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 competitor-news-monitorgit 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/competitor-news-monitor)<a href="https://agentmods.dev/skills/androoagi/starnet/competitor-news-monitor"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/competitor-news-monitor/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/competitor-news-monitor"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/competitor-news-monitor.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 | $0.01702 |
| Opus 5.5 | $0.00018 | $0.00681 |
| Sonnet 5.5 | $0.00009 | $0.00340 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
competitor-news-monitor 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor News Monitor
Track a declared set of companies and report only material, new developments with primary-source evidence. This is not a page-change watcher: it applies company-news categories, a source hierarchy, event deduplication and business significance. Setup runs once in chat with the Commander; the recurring check runs as a routine.
When to use
- "Monitor these competitors weekly."
- "Tell me when Company X changes pricing or launches a product."
- "Create a competitor intelligence digest."
- "Track funding, partnerships, executive moves and incidents."
- A routine fires for an existing competitor watch (steps 3-6).
Not for one-off company research (use web_search and web_fetch directly) or for reading a single feed.
Procedure - Setup (in chat, once)
1. Freeze the watchlist
Record with the Commander: canonical company names, domains, products, aliases, geography and language, the event categories to track, how often, who reads the digest, and the materiality threshold (what is big enough to report). Done when a candidate article can be accepted or rejected the same way every time.
2. Build source coverage, then schedule
For each company include, where they exist:
- official newsroom or blog, and the changelog
- pricing and product pages
- regulatory filings and investor relations
- status and security pages
- reputable trade and financial press
- job postings, as weak supporting evidence only
Open each source once with web_fetch to confirm it loads; note a feed address if the page offers one. Write the watch contract with fs.write to competitor-watches/<watch-name>.json: the watchlist, categories, materiality threshold, the source list per company, the delivery choice and a starting cutoff date. Read the file back.
Keep each watch small enough for an unattended run, which is capped at eight minutes: about five companies per routine. Split a longer list into several watches.
Check routine.list for an existing watch, then create the job with routine.create: a schedule such as 0 9 * * 1 with the Commander's timezone, and a prompt that is complete on its own, because a scheduled run sees nothing else and cannot ask questions. A prompt that works:
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 · 116 lines · 44 tokens per session scan A 99fef332500a
competitor-news-monitor 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 1,702 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
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.