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 Knuckles-Team/servicenow-api --skill servicenow-table-apigit clone --depth 1 https://github.com/Knuckles-Team/servicenow-apiWrote 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/knuckles-team/servicenow-api/servicenow-table-api)<a href="https://agentmods.dev/skills/knuckles-team/servicenow-api/servicenow-table-api"><img src="https://agentmods.dev/badge/skills/knuckles-team/servicenow-api/servicenow-table-api.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00180 | $0.01608 |
| Opus 5 | $0.00090 | $0.00804 |
| Sonnet 5 | $0.00036 | $0.00322 |
| Haiku 4.5 | $0.00018 | $0.00161 |
Grade A, and why
servicenow-table-api 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 8d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ServiceNow Table API (foundational)
The generic, table-agnostic primitive that every other ServiceNow skill builds on. When a module has no dedicated REST API (TRM/APM, IRM/GRC, SecOps, custom scoped apps), you drive it through these tools against its scoped tables.
When to use
- CRUD on any table by name (
incident,cmdb_ci,sn_apm_*,sn_risk_*,u_*…). - Server-side counts / group-by roll-ups (Aggregate API).
- Any REST call the typed tools don't expose (raw escape-hatch).
When NOT to use
- A domain with its own skill — use it instead (it has richer, safer recipes):
servicenow-incident-management,servicenow-change-management,servicenow-cmdb,servicenow-knowledge,servicenow-trm,servicenow-irm-grc,servicenow-secops,servicenow-telecom-tmf. Fall back here only for tables those skills don't cover.
Prerequisites & environment
Connect via the mcp-client skill against the servicenow-api MCP server.
| Variable | Required | Notes |
|---|---|---|
SERVICENOW_INSTANCE |
✅ | Instance URL (alias SERVICENOW_URL) |
SERVICENOW_USERNAME |
✅ | Basic-auth user |
SERVICENOW_PASSWORD |
✅ | Basic-auth password |
SERVICENOW_CLIENT_ID / SERVICENOW_CLIENT_SECRET |
optional | OAuth2 |
SERVICENOW_SSL_VERIFY |
optional | TLS verification toggle |
Full env/tag matrix (do not re-document here): the mcp-client reference
agent-tools/mcp-client/references/servicenow-api.md. MCP_TOOL_MODE
(condensed|verbose|both) selects the 30-tool condensed surface (used below) vs.
the 119 one-to-one verbose tools.
Tools & actions
Prefer the condensed tools; each takes action + a params_json JSON string
whose keys are passed straight to the client method.
| Condensed tool | Actions |
|---|---|
servicenow_table_api |
get_table, get_table_record, add_table_record, update_table_record, patch_table_record, delete_table_record |
servicenow_aggregate |
get_stats |
servicenow_custom_api |
api_request |
servicenow_auth |
refresh_auth_token |
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.
- 8d ago First seen · 120 lines · 180 tokens per session scan A d774f5cb507d
servicenow-table-api is a skill published in the GitHub repository Knuckles-Team/servicenow-api (19 stars, last pushed 10d ago), licensed MIT. It adds 180 tokens to every session and 1,608 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
query-grammar
Reference for the query-string grammar every generated Kavo route understands — filter operators, sort, field selection (fields/fields[relation]), pagination strategies, includes, withDeleted, and the security/coercion rules behind them. Use when writing API-consumer docs, constructing a request against a Kavo…
mikroorm-adapter
Wiring @kavo/mikroorm into a Nest app — passing the MikroORM instance rather than an EntityManager, why no RequestContext middleware is needed, opt-in case-insensitive filtering, declared soft delete, and native cross-relation filtering. Use when adding Kavo to a MikroORM project, or answering "how do I use Kavo with…
prisma-adapter
Wiring @kavo/prisma into a Nest app — the marker classes Prisma entities need, createInfrastructure's datamodel/entities options, case-insensitive filtering per database, and how the setup differs from the TypeORM path. Use when adding Kavo to a Prisma project, or answering "how do I use Kavo with Prisma" and "why…
soft-delete
Reference for Kavo's soft delete, restore, and purge behavior — strategy resolution (auto/soft/hard), enabling restoreOne/purgeOne, read semantics and withDeleted, and edge cases (unique constraints, cascades). Use when configuring delete, wiring restore/purge routes, or answering "what happens to a deleted row"…
mongoose-adapter
Wiring @kavo/mongoose into a Nest app — models as entity identities, ObjectId rendered as hex strings and id-keyed DTOs, declared soft delete, ref paths as relation and foreign key at once, and the cross-relation filter that is refused. Use when adding Kavo to a Mongoose/MongoDB project, or answering "how do I use…
quick-start
Fastest path to a working Kavo API in a brand-new project, using TypeORM and SQLite specifically — npm install list, minimal tsconfig, a single plain entity (no DTOs), and a zero-config @Kavo controller. Use when scaffolding a new Kavo app from scratch or answering "how do I get started with Kavo" questions. For a…