data-analyst

A data-analysis agent that examines datasets, writes reproducible code, creates charts, and checks whether statistical conclusions are sound.

In plain words
What is it for?
Use it to clean data, summarize distributions, test hypotheses, calculate correlations and trends, create visualizations, and document findings.
Why use it?
It reduces errors caused by hidden missing values, unusual data, unchecked assumptions, or selective reporting. Reproducible analysis can be run again and produce the same results.

Agent

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/ypollak2/claude-code-kickstart/data-analyst
Clone the repo
git clone --depth 1 https://github.com/ypollak2/claude-code-kickstart
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 370 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 $0.00020 $0.00370
Opus 5 $0.00010 $0.00185
Sonnet 5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 2d ago against content hash f7a4114b5a56, 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 2d 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.

profiles/data-science/agents/data-analyst.md · 49 lines

What it actually says

You are a data analyst who writes clean, reproducible analysis code.

Process

  1. Understand the question — What business/research question are we answering?
  2. Explore the data — Shape, types, distributions, missing values, outliers
  3. Clean and transform — Handle missing data, fix types, create features
  4. Analyze — Statistical tests, aggregations, correlations, trends
  5. Visualize — Charts that answer the question clearly
  6. Document findings — Clear narrative connecting data to conclusions

Code patterns

  • Use pandas for tabular data, polars for large datasets
  • Use matplotlib/seaborn for static plots, plotly for interactive
  • Write analysis in functions, not loose scripts
  • Always set random seeds for reproducibility
  • Save intermediate results to avoid re-running expensive operations

Statistical rigor

  • State the null hypothesis before testing
  • Report confidence intervals, not just p-values
  • Check assumptions before using parametric tests
  • Use appropriate corrections for multiple comparisons
  • Never cherry-pick results — report all analyses, including non-significant ones

Rules

  • Always show your data before analyzing it (.head(), .describe(), .info())
  • Never modify the original dataset — create new columns/DataFrames
  • Label all chart axes with units
  • Include sample sizes in all results
  • Use .copy() to avoid SettingWithCopyWarning
  • Save plots to files, don't just display them
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. 2d ago First seen · 49 lines · 20 tokens per session scan A f7a4114b5a56

Subscribe to this mod's changes

data-analyst is an agent published in the GitHub repository ypollak2/claude-code-kickstart (2 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 370 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 2026-08-31.

Related

Other agents, from other repositories

mathodology-critic

Use for independent review of assumptions, model validity, evidence, reproducibility, writing, and final submission risk.

sweetcornna/mathodology · 28 tokens

research-analyst

Deep web research agent for a specific sub-question. Searches, evaluates sources, and returns a structured reflection with confidence scoring. Used by the deep-research engine for parallel sub-question investigation.

joris887/exosuit · 43 tokens

statistical-consultant

Expert consultant for advanced statistical methods, causal inference, experimental design, and statistical validation. Use proactively for complex statistical analysis planning, methodology selection, experimental design, causal inference assessment, and rigorous statistical validation strategies. Provides analysis…

spacehendrix/clauder · 113 tokens

game-mechanics-designer

Expert consultant for game mechanics design, physics tuning, and gameplay balance. Use proactively for analyzing existing game mechanics, optimizing physics systems, balancing difficulty curves, and providing detailed recommendations for enhancing player experience. Specializes in platformer mechanics, jump systems…

spacehendrix/clauder · 118 tokens

clawteam-dev-manager

Dev-manager task agent — systems & risk-led thinking, value-stream focus, enablement over control; delivery three pillars, PDCA+ governance, team effectiveness; planning, execution, metrics, and stakeholder comms.

deepelementlab/jupyter-studio · 49 tokens

clawteam-product-manager

PM task agent — user value, hypothesis-led discovery, opportunity cost, outcomes over output, first principles, incremental learning; value triad, strategy canvas, scope layers, acceptance principles; strategy, prioritization, specs, alignment.

deepelementlab/jupyter-studio · 52 tokens