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 yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server --skill three-way-matchgit clone --depth 1 https://github.com/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-serverWrote 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/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/three-way-match)<a href="https://agentmods.dev/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/three-way-match"><img src="https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/three-way-match/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/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/three-way-match"><img src="https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/three-way-match.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 | $0.00151 | $0.01315 |
| Opus 5 | $0.00076 | $0.00658 |
| Sonnet 5 | $0.00030 | $0.00263 |
| Haiku 4.5 | $0.00015 | $0.00131 |
Grade A, and why
three-way-match 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 11d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acumatica - Three-Way Match (Bill <-> Receipt <-> PO)
Reconcile what was ordered (PO) vs received (receipt) vs billed (bill), line by line, and flag variances before a bill is paid. Read-only - never releases or edits a document.
⚠️ Known tenant behaviour
$orderbyis silently ignored - sort client-side.- Date filters need
datetimeoffset'YYYY-MM-DDTHH:MM:SS-04:00'literals. $select/$filterfield names must match exactly or you get a hard 500.- Decimal comparison filters (e.g.
gt 0) may 500 with "Type conversions not supported" - filter client-side instead. - Render each document number as a Markdown link from its
browser_url.
The linking chain (verified field names)
Each Bill line (Bill -> expand="Details") carries the back-references:
POOrderType, POOrderNbr, POLine -> the originating PO line, and
POReceiptType, POReceiptNbr, POReceiptLine -> the receipt line. Line amounts: Qty, UnitCost, ExtendedCost, Amount, InventoryID, LineType.
Each PurchaseReceipt line (PurchaseReceipt -> expand="Details") carries:
POOrderType, POOrderNbr, POLineNbr (link to PO line), ReceiptQty, OrderedQty, OpenQty, UnitCost, ExtendedCost, InventoryID, POReceiptNbr, POReceiptLineNbr.
Each PurchaseOrder line (PurchaseOrder -> expand="Details") carries:
LineNbr, InventoryID, OrderQty, QtyOnReceipts, UnitCost, ExtendedCost, Completed.
Goods lines carry these PO/receipt references. Non-goods bill lines (e.g. accrued warranty, freight, GL-only) have the reference fields empty - those are legitimately "no PO" and should be reported as unmatched-by-design, not as errors.
How to match a single bill
get_record(entity="Bill", id="Bill/<RefNbr>", expand="Details").- For each bill line with a
POOrderNbr, pull the PO once:get_record(entity="PurchaseOrder", id="<POOrderType>/<POOrderNbr>", expand="Details")and find the line whereLineNbr == bill.POLine. - For each bill line with a
POReceiptNbr, pull the receipt:get_record(entity="PurchaseReceipt", id="<POReceiptType>/<POReceiptNbr>", expand="Details")and find the line where itsPOReceiptLineNbr/LineNbrmatchesbill.POReceiptLine. - Compare per line (see rules) and classify each as Match, Variance, or Unmatched.
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.
- 11d ago First seen · 87 lines · 151 tokens per session scan A b2be9d53c6c6
three-way-match is a skill published in the GitHub repository yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server (0 stars, last pushed 27d ago), licensed MIT. It adds 151 tokens to every session and 1,315 once invoked, about $0.0008 per session on Opus 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 2026-09-01.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
excel-author
Build auditable financial workbooks headless via openpyxl.
hyperliquid
Hyperliquid market data, account history, trade review.
solana
Query Solana wallets, tokens, txs, and NFTs in USD.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.