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 bikemeardsley/claude-servicenow-docs --skill servicenow-docsgit clone --depth 1 https://github.com/bikemeardsley/claude-servicenow-docsWrote 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/bikemeardsley/claude-servicenow-docs/servicenow-docs)<a href="https://agentmods.dev/skills/bikemeardsley/claude-servicenow-docs/servicenow-docs"><img src="https://agentmods.dev/badge/skills/bikemeardsley/claude-servicenow-docs/servicenow-docs/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/bikemeardsley/claude-servicenow-docs/servicenow-docs"><img src="https://agentmods.dev/badge/skills/bikemeardsley/claude-servicenow-docs/servicenow-docs.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 | $0.00156 | $0.02426 |
| Opus 5 | $0.00078 | $0.01213 |
| Sonnet 5 | $0.00031 | $0.00485 |
| Haiku 4.5 | $0.00016 | $0.00243 |
Grade B, and why
servicenow-docs scanned grade B with 2 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 12d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`curl -LsSf https://astral.sh/uv/install.sh | sh` (macOS/Linux) or Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -LsSf https://astral.sh/uv/install.sh | sh` (macOS/Linux) or How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ServiceNow Docs (via the Fetch connector)
This skill answers ServiceNow questions from the official
ServiceNow/ServiceNowDocs repository - the docs ServiceNow publishes as one Markdown file
per topic, with a machine-readable llms.txt index designed for "read the index, then fetch
the file you need" retrieval.
Use the Fetch connector for every retrieval
This plugin bundles the Fetch MCP server, exposed as the fetch connector. It
provides a fetch tool that takes a url and returns the page as Markdown.
Every piece of content you cite in an answer must come from a fetch call made during this
conversation. When the user invokes this skill, they are explicitly asking you to consult
the live documentation - so:
- Always call
fetchfirst. Do not answer a ServiceNow question from memory and then offer to look it up. Look it up, then answer. - Never reconstruct doc content from recall and present it as documentation, even when you are confident. Confidence is not a citation.
- Never present content as read without a successful
fetchconfirming it. Deriving a candidate path - from a search result, a landing-page link, or a directory listing - is fine and expected. Treating an unconfirmed derived path as documentation is not: if the fetch 404s, that path told you nothing. - If the docs contradict your prior knowledge, the fetched docs win - say so plainly if the difference matters to the user.
Base locations
HEAD works as a branch alias everywhere on this repo and always resolves to the current
release family (australia today; ServiceNow rotates it as new families ship). Use the
literal string HEAD in every URL below. There is no branch to resolve, and no reason to
call api.github.com/repos/ServiceNow/ServiceNowDocs for default_branch.
| Purpose | URL |
|---|---|
| Topic file - the thing you actually want | https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/HEAD/markdown/{publication}/{file}.md |
| Landing page - curated hub for a subtopic | https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/HEAD/markdown/{publication}/{topic}-landing.md |
| Directory listing - last resort, see workflow | https://api.github.com/repos/ServiceNow/ServiceNowDocs/git/trees/HEAD:markdown/{publication} |
| Publication list - orientation only | https://raw.githubusercontent.com/ServiceNow/ServiceNowDocs/HEAD/llms.txt |
| Human-browsable repo - for citing back to the user | https://github.com/ServiceNow/ServiceNowDocs |
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.
- 12d ago First seen · 154 lines · 156 tokens per session scan B 1005fa90a739
servicenow-docs is a skill published in the GitHub repository bikemeardsley/claude-servicenow-docs (1 stars, last pushed 29d ago), licensed CC0-1.0. It adds 156 tokens to every session and 2,426 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
architecture-decision-record
ADR templates in the Nygard format with context, decision, consequences, and alternatives. Use when writing ADRs, recording an architectural decision, or evaluating options.
documentation-patterns
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation, writing architecture decisions, documenting APIs, or maintaining changelogs.
servicenow-sdk-docs-builder
Automation skill to generate or update the servicenow-sdk-docs documentation skill by fetching and processing the ServiceNow SDK and Examples repositories. It combines READMEs, extracts code samples, harvests the SDK CLI/auth docs, and creates a self-contained, portable documentation skill.
init
Bootstrap docaudit for a repo, or add and refresh its optional local documentation harness. Use when the user asks to set up docaudit, initialize the doc-audit harness, or run docaudit on a repo that lacks /check-docs / /review-docs / doc-lint. Inventories the repo, proposes a doc-audit.json config for approval…
audit
Change-driven documentation audit. Use when the user asks to audit docs since the last audit, check documentation consistency after code/config changes, run a full doc consistency sweep, or verify nothing is stale before a release. Diffs since the anchor, maps changed files to impacted docs, runs the configured…
report
Render a research, documentation, or analysis report as a designed HTML document using the project template, instead of emitting a raw .md file. Use whenever the user asks for a report, analysis, deep-dive, investigation, postmortem, summary, write-up, briefing, or any structured long-form (>500 words, multiple…