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 brand-assetsgit 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/brand-assets)<a href="https://agentmods.dev/skills/androoagi/starnet/brand-assets"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/brand-assets/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/brand-assets"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/brand-assets.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 | $0.00038 | $0.00840 |
| Opus 5.5 | $0.00015 | $0.00336 |
| Sonnet 5.5 | $0.00008 | $0.00168 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
brand-assets 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.
A set looks like a brand when every piece follows the same written rules. image_generate takes no reference image, so consistency lives in the words: one style sheet, repeated exactly, and every result checked against it.
Method
- Read what is already approved (notebook.read). Search for the brand or project name. If a style sheet exists, use it as written; a new set that ignores the old one is a second brand.
- Write the style sheet. Five to eight concrete lines: palette (named colors or hex values), rendering style (flat vector, clay 3D, film photo), lighting, line weight, composition (subject centered, wide margin), and what never appears. Concrete beats adjectives — "two colors plus white, thick rounded outlines" survives a hundred prompts; "clean and modern" does not survive one.
- Get it approved on one piece. Generate a single hero image, show it, and revise until the Commander says yes.
- Pin the approved rules (notebook.write with
pinned: true). Save the style sheet and the approved file's path as a declarative fact, withscope: streamfor this project. Pinned requirements stay in context on later runs. Read that approved file again before every new variant. - Fix the formats per asset type. Decide once and reuse:
"16:9"for banners,"9:16"for stories,"1:1"for avatars and icons — or exactwidth+heightwhen the Commander names pixels. Name files by set and role withpath:brand/cover-launch.png,brand/icon-app.png. - Generate with the sheet pasted verbatim. Every prompt is the style sheet word for word, then one subject line. Only the subject changes. Keep one model per kind of asset: the default model for the set; the premium model the tool description names only for pieces that must carry readable text (and for all of those); and cutouts as their own sub-set, because
transparent: truegenerates on its own model. - Cutouts: ask for real transparency. Set
transparent: truefor logos, stickers and icons. The tool checks the saved file and says plainly when it came back opaque. An opaque result is a failure — regenerate; never deliver a painted checkerboard as a cutout. - Check every file against the sheet (image_analyze). Ask a pointed question: "Does this use only these colors, this outline weight, this composition? List every deviation." Regenerate deviations and keep a short note of what failed and why.
- Review the set side by side. Name the odd one out, if any, and redo it. Consistency is judged across the set, not file by file.
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 · 38 tokens per session scan A 93cea920683e
brand-assets is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 840 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
fs-electric-studio
OpenDesign as an enterprise design platform: a buyer-forwardable proposal for a design-org's economic buyer — pain, value, ROI, rollout. Built as a decision-grade B2B sales deck for economic buyer, design VP, procurement.
hps-true-blueprint
OpenDesign's engineering blueprint: how the sandbox, sidecar, and daemon fit — the system diagram and the invariants. Built as a decision-grade product management deck for engineering org.
ve-terminal-mono
OpenDesign from the CLI: driving the full design workflow with the od command — scripted, composable, agent-ready. Built as a decision-grade AI literacy deck for developers, power users.
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
hps-bauhaus
A visual-design fundamentals course for new brand designers — grid, type, color, and the exercises that build the eye. Built as a decision-grade professional training deck for junior designers, new hires.
hps-memphis-pop
A pop-culture retrospective on how 1980s design language shaped today's apps — the scenes, the turning point, and the takeaway. Built as a decision-grade story deck for talk audience, design community.