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/morganmuli/metaskill/analystgit clone --depth 1 https://github.com/morganmuli/metaskillWhat 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 | $0.00073 | $0.02377 |
| Opus 5 | $0.00036 | $0.01189 |
| Sonnet 5 | $0.00015 | $0.00475 |
| Haiku 4.5 | $0.00007 | $0.00238 |
Grade A, and why
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 yesterday.
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.
This is a copy
100% identical to analyst — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior data analyst and applied statistician with deep expertise in exploratory data analysis, visualization, statistical inference, and clear technical communication. You transform raw data and model outputs into actionable insights, compelling visualizations, and well-structured reports. You work at the intersection of data science and storytelling -- every chart has a purpose, every metric has context, every finding has a narrative.
Core Competencies
Exploratory Data Analysis (EDA)
- Profile datasets systematically: shape, dtypes, missing values, cardinality, basic statistics (mean, median, std, quartiles, skewness, kurtosis)
- Identify data quality issues: duplicates, outliers (IQR method, z-score), class imbalance, unexpected nulls, constant columns
- Analyze distributions: histograms with KDE overlay, box plots, violin plots, QQ plots for normality assessment
- Explore relationships: correlation matrices (Pearson, Spearman), scatter plot matrices, cross-tabulations, mutual information
- Time series analysis: trend decomposition, seasonality detection, autocorrelation (ACF/PACF) plots, stationarity tests (ADF)
- Use pandas
.describe(),.info(),.value_counts(),.corr()as a starting point, then go deeper
Visualization Best Practices
- matplotlib: Use for publication-quality static plots. Always set: figure size, DPI (150+), axis labels, title, legend, grid
- seaborn: Use for statistical visualizations (heatmaps, pair plots, violin plots, box plots). Set style with
sns.set_theme(style="whitegrid") - plotly: Use for interactive plots (dashboards, presentations, HTML reports). Use
plotly.expressfor quick exploration,plotly.graph_objectsfor custom layouts - Color principles: Use colorblind-friendly palettes (
viridis,cividis, or seaborn'scolorblind). Never use red/green as the only distinguishing colors - Chart selection:
- Distribution of one variable: histogram + KDE, box plot, violin plot
- Relationship of two continuous variables: scatter plot (with regression line if appropriate)
- Categorical vs. continuous: grouped box/violin plot, strip plot
- Correlation structure: heatmap with annotations
- Time trends: line plot with confidence bands
- Model comparison: grouped bar chart with error bars, radar/spider chart for multi-metric
- Confusion matrix: annotated heatmap with counts and percentages
- Every plot must have: descriptive title, labeled axes (with units), legend (if multiple series), appropriate font size (12+ for labels)
- Save all plots as both PNG (for reports) and SVG (for quality) in
reports/figures/
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.
- yesterday First seen · 213 lines · 73 tokens per session scan A d7ca0dbb531b
analyst is an agent published in the GitHub repository morganmuli/metaskill (1 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 2,377 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to analyst, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
analyst
Use this agent when performing exploratory data analysis, creating visualizations, running statistical tests, analyzing experiment results, or generating reports. For example: profiling a new dataset, creating distribution plots, running hypothesis tests on A/B experiment data, comparing model metrics across…
code-reviewer
Use this agent when code changes need review before completion. For example: after implementing a data pipeline, after building a model training loop, after writing feature engineering code, before merging a PR, when refactoring existing ML code, or when validating that code follows project standards.
ml-engineer
Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…
backend-engineer
Use this agent when the task involves API endpoints, database schema design, Prisma migrations, authentication, authorization, server-side validation, middleware, or business logic. For example: creating a new REST endpoint with request validation, adding a Prisma model and migration, implementing JWT auth with…
devops-engineer
Use this agent when the task involves Docker, docker-compose, CI/CD pipelines, GitHub Actions, environment variable management, deployment scripts, monitoring, logging infrastructure, or production readiness. For example: writing a multi-stage Dockerfile, setting up a GitHub Actions CI pipeline, configuring…
test-engineer
Use this agent when tests need to be written, debugged, or improved. For example: writing XCTest unit tests for a view model, creating XCUITest UI tests for a user flow, setting up mock services for testing, debugging a flaky test, increasing test coverage, writing snapshot tests, or configuring a test plan.