Clean — Data & AI agent for Claude Code
Data quality — deduplication, validation, outlier detection, ETL pipeline design.
How to install Clean
Installs to ~/.claude/agents/tonone-ai-tonone-clean.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/tonone-ai/tonone/HEAD/agents/clean.md -o ~/.claude/agents/tonone-ai-tonone-clean.md Restart Claude Code, or start a new session, for it to be picked up.
What Clean does
name: clean description: Data quality — deduplication, validation, outlier detection, ETL pipeline design tools:
- Read
- Bash
- Glob
- Grep
- Write
- WebFetch
- WebSearch model: sonnet
You are Clean — Data Quality Engineer on the Data Science Team. Designs data validation, cleaning, and quality monitoring pipelines that ensure models train on trustworthy data.
Think in data, experiments, and statistical rigor. Every claim needs a number. Every model needs a baseline. Eve
Alternatives in Data & AI
- Read Research For Nyquist Validation Data — cat "$phase_dir"/-RESEARCH.md 2>/dev/null node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" roadmap get-pha 38.5k ★
- Presenter Agent — Creates presenter objects using SimpleDelegator for clean view formatting and display logic 652 ★
- Dex Data — Use this agent when dealing with data analysis, SQL queries, dashboards, visualizations, statistical analysis 523 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
De Pipeline Expert
Expert data pipeline architect for ETL/ELT design, orchestration patterns, data quality, and cross-tool integr
Data Executor
Internal dynos-work agent. Implements data pipelines, backfills, ETL, analytics, reconciliation, and data qual
Data Engineering Reviewer
Use this agent to review data pipelines for idempotency, schema handling, and data quality. Trigger on "review
Creo SEO
Next.js SEO + GEO specialist. Full-site audits across 7 phases covering technical SEO, content quality with AI
Data Steward
Database migration management, data quality validation, and data pipeline reliability.
DB Performance Tuner
Database bottleneck specialist for the Hydraia pipeline. Evidence-first tuning across PostgreSQL, MySQL/MariaD
Related Skills
Data Pipeline
Design data pipelines — ETL/ELT, streaming vs batch, data warehouse, quality gates, lineage
Data Validation Rules
Governs data validation behavior across Country Finder and Salary Calculator — duplicate detection, missing-fi
Anomaly Hunter
Multi-agent anomaly detection with real-time investigation. Built with 8 AI/ML sponsors for autonomous data qu