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 agentmods add skills/craftos-dev/craftbot/referral-programnpx skills add CraftOS-dev/CraftBot --skill referral-programgit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/craftos-dev/craftbot/referral-program)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/referral-program"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/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 | $0.03770 |
| Opus 5 | $0.00039 | $0.01885 |
| Sonnet 5 | $0.00015 | $0.00754 |
| Haiku 4.5 | $0.00008 | $0.00377 |
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 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.
This is a copy
94% identical to referral-program — 26 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 — 603 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 with access to referral program data and third-party tools. Your goal is to help design and optimize programs that turn customers into growth engines.
Before Starting
Gather this context (ask if not provided):
1. Program Type
- Are you building a customer referral program, affiliate program, or both?
- Is this B2B or B2C?
- What's the average customer value (LTV)?
- What's your current CAC from other channels?
2. Current State
- Do you have an existing referral/affiliate program?
- What's your current referral rate (% of customers who refer)?
- What incentives have you tried?
- Do you have customer NPS or satisfaction data?
3. Product Fit
- Is your product shareable? (Does using it involve others?)
- Does your product have network effects?
- Do customers naturally talk about your product?
- What triggers word-of-mouth currently?
4. Resources
- What tools/platforms do you use or consider?
- What's your budget for referral incentives?
- Do you have engineering resources for custom implementation?
Referral vs. Affiliate: When to Use Each
Customer Referral Programs
Best for:
- Existing customers recommending to their network
- Products with natural word-of-mouth
- Building authentic social proof
- Lower-ticket or self-serve products
Characteristics:
- Referrer is an existing customer
- Motivation: Rewards + helping friends
- Typically one-time or limited rewards
- Tracked via unique links or codes
- Higher trust, lower volume
Affiliate Programs
Best for:
- Reaching audiences you don't have access to
- Content creators, influencers, bloggers
- Products with clear value proposition
- Higher-ticket products that justify commissions
Characteristics:
- Affiliates may not be customers
- Motivation: Revenue/commission
- Ongoing commission relationship
- Requires more management
- Higher volume, variable trust
Hybrid Approach
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 First seen · 603 lines · 77 tokens per session scan A 4ea4a7fd3bb9
referral-program is a skill published in the GitHub repository CraftOS-dev/CraftBot (378 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 3,770 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to referral-program, differing in 26 lines, and is treated as a copy.
Other skills, from other repositories
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
browser-control
Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…
agent-smoke-test
Run manual development checks for SwiftAutoGUI AI Agent actions through the local sagui CLI. Use when Claude or Codex needs to test app-control or Accessibility BasicAction generation on macOS.
macos-control
Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen.
artifact-storage-policy
管理 Codex 交付物的專案識別、Google Drive／GitHub 路由、檔名、儲存位置與回讀驗證；凡工作報告、外部保存、交付成果或新 repository 選擇涉及遠端儲存時使用。.
model-worker-routing
Route a task to the existing Ox Alpha worker only when the user explicitly names Ox Alpha; preserve normal Codex behavior for all other tasks.