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 agentmods add skills/fusengine/agents/astro-islandsnpx skills add fusengine/agents --skill astro-islandsgit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/astro-islands)<a href="https://agentmods.dev/skills/fusengine/agents/astro-islands"><img src="https://agentmods.dev/badge/skills/fusengine/agents/astro-islands.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00955 |
| Opus 5 | $0.00014 | $0.00477 |
| Sonnet 5 | $0.00005 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
astro-islands 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Also covers transition:persist for preserving component state across View Transitions, and prop serialization rules for data crossing the server/client boundary. Does not cover installing the underlying UI framework itself (astro-integrations) or Server Actions used inside islands (astro-actions) — those are separate skills.
Astro Islands Expert
Partial hydration architecture: zero JS by default, selective interactivity via directives.
Agent Workflow (MANDATORY)
Before ANY implementation, use TeamCreate to spawn 3 agents:
- fuse-ai-pilot:explore-codebase - Analyze existing components and hydration patterns
- fuse-ai-pilot:research-expert - Verify latest Islands docs via Context7/Exa
- mcp__context7__query-docs - Get client directive and server:defer examples
After implementation, run fuse-ai-pilot:sniper for validation.
Overview
When to Use
- Adding interactive React/Vue/Svelte/Solid components to Astro pages
- Deferring dynamic server content without blocking page load
- Persisting component state during View Transitions
- Optimizing Time to Interactive with lazy hydration
Why Islands Architecture
| Concept | Benefit |
|---|---|
| Zero JS by default | Maximum performance, minimal payload |
| Selective hydration | Only interactive components ship JS |
server:defer |
Dynamic server content without SSR blocking |
client:visible |
Lazy-load below-fold components |
transition:persist |
State survives page navigation |
Client Directives
| Directive | When JS Loads | Use Case |
|---|---|---|
client:load |
Immediately on page load | Critical interactive UI |
client:idle |
After requestIdleCallback |
Non-critical UI |
client:visible |
When component enters viewport | Below-fold components |
client:media="(query)" |
When media query matches | Responsive components |
client:only="framework" |
Client-only, no SSR | Components using browser APIs |
What ships with it
8 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.
- references/client-directives.md 3.0 KB
- references/overview.md 1.7 KB
- references/prop-serialization.md 1.6 KB
- references/server-islands.md 1.8 KB
- references/templates/interactive-island.md 2.2 KB
- references/templates/server-island.md 1.9 KB
- references/transitions.md 3.3 KB
- references/view-transitions.md 4.2 KB
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.
- 3d ago First seen · 97 lines · 27 tokens per session scan A bcdccbfcaa44
astro-islands is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 955 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 2026-08-30.
Other skills, from other repositories
agentmemory-architecture
How agentmemory is built, the iii engine primitives it runs on, its storage model, ports, and the viewer. Use when reasoning about how memory is stored or retrieved end to end, when extending the system, or when answering how agentmemory works under the hood.
agentmemory-mcp-tools
Map of every agentmemory MCP tool, what each does, and its parameters. Use when choosing which memory tool to call, when a tool name or argument is unclear, or when answering what agentmemory can do via MCP.
unity-console
Capture and query the Unity Editor console.
unity-profiler
Capture read-only Unity runtime performance snapshots.
unity-skills-index
Index of all Unity Skills modules with per-module mode labels (SA/FA/Mixed). Use to find which module covers a task before loading its doc.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).