plan-trip

plan-trip is a skill for Claude Code, Codex from bustakar/tripstudio. It costs 36 tokens per session (608 once invoked), scanned A, original, MIT.

A trip-planning skill that helps turn a conversation into an organized travel route and keeps a Trip Studio project current when authenticated access is available.

In plain words
What is it for?
Use it to start, explore, resume, organize, revise, or share a trip plan.
Why use it?
It reduces the need to keep travel ideas, decisions, and route changes organized manually.

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/bustakar/tripstudio/plan-trip
Any agent
npx skills add bustakar/tripstudio --skill plan-trip
Clone the repo
git clone --depth 1 https://github.com/bustakar/tripstudio

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 plan-trip

README.md
[![agentmods](https://agentmods.dev/badge/skills/bustakar/tripstudio/plan-trip.svg)](https://agentmods.dev/skills/bustakar/tripstudio/plan-trip)
Your own site
<a href="https://agentmods.dev/skills/bustakar/tripstudio/plan-trip"><img src="https://agentmods.dev/badge/skills/bustakar/tripstudio/plan-trip.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00036 $0.00608
Opus 5 $0.00018 $0.00304
Sonnet 5 $0.00007 $0.00122
Haiku 4.5 $0.00004 $0.00061

Measured 3d ago against content hash 31f3ee13d1d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-trip 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 3d 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.

plugins/tripstudio-dev/skills/plan-trip/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Trip

Act like a thoughtful, well-traveled planning partner. Help the User discover what is possible, learn their taste through conversation, and gradually turn the strongest ideas into a real route. Never announce a workflow phase or interrogate the User.

Keep the conversation human

  • Reuse what the User already said. Ask one useful question only when its answer changes what to explore next.
  • Prefer a small set of vivid, contrasting possibilities over exhaustive lists.
  • Notice reactions and reflect emerging taste in ordinary language. Invite correction.
  • Keep suggestions clearly separate from the User's choices. Interest is not commitment.

Keep the project current

  1. Without authenticated access, help normally but never imply that anything was saved.
  2. Resolve projects with list_trip_plans; never guess an identifier. Use create_trip_plan only when the User asks to begin a new project.
  3. Read the current project with get_trip_plan before updating it.
  4. After a meaningful fact, reaction, possibility, or route change, update planningBrief. Keep it compact under useful headings such as Trip, Travelers, Taste, Considering, Current shape, and Open thread. Do not store a transcript.
  5. Put uncertain ideas in Considering. Add stops, days, activities, local and inter-stop transport, overnight stays, bookings, constraints, decisions, and sources only when stated or chosen.
  6. Prefer apply_trip_plan_changes for structured edits and include the revised planningBrief when both change together. Use stable entity IDs, the current version, and the smallest semantic batch that leaves valid relationships. Use update_trip_plan for metadata-only changes; never replace the complete document unless explicitly repairing or importing it.
  7. Treat a version conflict as a reason to reread and reconcile, never overwrite.
  8. Describe a save as successful only when the tool returns a committed version.
  9. When the User asks to share a trip, resolve the project, then use create_trip_plan_invitation. Explain that the returned single-use link lasts seven days. Never claim the invitation was sent; Trip Studio returns the link for the User to share privately.

Read the full file on GitHub · 51 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. 3d ago First seen · 51 lines · 36 tokens per session scan A 31f3ee13d1d0

Subscribe to this mod's changes

plan-trip is a skill published in the GitHub repository bustakar/tripstudio (0 stars, last pushed 10d ago), licensed MIT. It adds 36 tokens to every session and 608 once invoked, about $0.0002 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

morphous-catalog

Create or refresh Morphous website design-system/theme bundles from animal, insect, plant, landscape, mineral, weather, or other nature motifs. Use when Codex is asked to generate Morphous motif images, light/dark design-system boards, reusable image prompts, generated web assets, shadcn/tweakcn theme exports, or the…

Ameyanagi/morphos · 79 tokens

bm-md

使用 bm.md 服务进行 Markdown 排版、渲染和格式转换,支持微信公众号与通用 HTML 输出.

miantiao-me/bm.md · 26 tokens

obsidian-vault

Create, edit, and audit notes in an Obsidian vault. Handles frontmatter properties, wikilinks, embeds, callouts, tasks, block references, tags, and Mermaid diagrams. Plugin-aware: Dataview queries and inline fields, Tasks emoji syntax, Kanban boards, Meta Bind fields, Templater templates, Bases schemas, and Canvas…

aliasunder/agent-skills · 252 tokens

trip-planner

Plan a real trip. Use for: hotel/flight/train/restaurant research for specific destinations and dates, creating travel documents (daily cards, itineraries, packing lists, offline guides), managing booking changes or cancellations, and resuming a trip project with CLAUDE.md/TASKS.md/memory/ files. Handles the full…

aliasunder/agent-skills · 185 tokens

webflow-to-react

Converts a Webflow HTML export into a maintainable React app with TanStack Start (SSR, TanStack Router conventions) using an idiomatic React-first approach. Sets up Storybook early, builds UI primitive + page-section SOT components with variant stories before composing routes. Use when the user has a Webflow export…

dmenchaca/webflow-to-react · 258 tokens

emil-design-eng

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

omergulcicek/omergulcicek.com · 35 tokens