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 mostafa-drz/claude-skills --skill should-i-buygit clone --depth 1 https://github.com/mostafa-drz/claude-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/mostafa-drz/claude-skills/should-i-buy)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/should-i-buy"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/should-i-buy/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/mostafa-drz/claude-skills/should-i-buy"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/should-i-buy.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 | $0.00184 | $0.07416 |
| Opus 5 | $0.00092 | $0.03708 |
| Sonnet 5 | $0.00037 | $0.01483 |
| Haiku 4.5 | $0.00018 | $0.00742 |
Grade A, and why
should-i-buy 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 today.
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.
- Bash(curl *) How it starts
The opening of the file, as written. The whole thing — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preferences
On startup, use Read to load ~/.claude/skills/should-i-buy/preferences.md. If missing, treat as first-run (see First-time detection below).
Defaults when no preferences exist:
output-root:~/Desktop/should-i-buy/(confirmed on first run)currency:USDbudget-style:value(value / premium / bargain — shapes the verdict weighting)tone:friendly-cli(terse, direct, warm — like a friend who actually knows the category)open-report:true(auto-open the HTML report when done)verdict-style:decisive(decisive / balanced — decisive means I pick one and say why; balanced lays out the trade-off)
Also load ~/.claude/skills/should-i-buy/feedback-journal.md if present — it contains thumbs-up/down on past verdicts. Summarize its signal (e.g., "regretted buying X for Y reason", "consistently prefers refurb over new") and carry that into the current verdict.
Context
On startup, use Bash to detect: today's date (date +%Y-%m-%d), and whether the output-root folder exists (ls or absence). Do not fetch the shared URLs yet — that happens after we've clarified the ask.
Command routing
Check $ARGUMENTS:
help→ show help, stopconfig→ run config flow, stopreset→ delete preferences + feedback journal, confirm, stopfeedback→ collect thumbs-up/down on the most recent decision (see Feedback section), stophistory→ list recent decision folders with titles and dates, stopsetuporpreflight→ run the Chrome extension setup/onboarding flow (see Setup section), stop- anything else (one or more URLs, optionally with flags) → run the skill (starts with a preflight check — see Step 0)
Help
should-i-buy — Paste links, get a verdict with a 2026-aesthetic comparison report
Usage:
/should-i-buy <url> [more urls...] One or more product links
/should-i-buy [...] --for <context> Who/what this is for (e.g., "me, daily driver")
/should-i-buy [...] --budget <range> Budget constraint (e.g., "under $200")
/should-i-buy [...] --use <use-case> How you'll actually use it
/should-i-buy [...] --deadline <when> "by Friday", "this month" — affects wait-for-sale advice
/should-i-buy [...] --notes <text> Constraints, dealbreakers, leanings
/should-i-buy config Set preferences
/should-i-buy reset Clear preferences + feedback journal
/should-i-buy feedback Rate the last verdict (teaches the skill)
/should-i-buy history List past decision folders
/should-i-buy setup Walk through Chrome extension setup
/should-i-buy help This help
Examples:
/should-i-buy https://www.amazon.com/dp/B0XXXXXX https://www.rei.com/product/123
--for "me, weekend hiking" --budget "under $180"
/should-i-buy https://bestbuy.com/... --use "home office, 2 monitors" --notes "USB-C PD required"
/should-i-buy https://apple.com/shop/buy-mac/mac-mini --deadline "before WWDC"
Output:
{output-root}/{YYYY-MM-DD}-{kebab-title}/
├── report.html ← modern 2026 single-file report with verdict
├── data.json ← structured data (options, scores, verdict)
├── options/
│ ├── {slug-1}/
│ │ ├── hero.png ← product image
│ │ ├── page.png ← screenshot of listing (best-effort)
│ │ └── notes.md
│ └── ...
└── sources.md ← URLs visited + reasoning trail
Current preferences:
(loaded from preferences.md)
What ships with it
1 file 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.
- today Changed · +3 lines d13b038dc784
- 12d ago First seen · 529 lines · 184 tokens per session scan A cf049ca13b23
should-i-buy is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed today), licensed MIT. It adds 184 tokens to every session and 7,416 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 2026-08-31.
Other skills, from other repositories
apparel-demand
Analyzes apparel demand prediction systems for trend forecasting, size curve optimization, color and style analytics, sell-through rate tracking, and markdown optimization following CPFR collaborative planning and GTIN product identification standards..
franchise-inventory
Analyze franchise inventory management for par level optimization, waste tracking and root cause analysis, and theoretical vs. actual usage variance.
merchandising-analytics
Analyze retail merchandising systems including planogram optimization (space-to-sales alignment, fair share index, sales per linear foot), visual merchandising effectiveness for in-store displays and e-commerce product pages, market basket analysis with association rule mining (Apriori.
mobile-monetization
Audit mobile app revenue implementation -- in-app purchases, subscriptions, ad SDKs, paywall design, trial conversion funnels, and store billing compliance. Triggers: reviewing IAP flows, optimizing subscription conversion, checking ad mediation setup.
checkout-audit
Audit an ecommerce checkout flow against the 2026 conversion playbook. Triggers: "checkout audit", "checkout optimization", "Shopify checkout", "Stripe checkout", "Apple Pay".
dynamic-pricing
Audit a dynamic pricing engine for revenue optimization and fairness. Evaluates price elasticity models, competitive intelligence feeds, promotional ROI, markdown optimization, price image management, and legal compliance including Robinson-Patman and price gouging regulations..