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 surfmind-space/awesome-surfmind --skill coupon-huntergit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/coupon-hunter)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/coupon-hunter"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/coupon-hunter/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/surfmind-space/awesome-surfmind/coupon-hunter"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/coupon-hunter.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 | $0.00083 | $0.00772 |
| Opus 5 | $0.00042 | $0.00386 |
| Sonnet 5 | $0.00017 | $0.00154 |
| Haiku 4.5 | $0.00008 | $0.00077 |
Grade A, and why
coupon-hunter 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 10d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coupon Hunter
Help the user find legitimate discount codes for the store they're shopping and point them to the sources most likely to carry a working one. Never claim a code works unless it's verified in the visible context, invent codes or expiration dates, or encourage bypassing a merchant's terms or abusing a promotion.
- Identify the merchant, product or category, region, and purchase context from the page, cart, or the user's request.
- Name the legitimate paths to check, ordered by likelihood: the merchant's own promo or sale page, the newsletter/first-order signup offer, student/teacher/military/healthcare programs, cashback and rewards portals, reputable browser coupon tools, and trusted deal forums. Mention cashback/rewards portals and newsletter/first-order signup offers even when they look unlikely or unavailable, so the user knows they were considered.
- Use web search or any browser/MCP tool available to look for current codes, then verify each against its expiration date, minimum spend, product exclusions, and region limits before presenting it. For the best offer you find, explicitly state at least three of those verification dimensions; if a dimension is not published, say that instead of guessing.
- For student, education, professional, or subscription discounts, put the program near the top and call out eligibility requirements such as school email, accreditation, account type, plan limits, annual-vs-monthly billing, and whether the offer is US-only, global, or otherwise region-limited.
- Flag red flags rather than passing them on — coupon sites that demand personal info to "unlock" a code, codes with no source or date, walls of dead codes, or claims you can't verify.
Return concise headings and include these sections when they fit: Likely discount paths, Search terms, Codes or offers to verify, Warnings, Next steps at checkout. If the visible context is insufficient, say what's missing and give the best supported next step.
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.
- 10d ago First seen · 54 lines · 83 tokens per session scan A 4c3266c2744d
coupon-hunter is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 772 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 2026-08-31.
Other skills, from other repositories
shopify-developer
Complete Shopify development reference covering Liquid templating, OS 2.0 themes, GraphQL APIs, Hydrogen, Functions, and performance optimization (API v2026-01). Use when working with .liquid files, building Shopify themes or apps, writing GraphQL queries for Shopify, debugging Liquid errors, creating app extensions…
live-commerce-operations-knowledge-builder
A skill for turning live-stream sales materials—such as schedules, product plans, host scripts, workflows, and review metrics—into an AI-ready operations knowledge base.
simple-review-analyzer
An AI tool for analysing online shop reviews from services such as Amazon, eBay, and AliExpress. It extracts customer themes, user profiles, problems, and VOC, meaning the recurring feedback customers express about a product.
ecommerce-product-manager
Expert E-commerce Product Manager with deep knowledge of online retail strategy, conversion optimization, marketplace operations, and platform-specific tactics for Amazon, Shopify, and Alibaba. Use when: ecommerce-strategy, product-launch, conversion-optimization, marketplace-management, pricing-strategy.
ecommerce-livestream-trainer
Expert-level E-commerce Livestream Trainer with deep knowledge of live selling techniques, platform operations (TikTok Shop, Taobao Live, JD Live), audience engagement, and sales conversion.
order
Place orders on Bob's Online Store. Use when the user wants to add items to a cart, apply coupons, choose shipping, and complete checkout via API. Handles the full purchase workflow from cart to confirmation. Requires a Bearer token (user must be logged in). Do NOT use for product search or browsing.