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 blocked-page-recoverygit 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/blocked-page-recovery)<a href="https://agentmods.dev/skills/androoagi/starnet/blocked-page-recovery"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/blocked-page-recovery/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/blocked-page-recovery"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/blocked-page-recovery.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 | $0.01583 |
| Opus 5.5 | $0.00018 | $0.00633 |
| Sonnet 5.5 | $0.00009 | $0.00317 |
| Haiku 4.5 | $0.00004 | $0.00158 |
Grade A, and why
blocked-page-recovery 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blocked Page Recovery
When a page will not load for you (403/429, a "Just a moment..." challenge, a bot-detection interstitial, a page that has since changed or vanished), do not give up and do not loop on the same URL. Third-party archives often hold a copy of the page. Work down this ladder, cheapest first.
What web_fetch already tried
One web_fetch call already climbs the live rungs: it reads through Jina Reader when a JINA_API_KEY is stored in TOOLSETS & CONNECTORS → KEYS, falls back to a direct fetch, and retries bot-blocked or JavaScript-only pages once through the station's own headless browser (the result then says "read via the station browser"). So when web_fetch reports that a page cannot be read, the live routes are mostly spent. Move to copies; do not refetch the same URL.
The ladder
1. Wayback Machine — availability API, then the CDX index (dated snapshot)
2. archive.today — domain rotation: archive.ph → .md → .li → .is (dated snapshot)
3. API-first pivot — /api/, /graphql, .json, RSS/Atom, sitemap on the same host (live)
4. Station browser — browser.navigate + browser.get_text, the most expensive rung (live)
Provenance discipline (non-negotiable)
Every recovered copy carries a provenance you MUST keep when citing it:
| Route | Provenance | How to cite |
|---|---|---|
| Wayback, archive.today | snapshot | Cite WITH the snapshot date: "as archived 2026-08-06". Never present a snapshot as the live page; it can be stale. |
web_fetch (any rung), data endpoint, station browser |
live | Cite normally. |
If the Commander needs current data (prices, availability, breaking news), a snapshot is context, not an answer. Say so explicitly and state its age.
1. Wayback Machine (best provenance, try first)
- Discovery:
web_fetchhttps://archive.org/wayback/available?url=<URL>(URL-encode the target when it has its own?or&). The JSON givesarchived_snapshots.closest.urland.timestamp(YYYYMMDDhhmmss). - If
archived_snapshotsis empty (the availability API often answers empty under load even when snapshots exist), ask the CDX index for the newest good captures:web_fetchhttps://web.archive.org/cdx/search/cdx?url=<URL>&output=json&fl=timestamp,original,statuscode&filter=statuscode:200&limit=-3. Each row is[timestamp, original, statuscode]. - Read the snapshot:
web_fetchhttps://web.archive.org/web/<timestamp>id_/<original>. Theid_suffix returns the archived page itself, without the archive's toolbar. - If CDX answers 503, do not retry-hammer it. As a last Wayback attempt,
web_fetchhttps://web.archive.org/web/2/<URL>, which redirects to the newest snapshot; its date is then unconfirmed, so say that when citing.
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 · 92 lines · 44 tokens per session scan A 13380c7397ec
blocked-page-recovery 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 1,583 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.