A procedure for diagnosing Acumatica business documents that are stuck or incorrect. Acumatica is an enterprise resource planning system; its transactional documents include purchase orders, receipts, bills, and sales orders.

Use it to inspect a document by number, identify its type, retrieve its lines, determine the likely cause, and propose a fix.

It provides a consistent way to investigate receiving failures, incorrect totals, documents on hold, and other status problems while accounting for known API quirks.

doc-doctor — Skill by yourlastnamesoundslikeatypeofpasta

Install

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.

Any agent

npx skills add yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server --skill doc-doctor

Clone the repo

git clone --depth 1 https://github.com/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/doc-doctor/github.svg)](https://agentmods.dev/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/doc-doctor)

Your own site

<a href="https://agentmods.dev/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/doc-doctor"><img src="https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/doc-doctor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/doc-doctor"><img src="https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/doc-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,700 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00170	$0.01700
Opus 5.5	$0.00068	$0.00680
Sonnet 5.5	$0.00034	$0.00340
Haiku 4.5	$0.00017	$0.00170

Measured 2mo ago against content hash 22c93197888a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doc-doctor 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 2mo 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.

skills/doc-doctor/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Acumatica - Document Doctor

Diagnose why a transactional document is stuck or wrong, then propose the fix. This is the tool for the "can you look at PO P0xxxxx?" requests - receive failures, total mismatches, on-hold/blocked docs.

⚠️ Known tenant behaviour

$orderby is silently ignored - sort client-side.
Date filters need datetimeoffset'YYYY-MM-DDTHH:MM:SS-04:00' literals.
$select/$filter field names must match exactly or you get a hard 500.
Always render the document number as a Markdown link using the browser_url field returned.

How to run a diagnosis

Identify the entity from the document number prefix when not stated: P -> PurchaseOrder, R -> PurchaseReceipt, numeric AP ref (e.g. 010001) -> Bill, O/I/QT -> SalesOrder, transfers/issues by ReferenceNbr.
Pull the document with its lines: get_record(entity, id, expand="Details"). Key formats: PurchaseOrder Type/OrderNbr (Type is usually Normal); PurchaseReceipt Type/ReceiptNbr; Bill Type/ReferenceNbr (Type Bill); SalesOrder OrderType/OrderNbr; TransferOrder / InventoryIssue single ReferenceNbr.
Run the matching playbook below.
Report: root cause in plain language -> the exact field(s) that prove it -> the proposed fix.
Only write after the user confirms. Show the before/after first.

Playbook - PurchaseOrder will not receive ⭐ most common

Header fields: Type, OrderNbr, Status, Hold, VendorID, OrderTotal, LineTotal, ControlTotal, Date. Line (Details) fields: LineNbr, InventoryID, OrderQty, QtyOnReceipts, Completed, Cancelled, CompleteOn, MinReceiptPercent, MaxReceiptPercent, ReceiptAction, UnitCost, ExtendedCost, WarehouseID.

Check, in order:

Line Completed = true while QtyOnReceipts < OrderQty -> the line was auto/ manually completed and is closed to further receipt. This is the classic "Status Completed, can't receive" case. Fix: reopen the PO and set the line Completed back to false (uncheck Completed per line).
CompleteOn threshold reached - when QtyOnReceipts >= OrderQty * CompleteOn/100 the line auto-completes. If they need to receive past it, the line must be reopened.
Line Cancelled = true -> line was cancelled; cannot receive. Needs re-add, not reopen.
Header Status = Completed / Closed -> reopen the order before any line will accept receipt.
Header Hold = true -> on hold; remove hold first.
MaxReceiptPercent limits over-receipt; ReceiptAction shows the over-receipt policy.

Read the full file on GitHub · 114 lines

Changes

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.

2mo ago First seen · 114 lines · 170 tokens per session scan A 22c93197888a

Subscribe to this mod's changes

doc-doctor is a skill published in the GitHub repository yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 170 tokens to every session and 1,700 once invoked, about $0.0007 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 2026-09-01.

LLM acumatica ai claude erp mcp

doc-doctor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
doc-doctoryourlastnamesoundslikeatypeofpasta/acumatica-mcp-server	Skill	0	2mo ago	MIT	A	170	Claude Code, Codex
subagent-driven-developmentNousResearch/hermes-agent	Skill	262k	today	MIT	A	17	Claude Code, Codex
mcporterNousResearch/hermes-agent	Skill	262k	today	MIT	A	16	Claude Code, Codex
article-writingaffaan-m/ECC	Skill	299k	2d ago	MIT	A	57	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	69k	2d ago	Apache-2.0	A	217	Claude Code, Codex
safe-refactorJuliusBrussee/caveman	Skill	118k	today	Apache-2.0	A	29	Claude Code, Codex
create-tech-designhumanlayer/humanlayer	Skill	13k	3d ago	Apache-2.0	A	16	Claude Code, Codex