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 notes-vaultgit 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/notes-vault)<a href="https://agentmods.dev/skills/androoagi/starnet/notes-vault"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/notes-vault/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/notes-vault"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/notes-vault.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 | $0.00878 |
| Opus 5.5 | $0.00018 | $0.00351 |
| Sonnet 5.5 | $0.00009 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
notes-vault 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notes Vault
Use this skill for filesystem-first work in a Markdown notes vault: a folder of .md notes such as an Obsidian vault. It covers reading notes, listing notes, searching note files, creating notes, appending content, and adding wikilinks.
Vault path
Resolve a concrete vault path before calling any file tool.
- Check
notebook.readfor a saved vault path first. If there is none, ask the Commander where the vault lives, then save it withnotebook.write(for example "Notes vault: ") so later sessions reuse it. - If the Commander is unsure, a common default is
Documents/Obsidian Vaultin their home folder. A folder that contains a hidden.obsidian/directory is a vault root. - File tools take a concrete absolute path. Never pass
~or an environment-variable reference as a path; resolve it first. - The vault lives outside your workspace, so the first file-tool call on it asks the Commander to trust that folder. After they approve, the file tools work there directly. An unattended routine can only use a vault folder that was already trusted.
- Vault paths often contain spaces. That is another reason to prefer the file tools over shell commands.
Read a note
Use fs.read with the absolute path to the note. Pass numbered: true when you need to cite or edit exact lines; use offset and limit to page long notes.
List notes
Use fs.search with target: "files", query: "*.md", and path set to the vault (or a subfolder) path. For a small vault, fs.list with recursive: true also works. Prefer these over shell dir, ls, or find.
Search
Use fs.search for both filename and content searches.
- Filenames:
target: "files"with a filename glob asquery. - Note contents:
target: "content"with the text asqueryandfile_glob: "*.md". Addregex: truefor a regular expression,ignoreCase: trueto ignore case, andoutput_mode: "files_only"when you only need which notes match. - Hidden folders such as
.obsidian/(the vault's app settings) are skipped, which is what you want.
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 · 62 lines · 44 tokens per session scan A f35b40abb22f
notes-vault 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 878 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
html-ppt
For consulting delivery work: turn diagnosis, frameworks, and project work into a client-adoptable action plan. Built around the core query "consulting-final-deck", with engagement manager judgment, buyer-ready proof, and this outcome: accept the recommendation and commit owners to the roadmap.
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
ib-pitch-book
OpenDesign's investor pitch book: market map, moat, unit economics, and the ask — analyst-grade and diligence-ready. Built as a decision-grade fundraising pitch deck for growth-equity investors.
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.
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…