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 ap-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/ap-health)<a href="https://agentmods.dev/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/ap-health"><img src="https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/ap-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/ap-health"><img src="https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/ap-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 | $0.00058 | $0.03662 |
| Opus 5 | $0.00029 | $0.01831 |
| Sonnet 5 | $0.00012 | $0.00732 |
| Haiku 4.5 | $0.00006 | $0.00366 |
Grade A, and why
ap-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 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 — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acumatica - AP Health Check
Run every step and produce one deterministic, reconciled report. Treat this document as an executable specification: do not omit, reinterpret, or replace queries, calculations, fallbacks, sections, or headline metrics.
Mandatory execution rules
- Use the current date in the user's timezone as the report date and aging date.
- Call
describe_entitybefore querying an entity if its fields or key format have not already been confirmed in the current session. - Run all four data queries. A failure in one query does not cancel the others.
- Paginate every
list_recordsquery:- Run the first call with the specified
topandskip=0. - If the page contains exactly
toprecords, call the same query again withskipincreased bytop. - Continue until a page contains fewer than
toprecords, including zero. - Combine pages and deduplicate by the response
id; ifidis absent, use the entity's business key. - If any later page fails, retain prior pages, mark all affected counts and
amounts as
at least/lower bound, and disclose the failed page andskipvalue.
- Run the first call with the specified
- Never treat a page containing exactly
toprecords as a complete result. - Sort and aggregate client-side. Do not rely on
$orderby; it is ignored on this tenant. - Use decimal arithmetic for money. Round only displayed values, not intermediate sums.
- Format currency with a dollar sign, thousands separators, and exactly two decimals. Format percentages with exactly one decimal. Format counts as integers.
- Render every cited Bill, Purchase Receipt, and Purchase Order identifier as
a Markdown hyperlink using its
browser_url. If absent, construct the link using the URL rules in the "Deep links" section. - Report every query failure, retry, changed filter, pagination action,
truncation, deduplication, and incomplete result in
QUERY DEVIATIONS AND DATA COMPLETENESS. - Do not make unsupported narrative claims such as "virtually all", "mostly", or "significant". Quantify the claim with a count, amount, or percentage, or omit it.
- Additional interpretation not required by this skill must appear only in a
separate
SUPPLEMENTAL ANALYSISsection after the required report.
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 · 415 lines · 58 tokens per session scan A ce735a30bea4
ap-health is a skill published in the GitHub repository yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server (0 stars, last pushed 27d ago), licensed MIT. It adds 58 tokens to every session and 3,662 once invoked, about $0.0003 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.