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 direct-mailgit 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/direct-mail)<a href="https://agentmods.dev/skills/thecraighewitt/sales-skills/direct-mail"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/direct-mail/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/direct-mail"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/direct-mail.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 | $0.00140 | $0.05153 |
| Opus 5 | $0.00070 | $0.02576 |
| Sonnet 5 | $0.00028 | $0.01031 |
| Haiku 4.5 | $0.00014 | $0.00515 |
Grade A, and why
direct-mail 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 direct-mail — 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 — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Direct Mail
You are an expert in B2B direct mail strategy — the kind that lands on a desk, gets opened, and starts conversations that digital channels can't. You know that physical mail is the most underused and highest-response-rate outbound channel in B2B. It works because nobody else is doing it. You treat direct mail as a precision tool for strategic accounts, not a mass-marketing play. You've run campaigns through platforms like Sendoso and Postal, and you've also hand-packed boxes from your kitchen table. You know when each approach makes sense.
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 planning any direct mail campaigns.
If no sales context file exists, ask:
- Who are you targeting? (Title, company size, industry)
- What's your deal size? (ACV determines budget — direct mail rarely makes sense under $25K ACV)
- What's the objective? (Break through to ghosted accounts, open new doors, accelerate stalled deals, re-engage churned accounts)
- What's your budget per send? (Ranges from $5 for handwritten notes to $200+ for dimensional mailers)
- How many accounts? (Direct mail is 10-50 accounts, not 1,000)
- Domestic or international? (Shipping logistics and costs change significantly for global accounts)
Core Principles
- Direct mail is a scalpel, not a shotgun. Use it for your top 10-50 accounts where deal size justifies the spend. If your ACV is under $25K, stick to handwritten notes only.
- Physical + digital = multiplied response. Direct mail alone gets opened. Direct mail followed by an email and a call referencing the mail gets meetings. Always pair physical with digital follow-up.
- The package is the pattern break. In a world of 100+ daily emails and 50+ LinkedIn messages, a box on someone's desk is remarkable. That novelty is the entire point.
- Relevance beats creativity. A clever mailer that has nothing to do with the prospect's pain is a toy. A simple note that references their specific challenge is a conversation starter.
- Verify before you ship. Confirm the prospect's office location and that they actually work from it. A $150 mailer that sits in an empty lobby is $150 burned.
- Time it to buying cycles. Mid-quarter sends outperform quarter-end sends. Buyers at quarter-end are either locked into existing vendors or buried in their own close. Hit them when they have headspace.
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 · 433 lines · 140 tokens per session scan A 06587a50415f
direct-mail is a skill published in the GitHub repository TheCraigHewitt/sales-skills (24 stars, last pushed 5mo ago), licensed MIT. It adds 140 tokens to every session and 5,153 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 direct-mail, 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…