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 kapa-ai/kapa-skills --skill analyze-source-analyticsgit clone --depth 1 https://github.com/kapa-ai/kapa-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/kapa-ai/kapa-skills/analyze-source-analytics)<a href="https://agentmods.dev/skills/kapa-ai/kapa-skills/analyze-source-analytics"><img src="https://agentmods.dev/badge/skills/kapa-ai/kapa-skills/analyze-source-analytics/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/kapa-ai/kapa-skills/analyze-source-analytics"><img src="https://agentmods.dev/badge/skills/kapa-ai/kapa-skills/analyze-source-analytics.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 | $0.00048 | $0.02021 |
| Opus 5 | $0.00024 | $0.01010 |
| Sonnet 5 | $0.00010 | $0.00404 |
| Haiku 4.5 | $0.00005 | $0.00202 |
Grade A, and why
analyze-source-analytics 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 11d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Source Analytics
You are helping the user audit their documentation against a Kapa source analytics CSV export. The goal is to find specific changes to documentation pages (additions, clarifications, restructures, cross-links, deletions) that would have improved Kapa's answers, backed by exact counts and verbatim quotes.
Background
Kapa is a Retrieval-Augmented Generation (RAG) system that customers deploy on their own documentation. Kapa indexes the documentation, then answers end-user questions about the product by retrieving the most relevant pages and citing them in its answer.
Every time Kapa answers a question, it logs which pages it cited. The source analytics export is the flat log of those citation events: one row per Q/A-to-page citation. The cited page is identified by the Referenced URL column, so grouping rows by that column gives you every Q/A in which a given page was used as a source.
A few terms to know:
- URL is one documentation page (the
Referenced URL). - Thread is one user conversation. A thread can contain multiple Q/As across follow-up turns.
- Question/Answer (Q/A) is one user question paired with Kapa's generated answer. Each Q/A in the export is one where Kapa cited a specific page while generating that answer.
- Uncertain is Kapa's own flag for an answer where it concluded the indexed knowledge sources did not sufficiently cover the user's question. A high uncertain count on a page does not necessarily mean the page is failing its citers. When Kapa cannot find a good source, it still cites the closest semantic match, so a broad page often ends up as a catch-all for adjacent topics it was never meant to cover. The fix for an uncertain question may belong on a different page (or on no existing page at all), not on the page that happened to be cited.
- Integration is the surface the question came in through (Website Widget, Slack Bot, Marketing, Interactive Demo, and so on), usually synonymous with where this instance of Kapa was deployed.
What ships with it
2 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.
- 11d ago First seen · 122 lines · 48 tokens per session scan A e5b38a2c4e34
analyze-source-analytics is a skill published in the GitHub repository kapa-ai/kapa-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 2,021 once invoked, about $0.0002 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 2026-08-31.
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…