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 ar-healthgit 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/ar-health)<a href="https://agentmods.dev/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/ar-health"><img src="https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/ar-health/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/ar-health"><img src="https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/ar-health.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 | $0.00055 | $0.01388 |
| Opus 5.5 | $0.00022 | $0.00555 |
| Sonnet 5.5 | $0.00011 | $0.00278 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
ar-health 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acumatica - AR Health Check
A multi-query accounts receivable audit. Run all steps and compile into a single report.
Acumatica mechanics (read first)
- Field names are never guessed. Use only names from
describe_entity(or the exact queries below). A wrong name infilter=/select=returns HTTP 500KeyNotFoundException. $orderbyis silently ignored. For "most recent", filter a narrow date window and widen (14 -> 30 -> 90 days), then sort client-side:filter="Date gt datetimeoffset'2026-06-22T00:00:00-04:00'"(compute the date from today).- Decimal literals fail in filters.
Amount gt 0returns "Type conversions are not supported" - drop the numeric clause and filter client-side. - Paginate. Default
topis 50. If a call returns exactlytoprows, repeat withskip=until a short page comes back - never report a full page as the complete total. - Large results may arrive as a file path instead of inline JSON. Read the file and aggregate (jq / Python); do not re-run the query hoping it shrinks.
- Always pass
select=with only the fields you need. StockItem and ItemWarehouse are enormous without it. - Link every document. Render the primary identifier (RefNbr / OrderNbr / ID) as a
Markdown hyperlink using the record's
browser_urlfield. - On any error, read the
hintfield in the tool response - the server translates common 500s into the corrective action. - Invoice
DueDatefilters can be dropped silently by the server - if you filter onDueDate, verify the returned rows actually honor the bound (or queryBillinstead for AP). This skill avoids the problem by pulling open invoices and bucketing byDueDateclient-side. - Payment's date field is
ApplicationDate, notDate- filteringPaymentonDatereturns 500.
Step 1 - Open invoices (AR balance)
list_records(
entity="Invoice",
filter="Type eq 'Invoice' and Status eq 'Open'",
select="ReferenceNbr,Customer,Date,DueDate,Amount,Balance,Description",
top=1000
)
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 · 152 lines · 55 tokens per session scan A ef44ca391206
ar-health is a skill published in the GitHub repository yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 1,388 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 2026-09-01.
ar-health compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ar-healthyourlastnamesoundslikeatypeofpasta/acumatica-mcp-server | Skill | 0 | 2mo ago | MIT | A | 55 | Claude Code, Codex |
| dcf-modelNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| comps-analysisNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 13 | Claude Code, Codex |
| hyperliquidNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 16 | Claude Code, Codex |
| stocksNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 15 | Claude Code, Codex |
| polymarketNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 18 | Claude Code, Codex |
| connect-recommendstripe/ai | Skill | 2.0k | yesterday | MIT | A | 151 | Claude Code, Codex |