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 mapsgit 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/maps)<a href="https://agentmods.dev/skills/androoagi/starnet/maps"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/maps/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/maps"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/maps.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 | $0.00045 | $0.02958 |
| Opus 5.5 | $0.00018 | $0.01183 |
| Sonnet 5.5 | $0.00009 | $0.00592 |
| Haiku 4.5 | $0.00005 | $0.00296 |
Grade A, and why
maps scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- If the WORKBENCH is placed and the Commander wants the steps in chat, save the response with `shell.exec` (`curl -s -A "StarNet maps skill" -o route.json "<the routing URL>"`) and page through it with `fs.read`. How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maps
Location intelligence from free, open data services, called directly with web_request. No API key, no install, no scripts.
Services: Nominatim (OpenStreetMap geocoding), the Overpass API (OpenStreetMap place search), OSRM routing on the FOSSGIS servers, and TimeAPI.io.
When to use
- The Commander shares coordinates or a location pin (latitude/longitude in a message, for example from a connected chat channel) and asks what is nearby → nearby
- Coordinates for a place name → search
- An address for coordinates → reverse
- Nearby restaurants, pharmacies, hospitals, hotels, and similar → nearby
- Driving, walking, or cycling distance or travel time → distance
- Turn-by-turn directions → directions
- The timezone of a location → timezone
- Places inside a named area → area, then bbox
Rules for every call
- Use
web_request(GET unless stated). Each call can ask the Commander for approval, so plan the fewest calls that answer the question. - Identify yourself. Always send the header
"User-Agent": "StarNet maps skill". The OpenStreetMap services refuse or throttle anonymous browser-like clients. - Rate limits: at most 1 request per second to Nominatim and to the routing server, no bulk geocoding, no scraping. Reuse results you already have in this conversation instead of asking again.
- URL-encode every value you put in a query string (spaces, commas, quotes, brackets, semicolons, newlines).
- Response window:
web_requestreturns about 8,000 characters of body. Keeplimitsmall (3-5 for geocoding, about 10 for places) and use the compact CSV output for place lists. - Attribution: end location answers with "Data © OpenStreetMap contributors (ODbL)".
- Order: Nominatim and Overpass use latitude, longitude. OSRM URLs use longitude,latitude. Getting this backwards is the most common error.
search: geocode a place name
GET https://nominatim.openstreetmap.org/search?q=<place, URL-encoded>&format=jsonv2&limit=3&addressdetails=1
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 · 166 lines · 45 tokens per session scan A 008e62460e89
maps is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 2,958 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.
Check work (verify against criteria)
Verify an implementation against acceptance criteria with a reviewer and a tester.
Commit (clean, conventional)
Stage the right changes and write a clear, conventional commit message.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.