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 rianvdm/product-ai-public --skill finding-cd-bundlesgit clone --depth 1 https://github.com/rianvdm/product-ai-publicWrote 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/rianvdm/product-ai-public/finding-cd-bundles)<a href="https://agentmods.dev/skills/rianvdm/product-ai-public/finding-cd-bundles"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/finding-cd-bundles/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/rianvdm/product-ai-public/finding-cd-bundles"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/finding-cd-bundles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 111 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00173 | $0.09664 |
| Opus 5 | $0.00086 | $0.04832 |
| Sonnet 5 | $0.00035 | $0.01933 |
| Haiku 4.5 | $0.00017 | $0.00966 |
Grade A, and why
finding-cd-bundles scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`deepdiscount.com` is behind **Cloudflare Bot Management** — every path including the homepage returns `403` with a 12-byte body and sets `__cf_bm`. Both curl-with-a-browser-UA and WebFetch get the same 403. **The `claud How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buying wantlist CDs on eBay
Overview
Price Rian's Discogs wantlist against live eBay listings — cheapest copy of each album, and whether any seller holds enough of them to be worth bundling.
Core insight: a CD remaster carries its own UPC — Thriller is 074643811224 original, 074646607329 for the 2001 Special Edition, 888750438621 for the 2014 reissue. So searching eBay by the barcode of the exact wantlist pressing returns that master and skips the remasters automatically. The barcode does the same job finding-original-cds does by hand. That's the whole trick; don't re-derive it.
Corollary that matters: this tool inherits its master judgement entirely from the wantlist. If a remaster got wantlisted by mistake, this faithfully finds remasters. The wantlist is the filter — curate it with finding-original-cds first.
And check the other marketplace. Every album is also priced against the Discogs marketplace floor, because eBay loses that comparison more often than not — see The Discogs cross-check below. Never report an eBay price without it.
Buy the subset, and message the seller
Two things about bundles that are easy to get wrong, both learned the hard way on 2026-08-05:
1. Never buy a whole bundle — buy the subset that wins. A seller's price is competitive on some of their stock and bad on the rest. resellingroly held 5 wantlist albums; four of them beat the market but their Nevermind was $21.99 against $13.20 elsewhere. Buy those four, get Nevermind somewhere else. Evaluating bundles all-or-nothing made every one of 51 look like a loss — the script now computes the optimal subset (include an item whenever the seller's price undercuts the cheapest landed price elsewhere; shipping is paid once, which is what creates the room).
2. The combined-shipping discount is negotiable, not a fixed property of the seller. eBay exposes no combined-shipping rule through the API, and plenty of sellers have none configured — resellingroly charged 4 × per-item shipping to the cent, $18.98 on $24.23 of CDs. Rian messaged them and they refunded the excess. So the "if they combine" figure isn't hypothetical; it's what you get by asking, and asking worked first try. That purchase saved ~$8.66 over buying the same four separately.
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.
- 11d ago First seen · 354 lines · 173 tokens per session scan A 83bdc5e3e95d
finding-cd-bundles is a skill published in the GitHub repository rianvdm/product-ai-public (16 stars, last pushed 2d ago), licensed MIT. It adds 173 tokens to every session and 9,664 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
amazon-price-tracker
Amazon price monitoring and competitive pricing intelligence. Real-time price tracking, Buy Box analysis, promotion detection, and dynamic pricing strategy optimization. Use when the user asks about price monitoring, competitor pricing, Buy Box tracking, or pricing strategy.