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 tushaarmehtaa/tushar-skills --skill user-insightsgit clone --depth 1 https://github.com/tushaarmehtaa/tushar-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/tushaarmehtaa/tushar-skills/user-insights)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/user-insights"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/user-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/tushaarmehtaa/tushar-skills/user-insights"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/user-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 | $0.00039 | $0.00812 |
| Opus 5 | $0.00019 | $0.00406 |
| Sonnet 5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
user-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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User insights
Start from a product decision and metric definition. Do not turn convenient columns or arbitrary time thresholds into personas.
Choose a mode
- Question framing: turn a product concern into measurable questions.
- Segmentation: identify behaviorally meaningful groups from distributions or justified business rules.
- Retention/cohort: measure return behavior from event history.
- Activation/funnel: locate progression and drop-off.
- Feature adoption/pathing: understand use sequences and value realization.
- Churn/monetization: analyze decline, cancellation, expansion, and revenue behavior.
- Qualitative synthesis: connect interviews, support, or survey evidence to behavioral patterns.
- Audit: validate an existing query, dashboard, segment, or conclusion.
Workflow
- State the product decision, population, behavior, time window, and action the analysis may trigger.
- Inspect schemas, event taxonomy, identity model, account/user relationships, plan history, billing/refunds, timezone, retention policy, and available qualitative evidence. Match the query language to the actual system.
- Audit data quality before analysis: event semantics, duplicate/late events, nulls, bots/internal/test accounts, identity merges, plan changes, censoring, seasonality, and instrumentation changes.
- Define every metric with numerator, denominator, eligibility, window, and unit of analysis. Prefer event history over current user snapshots for trends and retention.
- For segments, inspect distributions and use quantiles, clusters, or business thresholds only when interpretable and justified. Test sensitivity to reasonable boundary changes. Small groups and ties need explicit handling.
- For retention, build cohort-period activity from events and distinguish classic, rolling, and bounded retention. Do not infer historical retention from
last_active_at. - For decline or churn risk, compare each subject with its own prior behavior or an appropriate matched baseline; do not call low cumulative usage a decline.
- Execute queries only when access is available. Otherwise return executable queries and expected result shapes without fabricating counts.
- Quantify sample size, uncertainty, missingness, and alternative explanations. Treat observational associations as non-causal.
- Connect each finding to a decision, mechanism, proposed action, and validation method. Prefer experiments or staged tests for causal recommendations.
What ships with it
1 file 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 · 65 lines · 39 tokens per session scan A 4b9092daf9c6
user-insights is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (11 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 812 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 2026-08-30.
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…