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 issue-triagegit 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/issue-triage)<a href="https://agentmods.dev/skills/androoagi/starnet/issue-triage"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/issue-triage/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/issue-triage"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/issue-triage.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 | $0.00047 | $0.01242 |
| Opus 5.5 | $0.00019 | $0.00497 |
| Sonnet 5.5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
issue-triage 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage turns a pile of reports into a short list of work someone can start on, and an honest account of the rest. The bar: every item was read in full, every label has a reason, and nothing on GitHub changes until the Commander has approved the list.
Method
- Pick the road to GitHub. With a WORKBENCH, run
gh --versionandgh auth status(shell.exec); both succeed: usegh. Otherwise look for the connected GitHub account's tools (tool.search "github") and use the names it returns, never guessed ones. Neither: stop and tell the Commander to connect GitHub in ABILITIES, or to place a WORKBENCH with the GitHub CLI installed from its official site and signed in. - Learn the house labels first.
gh label list --limit 100, plus the contributing guide and issue templates if the project has them. Use the labels that exist; a new label is a proposal, not something you create. - Pull the backlog.
gh issue list --state open --limit 200 --json number,title,labels,author,createdAt,updatedAtand the same forgh pr list. If there are more than you pulled, say how many you covered out of how many. Track them with todo. - Read each one fully.
gh issue view <number> --comments— the body and every comment; the real report is often several comments down. For a pull request alsogh pr diff <number>andgh pr checks <number>. - Label by type and severity. Type: bug, feature request, question, documentation, chore. Severity for bugs: critical (data loss, a security hole, cannot start, no workaround), high (a main feature broken), medium (broken with a workaround), low (cosmetic). Give the one line of evidence behind each severity.
- Find duplicates. Search open and closed items by the exact error text and the key nouns (
gh issue list --state all --search "<text>"). A duplicate shares the cause, not just a word in the symptom. Link the original — the earliest, or the one with the best detail — and note anything new the duplicate adds (another version, another system). - Reproduce the bug reports that give steps. With a WORKBENCH, follow the steps against the project's own code at the stated version. Record exactly one of: reproduced (with the output), could not reproduce (what you tried, on which version and system), no steps given, not attempted (no WORKBENCH).
- Ask for the one missing detail. Where a report cannot be acted on, draft a single question for the one fact that blocks it — version, exact error text, or steps. Not a questionnaire.
- Write a brief for each accepted item. Four parts: what is wrong (seen against expected) · where (files and functions you confirmed with fs.search, or "not located") · how to verify (the command or steps that show it failing today) · done means (the observable finish). It must stand alone: an agent holding only the brief can start.
- Propose, then apply. Write the triage file (fs.write) ending in a numbered list of every proposed label, comment and closure. Wait for the Commander's approval, apply only the approved rows (
gh issue edit <number> --add-label,gh issue comment <number> --body-file,gh issue close <number> --reason), and re-read each item to confirm it took.
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 · 42 lines · 47 tokens per session scan A ac54a5f82141
issue-triage is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 1,242 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
linear-cli
Use when the user wants to list, view, start, create, or update Linear issues from the terminal via schpet/linear-cli, including setup, auth, repo config, and safe read/write boundaries.
jira
Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
Commit (clean, conventional)
Stage the right changes and write a clear, conventional commit message.
PR babysit (watch & drive to green)
Watch a pull request and delegate fixes until CI is green and reviews are addressed. Requires the GitHub MCP server or gh.
create-work-log
A tool that turns Git activity from configured repositories into a daily or weekly work log in Markdown. Git is a system that records changes to code, including who made them and when.