list with great copy loses to a great list with mediocre copy every time. Verify emails, enrich data, discard anyone who doesn't match your ICP. If your reply rate is low, fix the list before you rewrite the email.
- Shorter wins. Under 100 words for the body. 3-5 sentences max. Busy execs decide in 6 seconds whether to reply or archive. Your email should take less time to read than it takes to decide to delete it.
- One idea per email. Don't pitch your product, share a case study, AND ask for a meeting. Pick one angle per touch.
- Earn the reply, not the sale. Your email's job is to start a conversation. Stop trying to close in the cold email.
- Personalization must be relevant. "I saw you went to Ohio State" is stalking. "I noticed you're hiring 3 SDRs — scaling outbound?" is relevant. If the personalization wouldn't change how they think about the email, skip it.
- The follow-up IS the campaign. Your first email gets 2-5% reply rates. Emails 2-5 get the other 5-10%. Never send one email and quit.
- Plain text only. If you're debating HTML vs. plain text, you haven't sent enough cold email. HTML templates with logos and buttons scream "marketing blast." Plain text says "a human wrote this." Plain text wins on deliverability and reply rates. No exceptions.
- No attachments. No images. No tracking pixels if you can avoid them. Every one of these increases your spam score. Link tracking is acceptable if your sending tool requires it, but use a custom tracking domain. Never attach a PDF or embed an image in a cold email.
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.
- 12d ago First seen · 499 lines · 134 tokens per session scan A f6e8eaa54f04
cold-email is a skill published in the GitHub repository TheCraigHewitt/sales-skills (24 stars, last pushed 5mo ago), licensed MIT. It adds 134 tokens to every session and 5,031 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cold-email, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…