What is insights-analyst?

An analysis workflow that examines a dataset in response to a business question and produces an analysis plan plus a standalone findings narrative. It uses real calculations, including trends, group comparisons, contribution analysis, outliers, and statistical tests.

Use it to inspect a dataset, calculate and test business findings, quantify differences and trends, identify second-order effects, and prepare evidence for a dashboard or stakeholder report.

It keeps analysis focused on the question and replaces guesses with measured findings, while checking for less obvious patterns and misleading group comparisons.

insights-analyst — Agent for Claude Code by blakefeiza: An analysis workflow that examines a dataset in response…

Install

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.

agentmods

npx agentmods add agents/blakefeiza/vizwright/insights-analyst

Clone the repo

git clone --depth 1 https://github.com/blakefeiza/vizwright

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/blakefeiza/vizwright/insights-analyst.svg)](https://agentmods.dev/agents/blakefeiza/vizwright/insights-analyst)

Your own site

<a href="https://agentmods.dev/agents/blakefeiza/vizwright/insights-analyst"><img src="https://agentmods.dev/badge/agents/blakefeiza/vizwright/insights-analyst.svg" alt="Measured on agentmods" height="20"></a>

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 779 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00048	$0.00779
Opus 5	$0.00024	$0.00390
Sonnet 5	$0.00010	$0.00156
Haiku 4.5	$0.00005	$0.00078

Measured 4d ago against content hash 8177d2e426df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

.claude/agents/insights-analyst.md · 64 lines

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 by tools/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:
```
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>
```
It runs pairwise Welch t-tests, Bonferroni-corrects the family, and reports Cohen's d. Then obey the result:
- significant: true with 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 effect is negligible, 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.

Read the full file on GitHub · 64 lines

Changes

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.

4d ago First seen · 64 lines · 48 tokens per session scan A 8177d2e426df

Subscribe to this mod's changes

insights-analyst is an agent published in the GitHub repository blakefeiza/vizwright (3 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 779 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.

Analytics and metrics ai-agents claude-code dashboard data-visualization dataviz tableau

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…

andisab/swe-marketplace · 448 tokens

drivers-and-sync-backend-expert

Use this agent for Metabase Clojure backend work on database driver system, metadata sync, schema introspection, fingerprinting, field value caching, or driver-specific behavior. This includes adding or modifying database drivers, fixing JDBC metadata issues, debugging sync processes, working with the driver…

metabase/metabase · 528 tokens

notifications-backend-expert

Use this agent for Metabase Clojure backend work on notification system, dashboard subscriptions, alerts, pulse sending, email delivery, Slack integration, channel rendering, or scheduling infrastructure. This includes debugging notification delivery failures, working with the rendering pipeline (HTML email, chart…

metabase/metabase · 442 tokens

insights-analyst