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 deciqAI/knowledge-skills --skill referral-loop-designgit clone --depth 1 https://github.com/deciqAI/knowledge-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/deciqai/knowledge-skills/referral-loop-design)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/referral-loop-design"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/referral-loop-design/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/deciqai/knowledge-skills/referral-loop-design"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/referral-loop-design.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 | $0.00077 | $0.00638 |
| Opus 5 | $0.00039 | $0.00319 |
| Sonnet 5 | $0.00015 | $0.00128 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
referral-loop-design 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral Loop Design — Turn Customers into a Channel
Overview
A referral loop is a repeatable cycle where using the product produces new users: a happy customer is prompted, at the right moment, with the right incentive and an easy share, and the new user enters the same loop. Loops compound; one-off "refer a friend" banners don't. Referrals only work on a product people already value — they amplify love, they don't create it.
The Process
- Verify the precondition — strong retention/NPS. Gate: referring a product people don't love just spreads churn — fix retention first.
- Pick the trigger moment — right after a value peak (a win, a result, an "aha"), not at signup. (Pairs with peak-end thinking.)
- Choose the incentive type — double-sided (giver + receiver), status, or pure delight — matched to the audience's motivation.
- Remove friction — one-tap share, pre-written message, obvious reward. Gate: any extra step halves participation.
- Close the loop — the referred user lands in an experience that gets them to their own value fast, then hits the same trigger.
- Instrument K-factor — invites sent × conversion; iterate the weakest step. Gate: K without measuring each step = you can't tell what to fix.
When to Use
- Loved product with weak organic spread
- Designing/relaunching a referral program
- Cheap growth for low-budget SMBs/creators
Applying It Well
- Timing (post-value) matters more than reward size.
- Double-sided incentives usually beat one-sided.
- Referred users often retain better — treat their onboarding as sacred.
Red Flags
- Bolting referrals onto a leaky-retention product.
- Asking at signup, before any value.
- Multi-step share flows that kill participation.
Verification
- Retention/NPS precondition met
- Trigger fires at a value peak
- Incentive matched to audience; share is one-tap
- Each loop step instrumented and iterated
Part of deciqAI Knowledge Skills — 237 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. See it run → https://www.deciqai.com/s/referral-loop-design · Built by deciqAI · github.com/deciqAI · Contributions welcome.
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.
- 9d ago First seen · 44 lines · 77 tokens per session scan A 61ffcb8a2679
referral-loop-design is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 11d ago), licensed MIT. It adds 77 tokens to every session and 638 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.
cto-advisor
Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…
plan-payroll
Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…