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 lead-magnetsgit 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/lead-magnets)<a href="https://agentmods.dev/skills/androoagi/starnet/lead-magnets"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/lead-magnets/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/lead-magnets"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/lead-magnets.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 | $0.02398 |
| Opus 5.5 | $0.00019 | $0.00959 |
| Sonnet 5.5 | $0.00010 | $0.00480 |
| Haiku 4.5 | $0.00005 | $0.00240 |
Grade A, and why
lead-magnets 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Magnets
Plan a lead magnet: a free resource people trade their email address for, which attracts the right people and leads naturally toward the product. The bar: one specific problem, one format, an outline the Commander can build from, and a promotion and measurement plan with honest numbers.
When to use
- "What should I give away to get emails?" "Plan a checklist, template, guide or email course."
- "Turn this blog post into a download."
- An existing lead magnet that collects emails but not customers.
Not for the landing page copy itself (landing-copy), the emails that follow the sign-up (email-sequence), the publishing schedule (content-calendar), ad variations (ad-copy-testing), or a review of the finished capture page (conversion-review).
Method
- Gather context. Look for a product brief and existing content in the workspace with
fs.search, then ask only for what is missing:- Business: what the company does, the ideal customer, the problems the product solves.
- Today: how leads are captured now, what offers exist, the current sign-up rate.
- Assets: posts, guides, data, internal templates and expertise that could be reused.
- Goal: list growth, lead quality or product education; which buyer stage; time and budget.
- Pick the topic. One specific problem, not a broad subject. A good source is the question prospects most often ask before buying. If the DISH is placed, check what competitors already offer (
web_search,web_fetch) so the Commander's is not a copy of something freely available. - Pick the format by buyer stage and effort, using the tables below.
- Test it against the five principles. Change the topic or format until all five hold.
- Outline it. Use the structure for the chosen format in
references/format-guide.md(included at the end of this skill). Give title options, every section with its key points, target length, what makes it worth having, and the next step toward the product at the end. - Plan the exchange. What is gated, which fields are asked for, how the offer is framed.
- Plan the page and delivery. Landing page structure, delivery method, thank-you page.
- Plan promotion. Which channels, in what order, with what the Commander already has.
- Plan measurement. The numbers to watch and the first thing to test.
- Write the plan, save it with
fs.write, and name it withdeliverable_note. Offer to draft the magnet itself next if it is a text format (checklist, cheat sheet, guide, template text, email course).
What ships with it
4 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 · 156 lines · 48 tokens per session scan A 3d03b02f2b32
lead-magnets 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 2,398 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.