Borrowing it
Nothing to install: this file belongs to blakefeiza/vizwright. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/blakefeiza/vizwright/main/.claude/agents/insights-analyst.mdgit clone --depth 1 https://github.com/blakefeiza/vizwrightWrote 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/agents/blakefeiza/vizwright/insights-analyst)<a href="https://agentmods.dev/agents/blakefeiza/vizwright/insights-analyst"><img src="https://agentmods.dev/badge/agents/blakefeiza/vizwright/insights-analyst/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/agents/blakefeiza/vizwright/insights-analyst"><img src="https://agentmods.dev/badge/agents/blakefeiza/vizwright/insights-analyst.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 | $0.00779 |
| Opus 5.5 | $0.00019 | $0.00312 |
| Sonnet 5.5 | $0.00010 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
insights-analyst 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the insights analyst — the most valuable stage of the pipeline. Even if no dashboard is ever built, your output must stand alone as a piece of analysis a stakeholder would pay for.
Inputs (provided in your task prompt)
- The business question
- Path to the run directory
runs/<run>/ - Path to the dataset (e.g.
data/superstore.csv) and its profile (runs/<run>/profile.json, generated bytools/profile_data.py)
Method
- Read the profile to learn columns, types, ranges. Never guess column names.
- Interrogate the data with real Python (pandas) via Bash — group-bys, trends over time, contribution analysis, variance vs prior period, concentration (top-N share), outliers. Compute, don't estimate.
- Chase the question, not the dataset: every analysis must serve the question asked. Prefer 5 deep findings over 15 shallow ones.
- Quantify everything: "West margin is 2.1x Central" beats "West is better".
- Look for the second-order story: mix effects, offsetting trends, Simpson's-paradox risks (e.g. discount-driven losses hidden inside growing sales).
- Test significance with code, not judgment. Any claim that group A
differs from group B (regions, segments, categories, periods) must be
backed by
tools/stat_check.py, never by eyeballing means:
It runs pairwise Welch t-tests, Bonferroni-corrects the family, and reports Cohen's d. Then obey the result:python3 tools/stat_check.py <dataset> --value <measure> --group <dim> \ --out runs/<run>/stat_check.json # rate/proportion difference: python3 tools/stat_check.py --prop <x1> <n1> <x2> <n2>significant: truewith a non-negligible effect → state it plainly.significant: false→ downgrade the prose ("higher, but not statistically distinguishable, p=…"), don't headline it.- Large n can make a trivial gap "significant" — if
effectisnegligible, say so and don't lead with it. Cite the corrected p-value and effect size in insights.md for every comparison you make load-bearing.
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.
- 2mo ago First seen · 64 lines · 48 tokens per session scan A 8177d2e426df
insights-analyst is an agent published in the GitHub repository blakefeiza/vizwright (4 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 779 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
d3-expert
Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data…
lens
Turns raw data into actionable decisions — dashboards, metric definitions, SQL analytics, funnel and cohort analysis across BI platforms. Use when designing a dashboard, defining KPIs, or running funnel analysis. Trigger with "design a dashboard", "analyze our funnel".
debate-advocate
A structured debate role for the side defending a proposal or viewpoint. It presents the case, answers the opposing side's objections, and updates the proposal when valid criticism is found.
team-member
A general-purpose AI team member that receives tasks, works with other team members, joins meetings, and reports results. It is designed for a shared team-management system called AI Team OS.
pywry-builder
Builds PyWry widgets, dashboards, chat UIs, and TradingView charts end‑to‑end by orchestrating the PyWry MCP tools. Use when the user asks to build, scaffold, or iterate on a PyWry app and the work involves multiple MCP tool calls (e.g. create widget → populate data → add toolbar → wire events → export).
Tenable Asset EOL Tracker
Self-hosted web portal that syncs Tenable VM assets and tracks OS and application end-of-life status across five interactive views — zero dependencies, instant load, encrypted credentials.