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 IvanBBaev/servicenow-mcp-ai --skill sn-discovergit clone --depth 1 https://github.com/IvanBBaev/servicenow-mcp-aiWrote 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/ivanbbaev/servicenow-mcp-ai/sn-discover)<a href="https://agentmods.dev/skills/ivanbbaev/servicenow-mcp-ai/sn-discover"><img src="https://agentmods.dev/badge/skills/ivanbbaev/servicenow-mcp-ai/sn-discover/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/ivanbbaev/servicenow-mcp-ai/sn-discover"><img src="https://agentmods.dev/badge/skills/ivanbbaev/servicenow-mcp-ai/sn-discover.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 | $0.00053 | $0.00811 |
| Opus 5.5 | $0.00021 | $0.00324 |
| Sonnet 5.5 | $0.00011 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
sn-discover 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sn-discover — native instance discovery
Discovery runs inside the ServiceNow MCP server: one call to
servicenow_document_instance with a depth writes the files under
<SN_DOCS_DIR>/<profile>/discovery/. This skill holds no credentials and
makes no HTTP calls of its own — the server's profile, table policy,
redaction, capability preflight and write journal apply to every read and
file.
When not to use
- A question about one record, table or script — answer it directly, or hand
it to the
sn-investigatorsubagent (where the client has it) so the raw records stay out of the conversation. - Comparing instances or reviewing an update set — use sn-drift.
- Any change to the instance — use sn-safe-write.
Steps
- Packages: this skill calls tools from
docs, which the defaultdiscoveryprofile leaves off. ReadenabledPackagesinservicenow_get_status; for a missing package, enable it with the server'senable_packageadmin tool and tell the user, or ask the operator to add it toSN_TOOL_PACKAGES. A package listed indeniedPackagescannot be enabled — skip the steps that need it and report them as not checked. - Confirm the target:
servicenow_list_instances, thenservicenow_test_connectionfor the profile you will document. Switch withservicenow_use_instanceonly if the user asked for another instance. - Pick the tier (cumulative):
overview—discovery/overview.md: version, counts, automation.apps— addsdiscovery/apps.mdanddiscovery/tables-<scope>.mdper custom application (tables and their own dictionary columns).artefacts— addsdiscovery/artifacts-<scope>.mdper scope: every artefact type the server knows, with "collected / not collected and why" (no records, unverified, unreadable, package off, cap).
- Call
servicenow_document_instance({ depth }). Passapps: [...]to limit the scopes; without it everysys_appscope is covered (at most 50 per run — the rest are listed as a caveat). Addwrite: falsefor a dry run that returns the Markdown instead of writing it. - Read the result back with
servicenow_read_doc(for exampledefault/discovery/overview.md) and summarise: counts, the largest scopes, and every Caveats line — a caveat is where the map is incomplete. - For one scope in depth, follow up with
servicenow_document_apporservicenow_document_table;servicenow_search_docsfinds text across the written documents.
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 15a0f6349feb
- 8d ago Changed · +17 lines 596d514ce8ee
- 13d ago Changed cac834d1e178
- 20d ago First seen · 44 lines · 53 tokens per session scan A cfb315a2b498
sn-discover is a skill published in the GitHub repository IvanBBaev/servicenow-mcp-ai (8 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 811 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 2026-09-27.
Other skills, from other repositories
inbound-email
Handle email arriving at a ServiceNow instance — inbound email action ordering and stop-processing, the real syseventinemailaction column names, and reading sysemail when a message created no record.
mcp-tool-discovery
Find and call tools on this ServiceNow MCP server — the two meta-tools it starts with, why a missing session id makes every other tool unreachable, which queries actually match, and which advertised tools are not on the server at all.
background-script-execution
What actually happens when you call snowexecutescript — the Scripted REST endpoint Serac auto-deploys on first use, the scheduled-job fallback, what scheduledjobpending means, and how to get output back when the call comes home empty.
csdm-modeling
Pick the right ServiceNow service class under the Common Service Data Model — business service, service offering, application service, business application — and point the CMDB tools at it without creating the records CSDM tells customers to migrate away from.
document-management
Handle ServiceNow attachments from both sides — the six /api/now/attachment tools that move file bytes in and out of the agent, and GlideSysAttachment for copying between records — plus document generation from sysreporttemplate, PDFs, dmsdocument versioning, and attachment access checks.
cmdb-patterns
Create ServiceNow CIs and cmdbrelci relationships, walk upstream/downstream impact, detect orphan/stale CIs, and align discovered CIs with the proper sysclassname hierarchy.