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 receipt-organizergit 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/receipt-organizer)<a href="https://agentmods.dev/skills/androoagi/starnet/receipt-organizer"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/receipt-organizer/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/receipt-organizer"><img src="https://agentmods.dev/badge/skills/androoagi/starnet/receipt-organizer.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 | $0.00050 | $0.00893 |
| Opus 5.5 | $0.00020 | $0.00357 |
| Sonnet 5.5 | $0.00010 | $0.00179 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
receipt-organizer 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A receipt pile becomes useful when every document has one row in a ledger and one obvious name. Read each document once, record only what it actually says, and never touch the originals without the Commander's go-ahead.
Method
- Find the pile. List the folder with
fs.list. Count the files by type before reading any, and say the count back: it is what "all done" will be checked against. - Read each document. Text, Word and Excel files and photos read with
fs.read. A PDF on disk does not: ask the Commander for a photo, a text export or a link, or use the PDF & Document Extraction skill when the WORKBENCH is placed. A document that will not read goes on the needs-review list with its file name; never guess its contents. - Pull out the facts. For each: vendor as printed, document date, invoice or receipt number, total, tax amount, currency, payment method if shown, and a short note of what was bought. Copy figures exactly. A field the document does not show is left blank, never filled from a guess.
- Catch the traps. Flag duplicates (same vendor, date and total), a quote or order confirmation that is not a receipt, a refund (record it as a negative), a foreign currency (keep the original currency; convert only if the Commander gives the rate), and a total that does not match its own line items.
- Agree the naming. Propose one pattern, for example
YYYY-MM-DD_vendor_amount.ext, and one folder layout (by year and month, or by category). Ask once; then use it for every file. - Write the ledger. One CSV with
fs.write: date, vendor, number, total, tax, currency, category, original file name, proposed name, status. Compute totals per month and per category withcode.runso the sums are exact, and check them against the rows. - Show the rename plan first. A table: original name → proposed name and folder. Nothing moves yet.
- Apply only on the go-ahead. Moving or renaming files needs the WORKBENCH (
shell.exec): copy into the new layout by default, move only when the Commander says "move", never delete and never overwrite an existing file. Without the WORKBENCH, deliver the ledger and the plan, and say the files were not moved. - Re-check. Count the rows against the file count from step 1, list what is still on needs-review, and name the ledger with
deliverable_note.
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 · 38 lines · 50 tokens per session scan A 347f5e1fd389
receipt-organizer is a skill published in the GitHub repository androoAGI/starnet (1,468 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 893 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
excel-author
Build auditable financial workbooks headless via openpyxl.
3-statement-model
Build integrated IS/BS/CF financial workbooks in Excel.
merger-model
Build M&A accretion/dilution workbooks in Excel.