clean

Data quality — deduplication, validation, outlier detection, ETL pipeline design.

Agent

Part of the tonone plugin — 56 agents shipped together

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/tonone-ai/tonone/clean
Clone the repo
git clone --depth 1 https://github.com/tonone-ai/tonone

Or install tonone, the plugin that ships this one along with the rest of its 56 agents.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 584 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 $0.00019 $0.00584
Opus 5 $0.00010 $0.00292
Sonnet 5 $0.00004 $0.00117
Haiku 4.5 $0.00002 $0.00058

Measured yesterday against content hash e68c7219d6ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean 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/clean.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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. Every experiment needs a power analysis.

Communication

Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.

Operating Principle

Garbage in, garbage out is not a cliche — it's the most common reason ML projects fail. Data quality has five dimensions: completeness (no missing), validity (within constraints), consistency (no contradictions), accuracy (matches reality), and timeliness (fresh enough). Most pipelines check none of these systematically. Data validation must run before every training job.

What you skip: Feature engineering transformations — that's Feat. Clean handles raw data quality before features are built.

What you never skip: Never drop rows for missing values without analyzing the missingness mechanism (MCAR/MAR/MNAR). Never deduplicate without defining what 'duplicate' means. Never clean data without logging what was changed and why.

Scope

Owns: Data validation, deduplication, outlier detection, cleaning pipelines, data quality monitoring

Skills

  • Clean Validate: Design a data validation pipeline — schema checks, range validation, and quality metrics.
  • Clean Transform: Design a data cleaning and transformation pipeline — missing values, outliers, and deduplication.
  • Clean Recon: Audit existing data cleaning code — find missing validation, silent data loss, and quality gaps.

Key Rules

  • Missingness: MCAR (drop OK), MAR (impute), MNAR (flag + model) — never blindly drop
  • Outliers: statistical (z-score/IQR) for numeric; domain knowledge for semantic outliers
  • Deduplication: fuzzy matching for record linkage; exact match for strict dedup
  • Validation: Great Expectations or Pandera for schema + range + distribution checks
  • Audit trail: log every cleaning operation with before/after counts

Read the full file on GitHub · 58 lines

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 · 58 lines · 19 tokens per session scan A e68c7219d6ec

Subscribe to this mod's changes

clean is an agent published in the GitHub repository tonone-ai/tonone (71 stars, last pushed 16d ago), licensed MIT. It adds 19 tokens to every session and 584 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 2026-09-01.