island

island is a skill for Claude Code, Codex from dhaupin/vant. It costs 10 tokens per session (315 once invoked), scanned A, original, MIT.

A way to store separate, loadable sets of agent context. Each island is a bounded collection of files describing an identity, goals, and lessons for one focused area of work.

In plain words
What is it for?
Use it to list, create, load, and isolate reusable agent knowledge for focused tasks.
Why use it?
It keeps unrelated information out of the current context and makes it easier to switch between projects or focus areas when the available context is limited.

Skill for Claude CodeCodex

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

Good fit Use it to list, create, load, and isolate reusable agent knowledge for focused tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dhaupin/vant/vant-skill-island
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 dhaupin/vant --skill vant-skill-island
Clone the repo
git clone --depth 1 https://github.com/dhaupin/vant

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 island

README.md
[![agentmods](https://agentmods.dev/badge/skills/dhaupin/vant/vant-skill-island/github.svg)](https://agentmods.dev/skills/dhaupin/vant/vant-skill-island)
Your own site
<a href="https://agentmods.dev/skills/dhaupin/vant/vant-skill-island"><img src="https://agentmods.dev/badge/skills/dhaupin/vant/vant-skill-island/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 island

Your own site · 80×15
<a href="https://agentmods.dev/skills/dhaupin/vant/vant-skill-island"><img src="https://agentmods.dev/badge/skills/dhaupin/vant/vant-skill-island.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 315 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 $0.00010 $0.00315
Opus 5 $0.00005 $0.00158
Sonnet 5 $0.00002 $0.00063
Haiku 4.5 $0.00001 $0.00032

Measured 9d ago against content hash ea8233a46147, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

island 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 9d 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.

models/public/skills/vant-skill-island/SKILL.md · 100 lines

What it actually says

Island

A discrete, loadable brain.


What Is An Island

An island is a bounded context - a brain you can load.

islands/
├── identity.md
├── goals.md
└── lessons.md

Why Islands

  • Context windows are limited
  • Load only what you need
  • Keep brains discrete

How To Use

List Islands

vant islands list

Load Island

vant islands load [island-name]

Create Island

vant islands create [island-name]

Island Structure

File Purpose
identity.md Who this island is
goals.md What it's for
lessons.md What it knows

When To Use

Need Use
Focused work Load island
Multiple contexts Switch islands
Context window full Isolate

Output

## Island

### Loaded
- [name]: [purpose]

### Contents
- [n] files
- Goals: [count]
- Lessons: [count]

Role: Island Manager
Input: Island name
Output: Loaded context

Isolate your context.

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. 9d ago First seen · 100 lines · 10 tokens per session scan A ea8233a46147

Subscribe to this mod's changes

island is a skill published in the GitHub repository dhaupin/vant (9 stars, last pushed 9d ago), licensed MIT. It adds 10 tokens to every session and 315 once invoked, about $0.0001 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.