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 splunk/splunk-agent-skills --skill splunk-product-question-navigatorgit clone --depth 1 https://github.com/splunk/splunk-agent-skillsWrote 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/splunk/splunk-agent-skills/splunk-product-question-navigator)<a href="https://agentmods.dev/skills/splunk/splunk-agent-skills/splunk-product-question-navigator"><img src="https://agentmods.dev/badge/skills/splunk/splunk-agent-skills/splunk-product-question-navigator/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/splunk/splunk-agent-skills/splunk-product-question-navigator"><img src="https://agentmods.dev/badge/skills/splunk/splunk-agent-skills/splunk-product-question-navigator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00090 | $0.02682 |
| Opus 5 | $0.00045 | $0.01341 |
| Sonnet 5 | $0.00018 | $0.00536 |
| Haiku 4.5 | $0.00009 | $0.00268 |
Grade A, and why
splunk-product-question-navigator 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 10d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Splunk Product Question Navigator
Answer explanatory Splunk product questions by researching the current public record. This skill is a research and routing method, not a product knowledge base. Never treat its wording, model memory, prior answers, private Support material, or an unverified search snippet as product truth.
Prerequisites
The user must provide a product question and any known deployment, edition, version, build, app, integration, region, provider, experience, or topology details. Live access to a Splunk deployment is neither required nor permitted; this skill researches customer-safe public sources only.
When to Use
Own questions whose requested outcome is an explanation or a documented product fact, including:
- what a feature, setting, product, API, limit, or lifecycle label means;
- where a feature is documented or exposed;
- which product, deployment, edition, version, or app release includes it;
- whether a combination is publicly documented as supported or compatible;
- what publicly documented behavior changed between releases;
- how to complete a public, documented self-service procedure, including its prerequisites, ordered actions, expected result, and verification; and
- which current public workflow or specialist should handle the next step.
If the request mixes explanation with execution, answer only the explanatory
part and route the action. Cited public how do I steps are explanatory and in
scope: route only execution, private inspection, privileged mutation, or an
undocumented decision, not the documented procedure itself. Do not absorb an
actual action into this skill.
Non-Negotiable Evidence Contract
Research every product-specific answer live. Read public-research.md before browsing.
- Collect or explicitly mark unknown the product, deployment or edition, and exact version or build. When material, also collect cloud provider, region, experience, topology, app version, or integration version.
- Prefer a current official page that matches those facts. Match applicability separately for every material claim, and give a documented conditional branch when product, deployment, edition, version, or another material fact changes the result. A latest-version page does not prove behavior in an older release, and an old versioned page does not prove current behavior. Discard adjacent-version evidence for an exact-version claim instead of treating it as close enough.
- Cite a direct public page for every substantive product claim. Search-result snippets, generated summaries, and links to a search page are discovery aids, not evidence.
- State what the source directly establishes. Label any synthesis that goes
beyond the cited text as
Inference, with the evidence and uncertainty that support it. - Report when the evidence was checked and which product/version it covers. If the page exposes a publication or update date, preserve it.
- Preserve lifecycle language exactly. Preview, private preview, controlled availability, limited availability, beta, and general availability are not interchangeable. Do not turn a preview statement into a GA commitment.
What ships with it
3 files 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.
- 10d ago First seen · 269 lines · 90 tokens per session scan A 95ad553b694b
splunk-product-question-navigator is a skill published in the GitHub repository splunk/splunk-agent-skills (29 stars, last pushed 19d ago), licensed Apache-2.0. It adds 90 tokens to every session and 2,682 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…