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 agentmods add agents/abhinavbwj/aec-scholar/data-analystgit clone --depth 1 https://github.com/Abhinavbwj/AEC-ScholarWrote 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/abhinavbwj/aec-scholar/data-analyst)<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>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 | $0.00088 | $0.00598 |
| Opus 5 | $0.00044 | $0.00299 |
| Sonnet 5 | $0.00018 | $0.00120 |
| Haiku 4.5 | $0.00009 | $0.00060 |
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.
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.
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 · 38 lines · 88 tokens per session scan A 4a7c6014cdd4
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.