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 rossumai/claude-marketplace --skill netsuite-referencegit clone --depth 1 https://github.com/rossumai/claude-marketplaceWrote 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/rossumai/claude-marketplace/netsuite-reference)<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/netsuite-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/netsuite-reference/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/rossumai/claude-marketplace/netsuite-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/netsuite-reference.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 | $0.00217 | $0.00692 |
| Opus 5.5 | $0.00087 | $0.00277 |
| Sonnet 5.5 | $0.00043 | $0.00138 |
| Haiku 4.5 | $0.00022 | $0.00069 |
Grade A, and why
netsuite-reference 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 1mo 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.
What it actually says
NetSuite Integration Reference
Rossum integrates with NetSuite through two Rossum-hosted services:
- SOAP connector (
svc/netsuite-v3) — webhook hooks for both directions: importing NetSuite records into Master Data Hub datasets, and exporting vendor bills / credits (with the source PDF attached) back to NetSuite. Production-proven. - REST import (
netsuite_rest_import) — ajobhook that imports one dataset per hook with a SuiteQL query. Released for acceptance in October 2026; several features are still missing (see reference.md → REST import: what is not there yet). There is no REST export — export stays on the SOAP connector.
Oracle removes SOAP web services with NetSuite release 2028.2, and new TBA (and therefore new SOAP) integrations are blocked from 2027.1. New work should plan for the REST import, and for OAuth 2.0 on it.
For wiring, payloads, dataset shapes, the export mapping, the REST hook, SuiteQL rules, migration and gotchas, see reference.md.
Use this knowledge when:
- Wiring or reviewing a NetSuite import or export hook
(
https://<region host>/svc/netsuite-v3/api/v1/import|export, or anetsuite_rest_importjob hook) - Writing SOAP search payloads (
*SearchBasic,*SearchAdvancedwith joins) or SuiteQL queries - Reading NetSuite datasets in MDH matching (
internalId, nestedRecordRefs, advanced-searchbasic.<column>[0].searchValuerows, flat lowercase REST rows) - Building the export mapping —
RecordRefs, item vs expense lines, attachments - Migrating a SOAP import to REST, or planning around the SOAP removal
Related packs: workday-reference documents the mapping template language the SOAP export
shares (@{…}, $IF_SCHEMA_ID$, $FOR_EACH_SCHEMA_ID$, $DATAPOINT_MAPPING$);
mdh-reference covers the matching that reads the imported datasets.
What ships with it
1 file 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.
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.
- 1mo ago First seen · 39 lines · 217 tokens per session scan A b6ed285ead04
netsuite-reference is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 217 tokens to every session and 692 once invoked, about $0.0009 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 2026-10-09.
netsuite-reference compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| netsuite-referencerossumai/claude-marketplace | Skill | 5 | 5d ago | MIT | A | 217 | Claude Code |
| x402browser-use/browser-use | Skill | 121k | today | MIT | A | 166 | Claude Code |
| tushareHKUDS/Vibe-Trading | Skill | 38k | today | MIT | A | 79 | Claude Code, Codex |
| stripe-best-practicesstripe/ai | Skill | 2.1k | yesterday | MIT | A | 161 | Claude Code, Codex |
| hyperliquid-websocketgalleonlabs/hypergrok-trading-desk | Skill | 485 | 7d ago | MIT | A | 89 | Claude Code |
| wechatpay-payment-integrationwechatpay-apiv3/wechatpay-skills | Skill | 373 | 9d ago | MIT | A | 330 | Claude Code, Codex |
| build-a-stripe-integrationsuperset-sh/superset | Skill | 16k | 4d ago | MIT | A | 74 | Claude Code |