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/itamarzand88/cli-anything-web/amazon-clinpx skills add ItamarZand88/CLI-Anything-WEB --skill amazon-cligit clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEBWhat 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 | $0.00067 | $0.00582 |
| Opus 5 | $0.00034 | $0.00291 |
| Sonnet 5 | $0.00013 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
amazon-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
cli-web-amazon
Read-only Amazon browsing: search, product detail, Best Sellers, suggestions. Public endpoints only.
Install: pip install cli-web-amazon
Commands
search QUERY— search products by keyword. Options:--page N(default 1, typically 1–7 pages),--dept TEXT(e.g. electronics, books)product get ASIN— full detail for one product (10-char ASIN, e.g.B0GRZ78683)bestsellers [CATEGORY]— Best Sellers list (default category: electronics; others: books, toys-and-games, music, video-games, home-garden, clothing-shoes-jewelry, sports-outdoors, kitchen, beauty). Options:--page N(~50 items/page)suggest QUERY— autocomplete suggestions. Options:--limit N(default 11)
Examples
# Search — returns [{asin, title, price, rating, review_count, url}]
cli-web-amazon search "wireless headphones" --json
# Search → detail on top result
ASIN=$(cli-web-amazon search "headphones" --json | python3 -c "import json,sys; print(json.load(sys.stdin)[0]['asin'])")
cli-web-amazon product get "$ASIN" --json
# Top best sellers in a category — [{rank, asin, title, price, url}]
cli-web-amazon bestsellers books --json
# Autocomplete — [{value, type}]
cli-web-amazon suggest "iphone ca" --json
JSON output
Add --json for structured output. Success responses are bare arrays (search, bestsellers, suggest) or a bare object (product get). Errors: {"error": true, "code": "NOT_FOUND|RATE_LIMITED|NETWORK_ERROR|SERVER_ERROR", "message": "..."}.
Utilities
cli-web-amazon doctor [--json] diagnoses local setup. cli-web-amazon mcp-serve exposes the commands as MCP tools over stdio. Running with no subcommand opens an interactive REPL.
Agent tips
- Search-result
pricecan be empty (Amazon renders some prices client-side). Useproduct getfor reliable pricing; itsprice_noteexplains a missing price, andgeo_restrictedflags region-locked items.
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.
- yesterday First seen · 46 lines · 67 tokens per session scan A 8aa42d5c8a69
amazon-cli is a skill published in the GitHub repository ItamarZand88/CLI-Anything-WEB (216 stars, last pushed 8d ago), licensed MIT. It adds 67 tokens to every session and 582 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
scrapling-official
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
qirabot
Drive any GUI with AI vision on raw screenshots — no DOM, no CSS/XPath selectors — via the Qirabot Python SDK or the qirabot CLI. Hand it a whole goal to complete autonomously, or make single natural-language actions: click, type, extract, and verify on web browsers, Android, iOS, desktop apps, and games. Use this…
xianyu-monitor
Search and monitor Xianyu/Goofish (闲鱼) with private state, filters, tasks, and deduplication. Use for 搜闲鱼、闲鱼登录、上新监控、蹲二手 or recurring searches.
retail-scrapers
Assess, reuse, build, repair, and validate public retail catalog and price channels in the Retail Scrapers Python toolkit. Use when a user provides a retailer name or URL, asks whether an existing adapter or market configuration can handle it, requests a new channel, or needs an existing channel fixed after site drift.
xianyu-buying-assistant
在 Codex 中按需搜索、比较并推荐闲鱼二手商品。用于用户提出闲鱼选品、比价、购买建议、卖家可信度、二手行情、关键词找货，或希望从尽量完整的公开搜索结果中筛选值得购买商品的请求。.
reelminner
Scrape Instagram reels + followers via a Playwright user session. MCP tools manage the full application — jobs, sessions, results, settings, proxies, and status — plus the core scraping tools scrapereels, getstatus, importcookies, stopscrape, exportresults. Use for reel metadata extraction, follower counts, music…