tripsy

A skill for working with Tripsy travel data through the local Tripsy command-line tool or MCP server. Tripsy is a travel-planning service with data such as trips, activities, and lodging.

In plain words
What is it for?
Use it to manage Tripsy trips, activities, and lodging, including their dates, times, and time zones.
Why use it?
It gives an agent a defined way to inspect, create, update, and organize travel records without handling the service’s API directly.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tripsyapp/cli/tripsy
Any agent
npx skills add tripsyapp/cli --skill tripsy
Clone the repo
git clone --depth 1 https://github.com/tripsyapp/cli

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,533 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00034 $0.05533
Opus 5 $0.00017 $0.02766
Sonnet 5 $0.00007 $0.01107
Haiku 4.5 $0.00003 $0.00553

Measured yesterday against content hash 5ab27da2c61d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

tripsy scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://tripsy.app/install_cli | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://tripsy.app/install_cli | bash
skills/tripsy/SKILL.md · 517 lines

How it starts

The opening of the file, as written. The whole thing — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tripsy CLI Agent Skill

Use this skill when an agent needs to inspect, create, update, or organize Tripsy data through the local tripsy CLI or tripsy-mcp server.

The CLI and MCP server talk to the public Tripsy API at https://api.tripsy.app. Public API paths do not include an /api prefix.

Operating Rules

  • Prefer tripsy-mcp typed tools when the current client supports MCP.
  • Prefer friendly CLI commands over tripsy request when a wrapper exists.
  • Use --json for agent-readable output. Use --quiet only when raw data is needed without the envelope.
  • Read the ok, summary, data, and breadcrumbs fields from JSON envelopes.
  • Follow breadcrumbs when navigating related resources.
  • Do not print stored tokens unless the user explicitly asks for token output.
  • Do not ask the user for passwords in chat. Ask them to run tripsy auth login --username USERNAME locally, or use TRIPSY_TOKEN.
  • Use exact ISO-8601 UTC datetimes for every timed value, for example 2026-06-03T09:00:00Z. Always pair them with the relevant local IANA timezone field (timezone, departure_timezone, or arrival_timezone).
  • When displaying activity or lodging dates/times from MCP data, convert UTC starts_at and ends_at into the item's timezone before formatting local date/time.
  • When displaying transportation dates/times from MCP data, convert UTC departure_at with departure_timezone and UTC arrival_at with arrival_timezone; do not apply one endpoint's timezone to the other endpoint unless the fields explicitly match.
  • For trip dates, use date strings such as 2026-06-01.
  • trips list returns trips where the authenticated user is travelling. Use trips following for trips the user follows but is not travelling on.
  • has_dates is authoritative. If has_dates is false, ignore starts_at and ends_at even when those fields are present.
  • When creating a destination trip, choose a beautiful destination-specific Unsplash image and set it as cover_image_url.
  • Use a real direct Unsplash CDN URL copied from an image result, in the form https://images.unsplash.com/photo-1562869929-bda0650edb1f?ixid=...&ixlib=rb-4.1.0. Tripsy will add the needed rendering parameters.
  • The images.unsplash.com path must be photo-<numeric timestamp>-<asset hash>. Do not use the Unsplash page URL, and do not turn short photo IDs like nWdsya5_Yms into https://images.unsplash.com/photo-nWdsya5_Yms.
  • Before saving a trip cover_image_url, validate that it is a real direct Unsplash CDN URL. If the client has external URL access, also confirm the image URL is reachable and not returning a 404.
  • For itinerary planning, set trip dates whenever day-by-day timed planning is needed. If the user did not provide dates but asks for a planned itinerary, choose explicit reasonable dates and state them.
  • Create one item per actual stop, reservation, meal, tour, or activity. Do not create one activity that bundles a full day or multiple places.
  • Set latitude and longitude for every activity; MCP rejects activity creation without both coordinates so Tripsy's map is populated.
  • Set latitude and longitude for every known hosting and transportation point so Tripsy's map is populated.
  • Use the most specific supported category slug for Activity activity_type; do not default to general or tour when a better category exists.
  • Activities can use either a built-in activity_type slug or a visible custom category slug. Custom category slugs are only valid on Activity objects through activity_type; do not use them for lodging, transportation, expenses, or trips. If an activity has an activity_type outside the built-in list, fetch visible custom categories through tripsy_categories_list or tripsy categories list and resolve the slug there before displaying the category name, icon, or color.
  • Use hostings for hotels/lodging. The lodging category slug is lodging.
  • Use transportations for point-to-point movement such as flights, trains, cars, buses, cruises, ferries, roadtrips, walks, and similar travel.
  • For flights, create a transportation with transportation_type set to airplane, set departure_description and arrival_description to the airport IATA codes, include each airport's latitude and longitude, and omit name unless the user provided one.
  • For transfer activities, create a transportation with transportation_type set to roadtrip, and fill both departure and arrival locations with name/description, address, latitude, and longitude.
  • Delete operations can be executed when requested. Tripsy deletes are recoverable, so they can be undone if necessary. State what will be deleted before running the command when the user has not already been explicit.

Read the full file on GitHub · 517 lines

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. yesterday First seen · 517 lines · 34 tokens per session scan C 5ab27da2c61d

Subscribe to this mod's changes

tripsy is a skill published in the GitHub repository tripsyapp/cli (15 stars, last pushed 13d ago), licensed MIT. It adds 34 tokens to every session and 5,533 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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