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-api-developmentgit 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-api-development)<a href="https://agentmods.dev/skills/knuckles-team/servicenow-api/servicenow-api-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/servicenow-api/servicenow-api-development/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/knuckles-team/servicenow-api/servicenow-api-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/servicenow-api/servicenow-api-development.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 | $0.00040 | $0.01284 |
| Opus 5.5 | $0.00016 | $0.00514 |
| Sonnet 5.5 | $0.00008 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
servicenow-api-development 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 yesterday.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
servicenow-api development
This repository owns the ServiceNow API clients, connector mappings, MCP tools,
packaged prompts, skills, ontology, and connector identity. Shared transport,
MCP construction, release rendering, and delivery gates belong to
agent-connector-sdk and pipelines; admission and durable graph state belong
to their owning repositories. Read AGENTS.md before changing code and keep
tenant identifiers, credentials, endpoints, and local paths out of source,
fixtures, logs, and skill content.
Repository workflow
- Start from a real worktree based on
origin/mainand identify the owning row underspecs/before changing behavior. Generatedstatus.jsonfiles are evidence and are never hand-edited. - Trace a changed request from its MCP registration through the typed client,
authentication policy, response model, and connector mapping. Preserve the
stable
servicenow-mcpidentity and the existing tool names. - Keep changes in this connector boundary. Use SDK transports, credential references, TLS policy, and governed request helpers rather than adding a second client or a local serving layer.
- Use fake responses and task-local configuration in tests. Never call a live ServiceNow tenant or resolve a real secret from a local gate.
Rapid delivery: the 5-minute contract
Specs are already designed. Deliver one small, reviewable change at a time.
- Name the owning requirement and the proof before editing. Find the row with
git grep -n "<term>" -- specsand cite its ID in the commit trailer. - Keep a slice to one connector concern: one client or mapping behavior, one test seam, one workflow repair, or one substantive skill. A capability owned by the SDK, Arbora, pipelines, or the knowledge graph belongs there instead.
- Before adding spec text, extend the existing owning spec. Audits and carry-overs
land in that spec; they do not get a new directory. Run
pipelines-hook spec-statusto inspect generated evidence and never writestatus.jsonby hand. - Reuse the existing
Api, SDK client, authentication policy, MCP registration, ontology mappings, and package-data globs. A second implementation of a connector capability is a defect. - Keep tests independent of a live tenant and credentials. Prove malformed input, refusal, transport failure, and successful response shapes through existing fakes when behavior changes.
- Put
Spec: <ID>and the assisting agent trailer on consecutive lines in the final commit paragraph. UseSpec: none (...)for delivery wiring that is owned by the provider'sPIPE-CONNSPECrows.
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.
- yesterday First seen · 128 lines · 40 tokens per session scan A 92d906988b81
servicenow-api-development is a skill published in the GitHub repository Knuckles-Team/servicenow-api (20 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,284 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 2026-10-27.
Other skills, from other repositories
tunnel-manager-development
Develop, test, and publish tunnel-manager without breaking its typed SSH inventory, remote-execution, MCP action, packaged-content, spec-dashboard, or governed Pages contracts. Use when changing connector code, docs, skills, workflows, or repository-owned specifications.
gitlab-api-development
Develop, test, gate, and release the GitLab REST and GraphQL connector. Use this skill when changing API mappings, governed MCP tools, authentication, tenant selection, KG ingestion, packaged content, or repository gates.
jellyfin-mcp-development
Develop and validate the jellyfin-mcp connector using its actual agent-connector-sdk entrypoint, Jellyfin API clients, ontology assets, packaged skills, and focused tests. Use this skill for source changes and delivery gates; use the provider skills for live Jellyfin operations.
documentdb-mcp-development
Develop, test, gate, and release the documentdb-mcp connector while preserving its SDK-owned client boundary, action-routed tools, knowledge graph ingestion, packaged resources, and shared publication contracts.
api-contract-testing
Design and review API contract tests across providers and consumers. Use for schema changes, compatibility regressions and client integration failures.
api-aqa-flow
Workflow for backend API test automation: TMS / Issue Tracker test cases → automated API tests, HITL-gated.