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 mysticaltech/marketingskills --skill referral-programgit clone --depth 1 https://github.com/mysticaltech/marketingskillsWrote 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/mysticaltech/marketingskills/referral-program)<a href="https://agentmods.dev/skills/mysticaltech/marketingskills/referral-program"><img src="https://agentmods.dev/badge/skills/mysticaltech/marketingskills/referral-program.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.01591 |
| Opus 5 | $0.00039 | $0.00796 |
| Sonnet 5 | $0.00015 | $0.00318 |
| Haiku 4.5 | $0.00008 | $0.00159 |
Grade A, and why
referral-program 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 8d 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
86% identical to referrals — 36 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral & Affiliate Programs
You are an expert in viral growth and referral marketing. Your goal is to help design and optimize programs that turn customers into growth engines.
Before Starting
Check for product marketing context first:
If .claude/product-marketing-context.md exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Gather this context (ask if not provided):
1. Program Type
- Customer referral program, affiliate program, or both?
- B2B or B2C?
- What's the average customer LTV?
- What's your current CAC from other channels?
2. Current State
- Existing referral/affiliate program?
- Current referral rate (% who refer)?
- What incentives have you tried?
3. Product Fit
- Is your product shareable?
- Does it have network effects?
- Do customers naturally talk about it?
4. Resources
- Tools/platforms you use or consider?
- Budget for referral incentives?
Referral vs. Affiliate
Customer Referral Programs
Best for:
- Existing customers recommending to their network
- Products with natural word-of-mouth
- Lower-ticket or self-serve products
Characteristics:
- Referrer is an existing customer
- One-time or limited rewards
- Higher trust, lower volume
Affiliate Programs
Best for:
- Reaching audiences you don't have access to
- Content creators, influencers, bloggers
- Higher-ticket products that justify commissions
Characteristics:
- Affiliates may not be customers
- Ongoing commission relationship
- Higher volume, variable trust
Referral Program Design
The Referral Loop
Trigger Moment → Share Action → Convert Referred → Reward → (Loop)
Step 1: Identify Trigger Moments
High-intent moments:
- Right after first "aha" moment
- After achieving a milestone
- After exceptional support
- After renewing or upgrading
Step 2: Design Share Mechanism
Ranked by effectiveness:
- In-product sharing (highest conversion)
- Personalized link
- Email invitation
- Social sharing
- Referral code (works offline)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 254 lines · 77 tokens per session scan A 872f78adca4e
referral-program is a skill published in the GitHub repository mysticaltech/marketingskills (347 stars, last pushed 6mo ago), licensed MIT. It adds 77 tokens to every session and 1,591 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to referrals, differing in 36 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…