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 ItamarZand88/CLI-Anything-WEB --skill booking-cligit clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEBWrote 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/itamarzand88/cli-anything-web/booking-cli)<a href="https://agentmods.dev/skills/itamarzand88/cli-anything-web/booking-cli"><img src="https://agentmods.dev/badge/skills/itamarzand88/cli-anything-web/booking-cli/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/itamarzand88/cli-anything-web/booking-cli"><img src="https://agentmods.dev/badge/skills/itamarzand88/cli-anything-web/booking-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.00800 |
| Opus 5.5 | $0.00032 | $0.00320 |
| Sonnet 5.5 | $0.00016 | $0.00160 |
| Haiku 4.5 | $0.00008 | $0.00080 |
Grade A, and why
booking-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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cli-web-booking
Read-only Booking.com search: property search, property detail, destination autocomplete. AWS WAF protection is handled via stored cookies (auth login); autocomplete works without them.
Install: pip install "cli-web-booking[auth]", then playwright install chromium.
Commands
search find DESTINATION— search properties. Options:--checkin YYYY-MM-DD(default: tomorrow),--checkout YYYY-MM-DD(default: +3 days),--adults N(default 2),--rooms N(default 1),--children N,--sort [popularity|price|review_score|distance],--page N(25 results/page)get SLUG— property detail by URL slug (format{country}/{name}.html, e.g.fr/lesenatparis.html). Options:--checkin,--checkout,--adults,--roomsautocomplete QUERY— resolve a destination name to IDs. Options:--limit N(default 5). No auth neededauth login/auth status/auth logout— manage WAF cookies
Examples
# Cheapest hotels in Paris for specific dates
cli-web-booking search find "Paris" --checkin 2026-07-01 --checkout 2026-07-04 --sort price --json
# Search → detail on top result
SLUG=$(cli-web-booking search find "Rome" --json | python3 -c "import json,sys; print(json.load(sys.stdin)['properties'][0]['slug'])")
cli-web-booking get "$SLUG" --json
# Resolve a destination to dest_id/dest_type (city, district, airport, region, landmark)
cli-web-booking autocomplete "Tokyo" --json
JSON output
Add --json for structured output. Envelopes:
search find:{"success": true, "destination", "checkin", "checkout", "count", "properties": [{title, slug, score, score_label, review_count, price, price_amount, address, distance, property_type}]}get:{"success": true, "property": {name, description, score, review_count, full_address, country, postal_code, property_type, image_url, url, amenities}}autocomplete:{"success": true, "query", "results": [{dest_id, dest_type, title, label}]}- Errors:
{"error": true, "code": "...", "message": "..."}
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.
- 1mo ago First seen · 52 lines · 80 tokens per session scan A ad5a44ef2f10
booking-cli is a skill published in the GitHub repository ItamarZand88/CLI-Anything-WEB (233 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 800 once invoked, about $0.0003 per session on Opus 5.5. 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
using-b2c-tooling-sdk
Consuming the salesforce-b2c-tooling-sdk Python SDK from scripts or Jupyter notebooks — installation, choosing an authentication mechanism, and the available OCAPI/SCAPI/WebDAV clients and operations. Use when writing Python (or notebook) code that authenticates to a B2C Commerce instance, resolves config from…
xianyu-monitor
Search and monitor Xianyu/Goofish listings with filters, deduplication, and optional AI ranking. Use for searches, login, item analysis, and recurring alerts on 闲鱼 / Goofish.
elnora-admin
This skill should be used when the user asks to "log in", "logout", "check auth", "create API key", "revoke API key", "list API keys", "check health", "submit feedback", "view audit log", "shell completions", "get account", "update account", "account details", "view agreements", "accept terms", "validate token"…
elnora-files
This skill should be used when the user asks to "list files", "read a file", "get file content", "view protocol output", "file versions", "version history", "download protocol", "upload file", "upload batch", "bulk upload", "create file", "archive file", "fork file", "promote file", "working copy", "commit working…
elnora-orgs
This skill should be used when the user asks to "list organizations", "create org", "org members", "billing", "invite member", "manage invitations", "list invitations", "resend invitation", "reinvite", "cancel invitation", "accept invitation", "get invitation info", "remove member from org", "organization library"…
elnora-platform
Use when the user asks about "Elnora platform", "elnora CLI", "platform API", "platform overview", "what commands are available", "elnora help", "how to use Elnora", or any general question about the Elnora AI Platform that doesn't fit a specific domain. Routes to domain-specific sub-skills for token-efficient…