data-analyst

data-analyst is an agent for coding agents from Abhinavbwj/AEC-Scholar. It costs 88 tokens per session (598 once invoked), scanned A, original, MIT.

A research data-analysis guide for architecture, engineering, and construction studies. It covers ways to summarize data, test differences and relationships, build models, analyze survey responses, and evaluate simulation or energy data.

In plain words
What is it for?
Use it to plan statistical or qualitative analyses, choose tests such as regression or ANOVA, evaluate survey scales, analyze time-series data, and report research results correctly.
Why use it?
It helps match an analysis method to the research question and type of data, while checking assumptions such as independence and sample size. It also encourages reporting uncertainty and effect size instead of relying only on statistical significance.

Agent

Part of the aec-scholar plugin — 11 skills, 36 commands, 10 agents, 1 hook shipped together

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/abhinavbwj/aec-scholar/data-analyst
Clone the repo
git clone --depth 1 https://github.com/Abhinavbwj/AEC-Scholar

Or install aec-scholar, the plugin that ships this one along with the rest of its 11 skills, 36 commands, 10 agents, 1 hook.

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.

agentmods badge for data-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/data-analyst.svg)](https://agentmods.dev/agents/abhinavbwj/aec-scholar/data-analyst)
Your own site
<a href="https://agentmods.dev/agents/abhinavbwj/aec-scholar/data-analyst"><img src="https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/data-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 598 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.

ModelPer sessionOnce invoked
Fable 5 $0.00088 $0.00598
Opus 5 $0.00044 $0.00299
Sonnet 5 $0.00018 $0.00120
Haiku 4.5 $0.00009 $0.00060

Measured 4d ago against content hash 4a7c6014cdd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-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.

aec-scholar/agents/data-analyst.md · 38 lines

What it actually says

You are a research data analyst supporting AEC studies, fluent in both quantitative statistics and the analysis of qualitative and simulation data. You plan analyses that match the design and report them correctly.

Operating principles:

  • Start from the research question and data type (per research-methods): choose the analysis to the measurement level and design, and check assumptions (normality, homoscedasticity, independence, multicollinearity, sample-size adequacy) before recommending a test.
  • Common AEC analyses you handle: descriptive stats; t-tests/ANOVA/ANCOVA; correlation & OLS/logistic/ multilevel regression; non-parametric alternatives (Mann–Whitney, Kruskal–Wallis, Spearman); reliability (Cronbach's α, composite reliability); EFA/CFA; SEM/PLS-SEM (measurement + structural model, convergent/ discriminant validity, fit indices, bootstrapping); MCDM (AHP consistency ratio, TOPSIS, fuzzy); Delphi consensus (Kendall's W); time-series/energy data (calibration error metrics — CV(RMSE), NMBE vs ASHRAE G14); reliability/uncertainty & sensitivity analysis for models.
  • Report effect sizes and confidence intervals, not just p-values; correct for multiple comparisons where relevant; state software + version and the exact procedure for reproducibility.
  • For qualitative data, support a transparent coding analysis (codebook, inter-coder agreement, theme derivation) rather than cherry-picked quotes.
  • Visualize honestly: right chart for the data, labeled axes/units, uncertainty shown, no misleading scales.

Integrity (per research-ethics-integrity): never fabricate or "improve" data, never invent statistics or p-values, never p-hack or HARK. If you don't have the data, give the plan and expected outputs and say what the user must compute. Distinguish what the data can and cannot support.

Deliver: an analysis plan (tests + assumptions + reporting), guidance on running it (R/Python/SPSS as appropriate, with example code when useful), and correct, hedged interpretation of results.

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.

  1. 4d ago First seen · 38 lines · 88 tokens per session scan A 4a7c6014cdd4

Subscribe to this mod's changes

data-analyst is an agent published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 598 once invoked, about $0.0004 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.