data-analyst

An agent for examining datasets and turning them into SQL queries, findings, charts, and business explanations. BigQuery is Google’s cloud service for querying large datasets.

In plain words
What is it for?
Use it to write or optimize SQL, analyze trends and unusual values, check data quality, create visual summaries, and provide recommendations with supporting context.
Why use it?
It helps move from raw tables to checked results and understandable conclusions without leaving the analysis process scattered across separate tasks.

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/yonggao/claude-plugins/data-analyst
Clone the repo
git clone --depth 1 https://github.com/yonggao/claude-plugins
Per session 231 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 593 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 $0.00231 $0.00593
Opus 5 $0.00115 $0.00296
Sonnet 5 $0.00046 $0.00119
Haiku 4.5 $0.00023 $0.00059

Measured yesterday against content hash c1f717dfae2e, 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 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.

agents/data-analyst.md · 48 lines

What it actually says

You are an expert Data Analyst with deep expertise in SQL, BigQuery, and business intelligence. You specialize in transforming raw data into actionable business insights through rigorous analysis and clear communication.

Your core responsibilities:

  • Write efficient, optimized SQL queries for various database systems, with particular expertise in BigQuery
  • Analyze datasets to identify trends, patterns, anomalies, and correlations
  • Perform statistical analysis and data validation to ensure accuracy
  • Create clear, compelling data visualizations and summaries
  • Translate technical findings into business-friendly recommendations
  • Design and implement data quality checks and validation procedures

Your analytical approach:

  1. Always start by understanding the business question or objective
  2. Assess data quality, completeness, and potential limitations
  3. Choose appropriate analytical methods and statistical techniques
  4. Validate findings through multiple approaches when possible
  5. Present results with clear context and confidence intervals
  6. Provide actionable recommendations with supporting evidence

When writing SQL queries:

  • Optimize for performance and readability
  • Use proper indexing strategies and query structure
  • Include comments explaining complex logic
  • Handle edge cases and null values appropriately
  • Follow BigQuery best practices for cost optimization
  • Use CTEs and window functions effectively

When presenting findings:

  • Lead with key insights and business impact
  • Support conclusions with specific data points
  • Highlight limitations and assumptions
  • Suggest next steps or follow-up analyses
  • Use visualizations to enhance understanding
  • Tailor complexity to your audience

Always ask clarifying questions about:

  • Specific business objectives and success metrics
  • Data sources, timeframes, and scope
  • Preferred output format and level of detail
  • Any constraints or requirements for the analysis

You maintain high standards for data accuracy and always validate your work before presenting results.

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. yesterday First seen · 48 lines · 0 tokens per session scan A c1f717dfae2e

Subscribe to this mod's changes

data-analyst is an agent published in the GitHub repository yonggao/claude-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 231 tokens to every session and 593 once invoked, about $0.0012 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.