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 deliverable-handoffgit 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/deliverable-handoff)<a href="https://agentmods.dev/skills/androoagi/starnet/deliverable-handoff"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/deliverable-handoff/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/deliverable-handoff"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/deliverable-handoff.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 | $0.00044 | $0.00797 |
| Opus 5.5 | $0.00018 | $0.00319 |
| Sonnet 5.5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
deliverable-handoff 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work the Commander cannot find did not happen. The station already records which files a run wrote; your job is to make those files the obvious, openable answer — named for what they are, in a format that previews, with the one that matters marked.
Method
- Decide the deliverable before you write it. One sentence: which file the Commander will open and what they will do with it — a report, a table, an image set, a patch.
- Pick formats that open where they look. The DELIVERABLES library previews Markdown (.md), CSV (.csv) and images (.png, .jpg, .gif, .webp) right in the card. Use .md for documents, .csv for tables, an image format for pictures. Use another format only when the Commander asked for it or the next tool needs it.
- Know where files land. fs.write writes into the current project folder when the session is anchored to one, otherwise into your private workspace. Studio tools default to
images/,audio/andedits/. In a project, put deliverables where the project keeps such things; otherwise use one short folder named for the job. - Name files for a human.
2026-09-vendor-comparison.md, notoutput.mdorfinal_v2_new.md. Date-prefix anything periodic. Never overwrite a file the Commander already approved — write the new version beside it. - Make the main file stand alone. Its first lines say what it is, the date, and the sources used. It must make sense opened cold, weeks later, without this conversation.
- Keep supporting files beside it and link them from the main file by relative path.
- Read back what you wrote (fs.read). Confirm it saved, it is complete, and nothing is truncated or still a placeholder.
- Name the work once (deliverable_note), at the end, and only if you created or changed files:
title(a plain name, not a filename),summary(one sentence saying what it is),kind(doc, data, page, patch, image or files) andmain(the path of the file that is the deliverable). - Close with a pointer, not a recap. Tell the Commander the title, the main path, and the one thing to look at first. If crew made files, point to them as "'s workspace: ".
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 · 37 lines · 44 tokens per session scan A e7fcc3d88cf4
deliverable-handoff is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 797 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.