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 meeting-prepgit 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/meeting-prep)<a href="https://agentmods.dev/skills/androoagi/starnet/meeting-prep"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/meeting-prep/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/meeting-prep"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/meeting-prep.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 | $0.00056 | $0.00905 |
| Opus 5.5 | $0.00022 | $0.00362 |
| Sonnet 5.5 | $0.00011 | $0.00181 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
meeting-prep 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A meeting brief is read in the two minutes before the call. One page, every fact traceable to where it came from, and an honest "unknown" wherever you found nothing.
Method
- Pin the meeting. Title, date and time with time zone, attendees, who asked for it. Take them from the Commander or from the event in the connected calendar (find the calendar tools with
tool.search; never guess a tool name). If the purpose is unclear, ask one question: "What do you need to walk out with?" - Search your own records first.
notebook.readfor each person and company,recall_conversationfor earlier talks about them,fs.searchfor past briefs and notes in the workspace. Keep the date of each finding. - Read the past threads. With the connected Google account's mail tools, find the latest threads with the attendees: what was asked, who promised what, what is still unanswered. No mail connected: write "past threads: not read".
- Add the public picture, lightly.
web_searchthenweb_fetchfor each attendee's current role and company, plus company news from the last three months that bears on the goal. Make sure it is the right person (name, company and city agree); if you cannot tell two people apart, say so and add nothing. Work facts only: no home address, family or private accounts. - State the goal and the decision. One sentence each: what the Commander wants from this meeting, and what must be decided and by whom. Still unclear after asking: write "goal not confirmed".
- Draft the agenda. Three to five items with minutes. Put the decision early, not last.
- Carry over last time. Open items and promises: who owes what, since when. The Commander's own unkept promises go first; those are the ones that get asked about.
- Write the questions. Three to five that only this meeting can answer. Mark the one that matters most.
- Suggest the first sentence. One natural line, in the Commander's voice, that sets the goal.
- Assemble one page and save it. Fixed order: Meeting, Goal, Decision needed, People, Agenda, Open from last time, Questions, First sentence, Sources, Unknown.
fs.writetomeetings/YYYY-MM-DD-<short-name>-brief.md, re-read it, then name it withdeliverable_note.
What ships with it
1 file 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 · 41 lines · 56 tokens per session scan A 7706ab06099b
meeting-prep is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 905 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
flowai-live-dashboard-template
Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity sparklines, and a top-contributors panel, all in a single self-contained HTML file with light/dark theming, hoverable…
weekly-update
OpenDesign's weekly metrics standup: this week's numbers, the one anomaly, and the single decision it forces. Built as a decision-grade data & finance deck for ops & growth team.
code-import
Read an existing repository's structure into the project cwd as a normalised snapshot the agent can analyse without re-walking the tree on every turn.
pm-spec
A product-specification page skill for documenting a feature's problem, goals, user stories, success measures, rollout plan, and open questions. A PRD is a document that explains what a product feature should achieve and why.
team-okrs
OKR tracker page — quarter banner, three objectives with their key results as progress bars, owner avatars, status pills, and a "this quarter at a glance" sidebar. Use when the brief mentions "OKRs", "key results", "objectives", or "目标".
huashu-keynote-black
OpenDesign's all-hands: the year in review, the three priorities, and what every team owns next quarter. Built as a decision-grade corporate strategy deck for whole company.