ap-health

ap-health is a skill for Claude Code, Codex from yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server. It costs 58 tokens per session (3,662 once invoked), scanned A, original, MIT.

A procedure for checking accounts payable, meaning the bills a business owes its suppliers. It combines Acumatica records into a reconciled report about overdue bills, receipts without bills, and old purchase orders.

In plain words
What is it for?
Use it to answer what the business owes, find overdue vendor bills, review unpaid-receipt issues, and identify old open purchase orders.
Why use it?
It turns several related record searches into one consistent review and avoids incomplete totals when results span multiple pages or a later query fails.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to answer what the business owes, find overdue vendor bills, review unpaid-receipt issues, and identify old open purchase orders.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/ap-health
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 ap-health
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.

agentmods badge for ap-health

README.md
[![agentmods](https://agentmods.dev/badge/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/ap-health/github.svg)](https://agentmods.dev/skills/yourlastnamesoundslikeatypeofpasta/acumatica-mcp-server/ap-health)
Your own site
<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.

agentmods 80×15 button for ap-health

Your own site · 80×15
<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>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,662 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.

ModelPer sessionOnce 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

Measured 11d ago against content hash ce735a30bea4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

skills/ap-health/SKILL.md · 415 lines

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

  1. Use the current date in the user's timezone as the report date and aging date.
  2. Call describe_entity before querying an entity if its fields or key format have not already been confirmed in the current session.
  3. Run all four data queries. A failure in one query does not cancel the others.
  4. Paginate every list_records query:
    • Run the first call with the specified top and skip=0.
    • If the page contains exactly top records, call the same query again with skip increased by top.
    • Continue until a page contains fewer than top records, including zero.
    • Combine pages and deduplicate by the response id; if id is 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 and skip value.
  5. Never treat a page containing exactly top records as a complete result.
  6. Sort and aggregate client-side. Do not rely on $orderby; it is ignored on this tenant.
  7. Use decimal arithmetic for money. Round only displayed values, not intermediate sums.
  8. Format currency with a dollar sign, thousands separators, and exactly two decimals. Format percentages with exactly one decimal. Format counts as integers.
  9. 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.
  10. Report every query failure, retry, changed filter, pagination action, truncation, deduplication, and incomplete result in QUERY DEVIATIONS AND DATA COMPLETENESS.
  11. 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.
  12. Additional interpretation not required by this skill must appear only in a separate SUPPLEMENTAL ANALYSIS section after the required report.

Read the full file on GitHub · 415 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.

  1. 11d ago First seen · 415 lines · 58 tokens per session scan A ce735a30bea4

Subscribe to this mod's changes

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.