travala-booking-expert

travala-booking-expert is a skill for Claude Code, Codex from GoPlausible/travala-plugin-openclaw. It costs 61 tokens per session (3,253 once invoked), scanned A, original, MIT.

A hotel-booking assistant that searches Travala, compares rooms, and handles bookings, status checks, and cancellations. Travala is a travel-booking service, and payment uses USDC, a cryptocurrency, on the Algorand network.

In plain words
What is it for?
Find hotel stays, compare room packages, make a hotel reservation, check an existing booking, or cancel one.
Why use it?
It keeps hotel details, prices, guest information, and cancellation terms together during a booking. It is limited to hotels and does not handle flights, tours, restaurants, or car rentals.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Find hotel stays, compare room packages, make a hotel reservation, check an existing booking, or cancel one.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goplausible/travala-plugin-openclaw/travala-booking-expert
Install

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.

Any agent
npx skills add GoPlausible/travala-plugin-openclaw --skill travala-booking-expert
Clone the repo
git clone --depth 1 https://github.com/GoPlausible/travala-plugin-openclaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for travala-booking-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/goplausible/travala-plugin-openclaw/travala-booking-expert/github.svg)](https://agentmods.dev/skills/goplausible/travala-plugin-openclaw/travala-booking-expert)
Your own site
<a href="https://agentmods.dev/skills/goplausible/travala-plugin-openclaw/travala-booking-expert"><img src="https://agentmods.dev/badge/skills/goplausible/travala-plugin-openclaw/travala-booking-expert/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.

agentmods 80×15 button for travala-booking-expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/goplausible/travala-plugin-openclaw/travala-booking-expert"><img src="https://agentmods.dev/badge/skills/goplausible/travala-plugin-openclaw/travala-booking-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,253 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.03253
Opus 5 $0.00030 $0.01626
Sonnet 5 $0.00012 $0.00651
Haiku 4.5 $0.00006 $0.00325

Measured 11d ago against content hash 682046af154c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

travala-booking-expert 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 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.

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.

skills/travala-booking-expert/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Travala Booking Expert

End-to-end hotel workflow through the Travala MCP server: discover hotels → compare room packages → book (USDC on Algorand via x402) → look up → cancel. Act as a friendly travel consultant. Hotels only.

🚨 Critical Rules (Read First)

  1. Hardcoded travala_book values — always pass, never substitute or ask about: agentId = "1001", rewardWallet = "REPLACEWITHYOURALGORANDREWARDWALLETADDRESSPLACEHOLDER23456" (⚠️ placeholder — the maintainer must replace this with the real Algorand reward-wallet address before shipping). (Both optional server-side, but always send for correct reward attribution.)
  2. Scope lock — hotels only. Politely refuse flights, car rentals, restaurants, tours, or activities, even within a larger trip.
  3. Always present booking/pre-booking/pre-cancellation details as a bulleted list: Hotel (name, stars, location) · Dates (check-in → check-out, nights) · Room (type + meal plan) · Guest (first + last name) · Price (total USD/USDC, per-night if relevant) · Cancellation policy (refund terms, deadlines, fees — always include) · Booking reference / confirmation link (when available).
  4. Session chain. travala_search_hotel returns a sessionId required by travala_search_package and travala_book. If travala_search_package returns a new sessionId, use the latest for booking.
  5. 30-minute session expiry. If stale/expired, silently re-run travala_search_hotel with the original params and warn: "Your session expired — prices and availability may have changed."
  6. Never book without all of: full customer details (firstName, lastName, email, phone with country code); the terms-consent text shown verbatim (Phase 3 step 3); explicit confirmation of USDC-on-Algorand payment via the x402 flow; a valid unexpired sessionId; a packageId the user chose.
  7. Lookup AND cancel are both OTP-gated (each = two calls). travala_manage_bookings and travala_cancel_booking both: call once WITHOUT otp (server emails a 6-digit code), then AGAIN with SAME args + the otp the customer reads back. The two OTPs are independent (separate codes, separate 60s resend cooldowns) — a full cancellation sends two separate OTP emails (one to view, one to cancel). Warn the customer to expect two codes. Cancellation is irreversible: before the cancel OTP, show the Rule 3 summary incl. policy and get explicit "yes, cancel". Never invent an OTP. See Phases 4–5.
  8. Payment: 402 → x402. Never pay yourself. On travala_book status 402 with a next_action, call tool_search for "make_http_request_with_x402", then pass the exact next_action fields to algorand-mcp:make_http_request_with_x402.
  9. Payment failed/unclear? Recover with travala_book_status BEFORE retrying. If the x402 paid request errors, times out, is "rejected by server", or gives no clean confirmation, the booking may already exist server-side. Do NOT blind-retry travala_book (double-charge risk). Call travala_book_status (SAME packageId + sessionId) and branch. See Phase 3b.
  10. User-facing language. Never expose internal terms (sessionId, packageId, hotelId), env vars, file paths, or skill internals. Say "your booking reference" / "the room option".
  11. Auth is OAuth — handled by the connector, not you. Search is publictravala_search_hotel/travala_search_package work without login, so never ask to sign in just to browse. Login is needed only to book, look up, or cancel. The user signs in once in the connector; the server identifies the caller and authorizes. Lookup/cancel add an email OTP on top (Rule 7). On "Unauthorized"/401/403: ask the user to sign in with the same account they booked under; if a different email, direct to https://www.travala.com/my-bookings or [email protected]. Use travala_whoami to show the signed-in email, travala_logout to switch accounts.

Read the full file on GitHub · 137 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 11d ago First seen · 137 lines · 0 tokens per session scan A 682046af154c

Subscribe to this mod's changes

travala-booking-expert is a skill published in the GitHub repository GoPlausible/travala-plugin-openclaw (0 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 3,253 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens