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 weekly-reviewgit 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/weekly-review)<a href="https://agentmods.dev/skills/androoagi/starnet/weekly-review"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/weekly-review/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/weekly-review"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/weekly-review.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 | $0.00042 | $0.01141 |
| Opus 5.5 | $0.00017 | $0.00456 |
| Sonnet 5.5 | $0.00008 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
weekly-review 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Review and Planning
Run a bounded weekly reset across the systems the Commander actually uses. This is a concrete recurring job, not a productivity philosophy. Run it on demand, or as a weekly routine.
When to use
- "Run my weekly review."
- "What did I commit to, and what is slipping?"
- "Plan next week from my calendar, tasks, and notes."
- "Find stale projects and waiting items."
- A scheduled weekly routine fires.
Not for a daily brief, and not for working one inbox thread by thread (an inbox-triage recipe owns that).
Procedure
1. Set the systems and the window
Confirm the timezone, the review period, the planning horizon, the authoritative store for tasks and projects (the station task board via task.list, a connected tracker, or notes files), which calendars and inboxes to read, and what you may change. Call connectors.list to see what is really connected; never assume a calendar or tracker exists. Check notebook.read for standing preferences from earlier reviews. Default to recommendations and drafts, not changes. Done when every source-of-truth conflict has a declared winner.
2. Review calendar evidence
Read the connected calendar for the completed week (meetings held, commitments made), then the next 1-2 weeks (deadlines, travel, preparation, capacity). Capture follow-ups implied by past events and conflicts ahead. If no calendar is connected, say so and record it as a coverage gap. Done when both the look-back and the horizon are covered, or the gap is stated.
3. Clear capture inboxes
Review the task inbox, notes (files through fs.search and fs.read), flagged mail through a connected mail connector, and any other capture point the Commander named. Sort each item into: next action, project, waiting, scheduled, someday, reference, archive, or delete proposal. Change nothing until the scope is approved. Done when the remaining unprocessed items are counted and stated.
4. Reconcile active projects
For each project, record the desired outcome, next action, owner, deadline, blocker, last meaningful activity, and source link. Flag projects with no next action, missed dates, duplicate records, or contradictory status. Done when every active project is actionable or explicitly paused.
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 · 90 lines · 42 tokens per session scan A 0bdf761ad10f
weekly-review is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 1,141 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
orbit-general
Open Orbit briefing skill — selected by the Orbit pipeline when the user has two or more connectors connected. Pulls the past 24 hours of activity from every authenticated connector (GitHub, Linear, Notion, Slack, 飞书, Calendar, Gmail, Drive, Sentry, Vercel, …) and renders a single adaptive bento-grid dashboard at the…
orbit-gmail
Open Orbit briefing skill — selected by the Orbit pipeline when Gmail is the user's only connected connector, or when the user explicitly scopes their daily digest to Gmail. Pulls the past 24 hours of inbox activity (replies awaited, mentions, cc, auto- categorized bulk) from the user's authenticated Gmail connection…
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
discovery-question-form
Structured clarification form for unresolved material requirements.
cron
Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/update/pause/resume/delete/run, and always pass --agent-id explicitly.
cron
A procedure for creating and managing tasks that run automatically at a future time or repeat on a schedule. It uses QwenPaw's scheduling commands and requires an agent identifier.