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 project-onboardinggit 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/project-onboarding)<a href="https://agentmods.dev/skills/androoagi/starnet/project-onboarding"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/project-onboarding/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/project-onboarding"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/project-onboarding.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 | $0.00043 | $0.00911 |
| Opus 5.5 | $0.00017 | $0.00364 |
| Sonnet 5.5 | $0.00009 | $0.00182 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
project-onboarding 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.
The first hour in a new folder decides whether every later run works with the project or against it. Read before you write, and save what you learned so the next run starts from the map instead of from zero.
Method
- Get the folder trusted. Your file tools start in your private workspace. Pass the folder's absolute path: the first time you reach into it, the station asks the Commander whether you may work there (always, once, or no). Only a run the Commander is watching can ask — an unattended run is simply refused. If the answer is no, stop.
- Read the house rules first. AGENTS.md, CLAUDE.md or .cursorrules at the root are loaded into project-anchored sessions automatically; read them anyway (fs.read) and follow them over your own habits.
- Map the layout. fs.list the root (not recursive), then list the source folders one at a time — a recursive list stops at 500 entries and does not skip dependency folders. fs.search with
target: "files"skips node_modules and ignored files, so use it to survey by name. Read the entry points: README, the manifest (package.json, pyproject.toml, Cargo.toml, go.mod), build config, CI config, docs. Note what is generated or vendored and leave it out of the map. - Find how it runs. From the manifest and CI config: install, build, test and start commands, plus the runtime versions. With a WORKBENCH, run the test command once (shell.exec; the Commander approves) and record the real result — pass, fail, or not runnable and why. Without one, label the commands "from config, not run".
- Find where things live (fs.search,
target: "content"). The entry file, routing, data models, config loading, the tests. Read the two or three files everything else imports, with fs.readnumbered: trueso you can cite lines. - Read the recent past. With a WORKBENCH,
git log --oneline -20andgit statusshow what is moving and what is uncommitted. Uncommitted work belongs to someone; leave it alone. - Note the traps. Generated files that must not be hand-edited, tests that need a service running, paths the house rules forbid. (.env files and .git internals are closed to your file tools regardless.)
- Write the map (notebook.write,
scope: stream). Short declarative facts, each with where you saw it: "Tests:npm test(package.json scripts; ran 2026-09-29, all passing)." One note per topic — layout, commands, conventions, traps — not one giant note. Pin only rules the Commander confirms. - Report what you learned and what you could not confirm, and ask the one question the files could not answer, if there is one.
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 · 43 tokens per session scan A 4721847a06f8
project-onboarding is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 911 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.