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 hallboys/MCP4Acumatica --skill acumatica-gi-descriptionsgit clone --depth 1 https://github.com/hallboys/MCP4AcumaticaWrote 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/hallboys/mcp4acumatica/acumatica-gi-descriptions)<a href="https://agentmods.dev/skills/hallboys/mcp4acumatica/acumatica-gi-descriptions"><img src="https://agentmods.dev/badge/skills/hallboys/mcp4acumatica/acumatica-gi-descriptions/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/hallboys/mcp4acumatica/acumatica-gi-descriptions"><img src="https://agentmods.dev/badge/skills/hallboys/mcp4acumatica/acumatica-gi-descriptions.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 | $0.00150 | $0.02214 |
| Opus 5.5 | $0.00060 | $0.00886 |
| Sonnet 5.5 | $0.00030 | $0.00443 |
| Haiku 4.5 | $0.00015 | $0.00221 |
Grade A, and why
acumatica-gi-descriptions 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 3d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Describing Generic Inquiries for AI consumption
A GI name tells a model almost nothing. PO-Receipt and PO Receipt History Analysis are different grains of different tables; GL-Trial Balance may not be
a trial balance at all. When several GIs are exposed under names like these, a
model picks by vibes and answers confidently from the wrong one.
The fix is a description per GI and per result column — but a description invented from the name just launders a guess into something that looks authoritative. Everything here exists to make descriptions fall out of the GI's actual design.
Tag legend
This skill mixes platform behaviour with instance-specific observations. Keep them apart, or you will carry one tenant's configuration into another as if it were a rule.
[UNIVERSAL]— Acumatica platform/API behaviour. Holds for any tenant on a comparable version. Safe to rely on; still confirm the release.[TENANT]— depends on a specific instance's configuration, customization or data. Never copy the value into another engagement — only the lesson.
The pipeline
Work in this order. Each step feeds the next, and skipping the metadata pull is what produces plausible-sounding fiction.
- Inventory every GI, with parameter count and exposure flags.
- Select which GIs are worth describing. Most instances have hundreds; a large menu is as useless to a model as an undescribed one.
- Pull design metadata for the selection: result columns, joins, conditions.
- Build a per-GI brief that condenses that metadata into something writable.
- Draft GI-level, then column-level descriptions.
- Validate mechanically before anyone reads them.
- Load into Acumatica and verify by reading back.
references/workflow.md has the concrete steps, queries and slicing strategy.
Read it when you start step 1.
The rules that actually bite
These are the ones that produce confidently wrong output if ignored. Each cost real debugging time.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/description-spec.md 3.5 KB
- references/design-signals.md 6.2 KB
- references/platform.md 11 KB
- references/workflow.md 7.5 KB
- scripts/align_columns.mjs 20 KB runs code
- scripts/audit_truncation.mjs 2.5 KB runs code
- scripts/build_brief.mjs 5.1 KB runs code
- scripts/validate_descriptions.mjs 4.7 KB runs code
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.
- 3d ago Changed · +2 lines 470040b5c403
- 2mo ago First seen · 185 lines · 150 tokens per session scan A 6e4926c4a22b
acumatica-gi-descriptions is a skill published in the GitHub repository hallboys/MCP4Acumatica (20 stars, last pushed 3d ago), licensed Apache-2.0. It adds 150 tokens to every session and 2,214 once invoked, about $0.0006 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 2026-08-30.
acumatica-gi-descriptions compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| acumatica-gi-descriptionshallboys/MCP4Acumatica | Skill | 20 | 3d ago | Apache-2.0 | A | 150 | Claude Code, Codex |
| opik-diagnosecomet-ml/opik-mcp | Skill | 225 | 9d ago | Apache-2.0 | A | 187 | Claude Code |
| ue-mcp-epic-routingdb-lyon/ue-mcp | Skill | 476 | yesterday | MIT | A | 81 | Claude Code, Codex |
| qa-knowledgegriddynamics/rosetta | Skill | 370 | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| apitapn1byn1kt/apitap | Skill | 131 | 17d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| frontmcp-setupagentfront/frontmcp | Skill | 148 | yesterday | Apache-2.0 | A | 176 | Claude Code, Codex |
| x-use-reviewihuzaifashoukat/x-use | Skill | 181 | 4d ago | MIT | A | 56 | Claude Code |