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-action-itemsgit 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-action-items)<a href="https://agentmods.dev/skills/androoagi/starnet/meeting-action-items"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/meeting-action-items/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-action-items"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/meeting-action-items.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 | $0.00039 | $0.00922 |
| Opus 5.5 | $0.00016 | $0.00369 |
| Sonnet 5.5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
meeting-action-items 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Action Items
Convert an existing transcript or set of notes into accountable follow-through. This skill begins once the notes or transcript are available, from any source. If they live in a connected meeting or storage service, retrieve them through that connector first (connectors.list shows what is connected).
When to use
- "Extract the action items from this meeting."
- "What did we decide, and who owns what?"
- "Draft the follow-up and create the tasks."
- "Reconcile these notes with the existing board."
Not for retrieving recordings or transcripts; get them first.
Procedure
1. Establish the meeting evidence
Read the provided notes or transcript with fs.read (or take the pasted text). Identify the meeting title and date, participants, source files, how complete the transcript is, and whether speaker or time references exist. Done when missing portions and low-confidence transcription are stated.
2. Separate evidence types
Extract into distinct lists:
- decisions actually made
- proposals not decided
- explicit commitments
- questions and blockers
- risks and dependencies
- facts and context
Do not turn brainstorming into decisions. Done when each candidate item has a supporting quote, timestamp, page, or note reference where one is available.
3. Normalize action items
For every commitment, record:
| Field | Rule |
|---|---|
| outcome | A concrete result, not a vague topic |
| owner | An explicitly named owner; otherwise unresolved |
| due date | An explicit date or unresolved; never invent one |
| dependency | What must happen first |
| acceptance | An observable completion condition |
| source | Transcript or note reference |
Done when every action has supported fields or visibly unresolved values.
4. Reconcile existing records
Search the system that owns the work before creating anything: the station task board (task.list) or the Commander's connected tracker. Recurring meetings breed duplicate tickets. Keep conflicts in owner, date, or status visible for the Commander to confirm rather than silently overwriting them. Done when proposed creates and proposed updates are clearly separated.
What ships with it
2 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 · 91 lines · 39 tokens per session scan A 519f22bf4d1e
meeting-action-items is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 922 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.