data-analysis

data-analysis is a command for coding agents from Abhinavbwj/AEC-Scholar. It costs 17 tokens per session (462 once invoked), scanned A, original, MIT.

A command for planning statistical and data analysis for an AEC study, meaning research related to architecture, engineering, or construction.

In plain words
What is it for?
Use it to plan analyses such as summaries, group comparisons, correlations, regression, reliability tests, factor analysis, structural equation models, Delphi studies, decision methods, energy-model checks, or qualitative coding.
Why use it?
It helps match research questions and data to suitable methods, check whether those methods are appropriate, and plan transparent reporting and code.

Command

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 commands/abhinavbwj/aec-scholar/data-analysis
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-analysis

README.md
[![agentmods](https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/data-analysis.svg)](https://agentmods.dev/commands/abhinavbwj/aec-scholar/data-analysis)
Your own site
<a href="https://agentmods.dev/commands/abhinavbwj/aec-scholar/data-analysis"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/data-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 462 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 $0.00017 $0.00462
Opus 5 $0.00009 $0.00231
Sonnet 5 $0.00003 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 4d ago against content hash 25c18c3ea88a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-analysis 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/commands/data-analysis.md · 34 lines

What it actually says

Plan the data analysis for: $ARGUMENTS

Use the data-analyst agent and the research-methods skill.

  1. Map question → data → method. Restate the RQ(s), the data type and measurement levels, and the design. Recommend the appropriate analysis (descriptive; t-test/ANOVA; correlation/regression — OLS/logistic/ multilevel; non-parametric alternatives; reliability + EFA/CFA; SEM/PLS-SEM; MCDM — AHP/TOPSIS; Delphi consensus; time-series/energy with calibration metrics CV(RMSE)/NMBE vs ASHRAE G14; uncertainty/ sensitivity analysis for models). For qualitative data, plan a transparent coding analysis (codebook + inter-coder agreement).

  2. Check assumptions. List the assumptions of the chosen test (normality, homoscedasticity, independence, multicollinearity, sample-size adequacy) and how to check/handle violations.

  3. Reporting plan. Specify what to report: effect sizes + confidence intervals (not just p-values), model-fit/validity indices for SEM, consistency ratios for AHP, calibration error for energy models; correction for multiple comparisons where relevant; and software + version for reproducibility.

  4. Code. When useful, provide runnable example code (R or Python preferred; SPSS steps if requested) for the analysis and the key plots — with honest, labeled, uncertainty-showing visualizations.

  5. Interpretation guide. Explain how to read the expected outputs and what they can and cannot support.

If the user provides the dataset, analyze it directly and report results with calibrated interpretation.

Integrity (hard rule): never fabricate data, statistics or p-values; no p-hacking or HARKing. If you don't have the data, deliver the plan + expected outputs and state what the user must compute.

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 · 34 lines · 17 tokens per session scan A 25c18c3ea88a

Subscribe to this mod's changes

data-analysis is a command published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 462 once invoked, about $0.0001 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.