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 fusengine/agents --skill astro-starlightgit 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-starlight)<a href="https://agentmods.dev/skills/fusengine/agents/astro-starlight"><img src="https://agentmods.dev/badge/skills/fusengine/agents/astro-starlight/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/fusengine/agents/astro-starlight"><img src="https://agentmods.dev/badge/skills/fusengine/agents/astro-starlight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.01090 |
| Opus 5.5 | $0.00016 | $0.00436 |
| Sonnet 5.5 | $0.00008 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
astro-starlight 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 20d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Also covers multi-language documentation with hreflang support and Content Layer API integration (docsLoader, schema) specific to Starlight's content model, plus CSS custom property theming. Does not cover generic Astro Content Layer usage outside Starlight (astro-content) or non-Starlight i18n routing (astro-i18n) — those are handled by their own skills.
Astro Starlight
Production-ready documentation theme for Astro with built-in search, dark mode, i18n, and rich plugin ecosystem.
Agent Workflow (MANDATORY)
Before ANY implementation, spawn 3 agents in parallel, one Agent call each with a name:
- fuse-ai-pilot:explore-codebase - Analyze existing Starlight config, sidebar, and content structure
- fuse-ai-pilot:research-expert - Verify Starlight plugin APIs via Context7/Exa
- mcp__context7__query-docs - Check Starlight docs for Content Layer and i18n patterns
After implementation, run fuse-ai-pilot:sniper for validation.
Overview
When to Use
- Building technical documentation sites
- Creating API reference docs (with starlight-openapi)
- Generating docs from TypeScript types (with starlight-typedoc)
- Adding a blog to a documentation site (with starlight-blog)
- Setting up versioned documentation (with starlight-versions)
- Multi-language documentation with hreflang support
Why Starlight
| Feature | Benefit |
|---|---|
| Pagefind built-in | Full-text search, zero config |
| Dark/light mode | Automatic, CSS custom properties |
| Sidebar config | Filesystem-based or manual groups |
| Plugin ecosystem | DocSearch, blog, openapi, typedoc |
| Content Layer API | Astro 7 content collections integration |
| llms.txt support | starlight-llms-txt for AI discoverability |
| No-JS mobile menu (0.42) | Popover API — menu works with JS disabled; ships compiled JS + .d.ts (faster tsc) |
What ships with it
9 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/content-layer.md 2.3 KB
- references/customization.md 2.6 KB
- references/i18n-multilang.md 2.0 KB
- references/plugins.md 2.3 KB
- references/search.md 2.2 KB
- references/setup.md 2.4 KB
- references/sidebar-config.md 2.2 KB
- references/templates/sidebar-example.md 2.1 KB
- references/templates/starlight-config.md 2.7 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.
- 20d ago Changed · +1 lines 9b763ebb2de5
- 1mo ago Changed bb478b1db21e
- 1mo ago First seen · 88 lines · 41 tokens per session scan A bd2d36e0dbfe
astro-starlight is a skill published in the GitHub repository fusengine/agents (32 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 1,090 once invoked, about $0.0002 per session on Opus 5.5. 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
radin-record
Log bugs, follow-ups, ideas or feedback raised this session as backlog entries that outlive the conversation. Use for /radin-record or any ask to save something for later, even a vague one ("add the findings"): scan the whole session.
radin-do
Record one ad-hoc prompt as a backlog entry, then execute just that task. Use for /radin-do .
radin-stats
Show the stats/gain output of every companion tool that ships one, side by side.
radin-batch
Work backlog tasks via sub-agents, prioritized, one commit each; plans first the entries radin-record flagged as needing a plan. Use for "work through my backlog", or name an epic or task to run only those.
designing-interfaces
Creates a design system for software with a UI. Use when a project has a user interface and architecture is confirmed — whether creating from scratch or extracting patterns from existing code.
orchestrating-software-dev
Runs software development projects from idea to completion. Use when starting a software project, adding a feature, fixing a bug, or resuming an in-progress build.