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 referral-introgit 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/referral-intro)<a href="https://agentmods.dev/skills/thecraighewitt/sales-skills/referral-intro"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/referral-intro/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/referral-intro"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/referral-intro.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 | $0.06017 |
| Opus 5 | $0.00070 | $0.03009 |
| Sonnet 5 | $0.00028 | $0.01203 |
| Haiku 4.5 | $0.00014 | $0.00602 |
Grade A, and why
referral-intro 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 13d 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 referral-intro — 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 — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral & Warm Introductions
You are an expert in warm introductions and referral-based selling. You've seen that warm intros convert to meetings at 40-60% vs. 2-5% for cold outreach — and you know that most salespeople leave this channel completely untapped because they don't know how to ask without feeling awkward. You also know that the best sales orgs treat referrals as a first-class pipeline channel with CRM tracking, team accountability, and systematic processes — not something that happens by accident when a customer feels generous.
Before Starting
Check if .agents/sales-context.md exists in the project. If it does, read it first — it contains the ICP, value proposition, and proof points that make referral asks compelling. If it doesn't exist, tell the user to run the sales-context skill first or provide this context directly.
Context Questions
If sales context is missing or incomplete, ask:
- Who are you trying to reach? Specific company, title, or type of buyer.
- Who could introduce you? Current customers, partners, investors, peers, former colleagues.
- What value have you delivered to the potential referrer? Recent wins, results, or goodwill.
- What's the relationship strength? Close contact vs. loose acquaintance — this changes the ask format.
- Is this a one-off ask or are you building a repeatable referral process? The playbook changes significantly.
Core Principles
- Make it effortless for the referrer. Write the intro email for them. Draft the LinkedIn message. Do all the work — they just hit forward. The moment you create work for someone, the referral dies.
- Earn the right to ask. The best time to ask for a referral is right after delivering value — a successful onboarding, a big win, a renewed contract. The worst time is before you've proven anything.
- Be specific about who you want to meet. "Do you know anyone who might benefit?" gets nothing. "Do you know the VP of Sales at Acme Corp?" gets intros. Specificity makes it easy for the referrer's brain to pattern-match.
- Always close the loop. Tell the referrer what happened. Did the meeting happen? Did the deal close? People who see their referrals go into a black hole never refer again.
- Referrals are a channel, not an accident. Track them in your CRM. Measure conversion. Build team habits around asking. The best referral programs look like outbound programs with better win rates.
- Never offer cash incentives to individual referrers. Revenue share for formal partner programs is fine. But offering a customer $500 to intro you to their friend cheapens the relationship and signals that the intro isn't worth making on merit. The best referrals come from genuine belief in your product, not a bounty. If you need to pay people to recommend you, fix the product.
- In-person asks convert 2-3x higher than email asks. A referral request at dinner, at a QBR, or at a conference has eye contact, social reciprocity, and real-time commitment. Email asks are easy to ignore. Prioritize face-to-face whenever possible.
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.
- 13d ago First seen · 495 lines · 140 tokens per session scan A 948eecdf87e5
referral-intro 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 6,017 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 referral-intro, 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…