StarNet is a local-first desktop harness for creating AI agents and arranging them in a pixel-art space station whose layout represents their capabilities, permissions, and workflow. It lets people run real model calls and tools through multiple bounded agents, using their own provider keys or accounts and optionally messaging the station through chat services. The catalogue entries are skills that extend or support work performed by StarNet agents.
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 androoAGI/starnet --skill seo-auditgit clone --depth 1 https://github.com/androoAGI/starnetWrote 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/androoagi/starnet/seo-audit)<a href="https://agentmods.dev/skills/androoagi/starnet/seo-audit"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/seo-audit/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/androoagi/starnet/seo-audit"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/seo-audit.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 | $0.00048 | $0.02504 |
| Opus 5.5 | $0.00019 | $0.01002 |
| Sonnet 5.5 | $0.00010 | $0.00501 |
| Haiku 4.5 | $0.00005 | $0.00250 |
Grade A, and why
seo-audit 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 12d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Audit
Find what is stopping a site from being found in search, and say what to fix first. The bar: every finding names the URL and what you actually saw there, and every check you could not run is listed as not run. No guessed scores, no findings from memory.
When to use
- "Audit my site's SEO." "Why am I not ranking?" "My traffic dropped."
- A technical check before or after a redesign or a migration.
- A review of titles, headings and content on named pages.
Not for writing a new page (landing-copy), planning what to publish (content-calendar), or raising sign-ups on a page that already gets visitors (conversion-review).
How you read a site, and what each tool cannot see
| You need | Use | Blind spot |
|---|---|---|
| robots.txt, sitemaps, page copy (usually with its headings marked) | web_fetch |
Cleaned text only. Scripts are dropped, so structured data never shows, and long files are cut short. |
| The first H1 as rendered | browser.get_text with the selector h1 |
First match only. |
| The page as a visitor's browser builds it | browser.navigate, then browser.get_text |
Visible text only. |
| Structured data (JSON-LD) | browser.get_text with the selector script[type="application/ld+json"] |
Returns the first matching block. If the raw HTML shows more blocks, read them there. |
| The page title as rendered | browser.get_text with the selector title |
None. |
Raw <head> (meta description, robots meta, canonical, hreflang), HTTP status, redirects |
web_request with method GET or HEAD |
Returns the status and the start of the raw response. Tags a script adds after load are not in it. |
| What loaded, what failed, how heavy it was | browser.network |
One lab visit, not real-visitor speed. |
| What the page looks like | browser.screenshot |
The current viewport only. |
Never report "no structured data" from web_fetch or raw HTML alone. Many sites add it with a script after the page loads. Only the rendered page settles it. If your tool list has a browser tool that runs a page expression (look with tool.search), use it to list every JSON-LD block and the rendered canonical and robots tags.
What ships with it
3 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.
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.
- 12d ago First seen · 135 lines · 48 tokens per session scan A 9c3d9d266e69
seo-audit is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 2,504 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 2026-10-04.
Other skills, from other repositories
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.
Check work (verify against criteria)
Verify an implementation against acceptance criteria with a reviewer and a tester.
Commit (clean, conventional)
Stage the right changes and write a clear, conventional commit message.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.