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 threat-modelgit 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/threat-model)<a href="https://agentmods.dev/skills/androoagi/starnet/threat-model"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/threat-model/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/threat-model"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/threat-model.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 | $0.00058 | $0.01678 |
| Opus 5.5 | $0.00023 | $0.00671 |
| Sonnet 5.5 | $0.00012 | $0.00336 |
| Haiku 4.5 | $0.00006 | $0.00168 |
Grade A, and why
threat-model 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Model a Source Code Repository
Deliver an actionable, AppSec-grade threat model that is specific to the repository or project path in front of you, not a generic checklist. Anchor every architectural claim to evidence in the repo and keep assumptions explicit. Put realistic attacker goals and concrete impacts ahead of generic vulnerability lists.
When to use
Use this only when the Commander explicitly asks to threat model a codebase or a path, to enumerate threats or abuse paths, or for application-security threat modeling.
Do not use it for a general architecture summary, a code review (code-review), or non-security design work. For a hunt for concrete vulnerabilities and leaked secrets, security-sweep is the closer fit; a threat model says where to look and why.
Quick start
- Collect (or infer) the inputs:
- The repo root and any in-scope paths. The project must be a folder you can read: your workspace, or a project folder the Commander trusted.
- Intended usage, deployment model, internet exposure, and authentication expectations, if known.
- Any existing repository summary or architecture document (
fs.searchfor README, ARCHITECTURE, docs/).
- Read
references/output-contract.md. It holds the working rules, the repository-summary brief, the full process, and the required output format. Follow the output format as written. - Explore with the station's file tools:
fs.listfor the shape of the repo,fs.searchfor the surfaces listed in the contract,fs.readfor the files that matter. Read-only: do not run the project's code to build a threat model.
Workflow
1) Scope and extract the system model
- Identify the primary components, data stores, and external integrations from the repo.
- Identify how the system runs (server, CLI, library, worker) and its entry points.
- Separate runtime behavior from CI, build and developer tooling, and from tests and examples.
- Map the in-scope locations to those components, and exclude out-of-scope items explicitly.
- Do not claim components, flows, or controls without evidence.
What ships with it
5 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 · 112 lines · 58 tokens per session scan A 5352c98f7341
threat-model is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 1,678 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.