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 indranilbanerjee/neels-plugins --skill analytics-insightsgit clone --depth 1 https://github.com/indranilbanerjee/neels-pluginsWrote 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/indranilbanerjee/neels-plugins/analytics-insights)<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/analytics-insights"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/analytics-insights/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/indranilbanerjee/neels-plugins/analytics-insights"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/analytics-insights.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 | $0.00031 | $0.05429 |
| Opus 5.5 | $0.00012 | $0.02172 |
| Sonnet 5.5 | $0.00006 | $0.01086 |
| Haiku 4.5 | $0.00003 | $0.00543 |
Grade A, and why
analytics-insights 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 2d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytics & Insights
GA4 "AI Assistant" channel group (added 13 May 2026)
Google Analytics 4 added a new default channel group called "AI Assistant" on 13 May 2026 (GA4 channel groups doc). When a referrer matches a recognized AI Assistant (ChatGPT, Gemini, Claude, etc.), GA4 automatically:
- Categorizes the session under the AI Assistant channel group
- Sets the Medium dimension to
ai-assistant
This is the attribution-side counterpart to the new GSC AI Performance Report (rolled out 3 June 2026 — see /digital-marketing-pro:gsc-ai-performance). Because the GSC AI report intentionally excludes click data, the GA4 AI Assistant channel is currently the cleanest path to attribute actual traffic coming from generative AI surfaces.
Recommended GA4 setup checks when onboarding a brand:
- Confirm the channel group is live in the property. Newer GA4 properties get it automatically; older ones may need it to appear after Google's backfill completes. If the brand reports their channel reports look unchanged after 13 May, check explore reports filtered by
sessionDefaultChannelGroup = "AI Assistant". - Add the AI Assistant channel to custom reports + dashboards — for any brand running an AEO program (
/digital-marketing-pro:aeo-geo,/digital-marketing-pro:aeo-audit), the AI Assistant channel trend is now a primary KPI alongside organic search clicks. - Don't merge AI Assistant into "Organic Search" or "Direct". Some legacy reporting templates roll AI traffic into Direct (because referrers weren't always present) or Organic Search (because answer engines feel "search-like"). Both are misattributions now — the AI Assistant channel is the authoritative bucket.
- Reconcile with
aeo-auditoutputs and the GSC AI report. Three data sources, three different views:aeo-audit(synthetic probing) — what AI engines could say about the brand- GSC AI Performance Report — actual impressions in Google AI Overviews / AI Mode (no clicks)
- GA4 AI Assistant channel — actual traffic from non-Google AI assistants (clicks materialized)
What ships with it
10 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.
- 2d ago First seen · 272 lines · 31 tokens per session scan A d526f68a4ba9
analytics-insights is a skill published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 5,429 once invoked, about $0.0001 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 2026-10-12.
Other skills, from other repositories
continuous-improvement-loop
Run the Part 12 continuous improvement loop into a quarterly brief for leadership. "produce the quarterly improvement brief".
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
attribution-report
Run attribution on real conversion paths, comparing models. "which channels actually drive revenue".
validate-output
Validate content structure against a schema: sections, word counts. "scan for leftover placeholders".
add-integration
Add a custom MCP integration: scaffold the server, write .mcp.json, test it. "add a new MCP server".
client-proposal
Draft a client proposal or RFP response: scope, deliverables, KPIs, pricing tiers. "respond to this RFP".