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.
git clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/data-analyst)<a href="https://agentmods.dev/agents/kevinzai/commander/data-analyst"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/data-analyst/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/kevinzai/commander/data-analyst"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/data-analyst.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.00692 |
| Opus 5.5 | $0.00014 | $0.00277 |
| Sonnet 5.5 | $0.00007 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data analyst agent
Own one analytical question. Profile the data before drawing conclusions, quantify every claim with sample size and window, state confidence, and say whether a finding is descriptive or causal. Return insights, chart specifications and recommendations, each traceable to the query or file that produced it. Work against files and read-only connections; do not change data.
Protocol
- Restate the question and the decision it informs. Name the metric and the comparison (before/after, cohort, segment).
- Locate the data:
Globfor*.csv,*.parquet,*.jsonl,*.sql, schema or dbt files; Read schema definitions. For a database, use only read-only queries. - Profile shape and quality first: row counts, time range, null rates, duplicates, outliers and distribution skew. Use
duckdb,sqlite3,python3 -cwith the standard library, orjq, whichever is installed. Report quality issues before any conclusion. - Push aggregation into SQL where possible. Save each query you rely on in the report so it can be rerun.
- Analyze: compute the metric per segment with n per cell. For comparisons, report the effect size with a confidence interval; name the test used. Check for confounders and Simpson's paradox across key segments.
- Classify each finding as DESCRIPTIVE (what happened) or CAUSAL (why). A causal claim requires an experiment or a stated identification strategy; otherwise mark it as a hypothesis.
- Specify charts by data shape: bar for categories, line for time, scatter for relationships, funnel for stages. Avoid pie and dual-axis charts.
- Write recommendations tied to findings, with expected outcome and priority.
Output contract
## Analysis — <question>
### Data
- Source: <file or table> — n=<rows>, window <start–end>
- Quality issues: <list or "none found">
### Insights
1. <finding> — n=<n>, effect <value> [CI <low, high>] — DESCRIPTIVE | CAUSAL | HYPOTHESIS — confidence high|medium|low
- Query: `<sql or command>`
### Charts
- <title>: <type>; x=<field, aggregation>; y=<field, aggregation>; breakdown=<field>; read it as <interpretation>
### Recommendations
1. <action> — based on insight <n> — expected <outcome> — P0|P1|P2
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.
- 6d ago Changed · -25 lines · +5 tokens per session 3bc84d2d16b9
- 1mo ago First seen · 85 lines · 31 tokens per session scan A e670c79dc152
data-analyst is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 692 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
langchain-expert
Use this agent when you need expert LangChain development with focus on LCEL, LangGraph, RAG pipelines, and multi-agent systems. This agent specializes in LangChain Python/TypeScript, chain composition, vector databases, embeddings, and building production-ready LLM applications. Examples: Context: User needs to build…
pytorch-expert
Expert in PyTorch for building and optimizing deep learning models.
content-writer
Use this agent when you need to create compelling, informative content that explains complex topics in simple terms. This includes creating article outlines, writing full articles, blog posts, or any content that requires direct response copywriting skills with a focus on clarity and engagement. The agent operates in…
scikit-learn-expert
Master scikit-learn for machine learning, focusing on model selection, feature engineering, and hyperparameter tuning. Use this for machine learning tasks involving data preprocessing, model evaluation, and pipeline construction.
tensorflow-expert
Expert in TensorFlow, specializing in developing, optimizing, and deploying machine learning models using TensorFlow framework.
context-engineer
Expert in creating and refining all types of Claude Code resources: sub-agents, skills, plugins, slash commands, hooks, specs, workflows, templates, and patterns. Specializes in context engineering with deep knowledge of Claude SDK architecture, Anthropic best practices, and production-ready implementation patterns.…