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 teach-megit 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/teach-me)<a href="https://agentmods.dev/skills/androoagi/starnet/teach-me"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/teach-me/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/teach-me"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/teach-me.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 | $0.00047 | $0.02368 |
| Opus 5.5 | $0.00019 | $0.00947 |
| Sonnet 5.5 | $0.00009 | $0.00474 |
| Haiku 4.5 | $0.00005 | $0.00237 |
Grade A, and why
teach-me 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teach Me
The Commander has asked you to teach them something. This is a stateful request: they intend to learn the topic over many sessions, so what you know about their progress has to live in files, not in this conversation.
When to use
- "Teach me X." / "I want to learn X."
- "Let's continue my lessons on X."
- "What should I learn next?" about a topic that already has a teaching workspace.
Not for a one-off explanation: answer those directly.
Teaching workspace
Each topic gets its own folder in your workspace: teaching/<topic-name>/. One mission per folder; two unrelated topics are two folders. The state of the Commander's learning is captured there:
MISSION.md— the reason the Commander wants this. It grounds all teaching.RESOURCES.md— trusted sources to draw knowledge from, and communities to draw wisdom from.GLOSSARY.md— the agreed words for this topic. Once a term is here, use it in every lesson.NOTES.md— your scratchpad: how the Commander likes to be taught, and working notes.learning-records/0001-<dash-case-name>.md— what the Commander has learned. Like decision records in software: non-obvious lessons and key insights that steer future sessions. The number goes up by one each time.lessons/0001-<dash-case-name>.html— the lessons. A lesson is one self-contained file that teaches one tightly scoped thing tied to the mission. It is the main unit of teaching.reference/— the compressed learnings: cheat sheets, algorithms, syntax, routines, the things the Commander will come back to.assets/— the master copies of parts that lessons share: the style block, quiz layouts, diagram helpers.
The formats for the mission, resources, glossary and learning records are in references/formats.md (included at the end of this skill). Create folders lazily, when the first file needs them.
Every session starts the same way
- Find the workspace. Check
notebook.readfor the saved path, or look withfs.listunderteaching/. If several topics exist and the Commander did not say which, ask. - Read
MISSION.md,NOTES.md,GLOSSARY.mdand the learning records withfs.read. They tell you what is known and what comes next. Never restart from zero when records exist. - For a new topic, create the folder, then go straight to the mission. When the first file is written, save the workspace path with
notebook.writeso the next session finds it. - Open with a short recall check on something from an earlier session: ask, wait, then give feedback. Spacing practice out over time is what makes it stick.
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 · 176 lines · 47 tokens per session scan A f3f5bf64da2c
teach-me is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 2,368 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
hps-academic-paper
A review deck on compositional generalization in large language models — the field map, the gap, the evidence, and open questions. Built as a decision-grade academic research deck for PI, lab group, reviewers.
fs-notebook-tabs
A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.
hps-bauhaus
A visual-design fundamentals course for new brand designers — grid, type, color, and the exercises that build the eye. Built as a decision-grade professional training deck for junior designers, new hires.
hps-memphis-pop
A pop-culture retrospective on how 1980s design language shaped today's apps — the scenes, the turning point, and the takeaway. Built as a decision-grade story deck for talk audience, design community.
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
html-ppt-zhangzara-cartesian
An economics senior thesis on the employment effects of local minimum-wage increases — identification strategy, evidence, and limitations. Built as a decision-grade coursework defense deck for thesis committee.