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 dhaupin/vant --skill vant-skill-islandgit clone --depth 1 https://github.com/dhaupin/vantWrote 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/dhaupin/vant/vant-skill-island)<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.
<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>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 | $0.00010 | $0.00315 |
| Opus 5 | $0.00005 | $0.00158 |
| Sonnet 5 | $0.00002 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00032 |
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.
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.
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.
- 9d ago First seen · 100 lines · 10 tokens per session scan A ea8233a46147
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.
Other skills, from other repositories
list-learned-actions
Explicit Codex workflow: List persisted reusable actions, UI skeletons, and legacy feedback memories before composing device primitives.
agentlas-auto-activation
Use when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .agentlas memory and sitemap files.
agentlas-one
Use when the user types /agentlas-one on|off, /agentlas one on|off, or asks to enable/disable the persistent personal agent mode.
memory-ticketing
Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memory Curator routing to an agent repo.
pm-soul
Use when preserving product intent, acceptance criteria, decision memory, open loops, roadmap context, or the product-manager continuity layer of an agent team.
distill-session-knowledge
Offline-mine this project's pi session JSONL logs into reusable, verified knowledge: extracts faults, decisions, corrections, procedures and docs, promotes only recurring patterns, and routes artifacts into skillmanage, memory and docs. Use on "mine my sessions", "distill session knowledge", "extract lessons from…