What is schema-auto-tagger?

A tool for suggesting policy tags and classifying Treasure Data tables and columns from their schema metadata. Policy tags label data for governance and compliance.

Use it to detect schema changes, inspect metadata patterns, and review tag suggestions with confidence scores.

It reduces manual schema review and helps identify new tables or columns that may need tags under policies such as GDPR, CCPA, HIPAA, or SOX.

schema-auto-tagger — Skill for Claude Code by treasure-data/td-skills

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.

Any agent

npx skills add treasure-data/td-skills --skill schema-auto-tagger

Clone the repo

git clone --depth 1 https://github.com/treasure-data/td-skills

Made for: Claude Code.

Or install semantic-layer, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/treasure-data/td-skills/schema-auto-tagger/github.svg)](https://agentmods.dev/skills/treasure-data/td-skills/schema-auto-tagger)

Your own site

<a href="https://agentmods.dev/skills/treasure-data/td-skills/schema-auto-tagger"><img src="https://agentmods.dev/badge/skills/treasure-data/td-skills/schema-auto-tagger/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/treasure-data/td-skills/schema-auto-tagger"><img src="https://agentmods.dev/badge/skills/treasure-data/td-skills/schema-auto-tagger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,060 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.03060
Opus 5.5	$0.00025	$0.01224
Sonnet 5.5	$0.00012	$0.00612
Haiku 4.5	$0.00006	$0.00306

Measured 1mo ago against content hash a3881566554d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

schema-auto-tagger 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 1mo ago.

The scan reads SKILL.md. This mod also ships 8 executable files (schema_auto_tagger_implementation.py, schema_tagger_td_api.py, setup_project.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

semantic-layer/schema-auto-tagger/SKILL.md · 441 lines

How it starts

The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Schema Auto-Tagger for Treasure Data

Automatically detect newly created tables and columns in Treasure Data, analyze their metadata, suggest appropriate policy tags and resource classifications, and streamline the tagging approval workflow for data governance.

When to Use This Skill

Use this skill when:

Data has just been imported/ingested into Treasure Data
You need to tag new tables or columns with appropriate policy tags
You want to suggest data classification, business domain, and compliance tags
You need to reduce manual schema tagging effort by ~80%
You want to establish consistent tagging patterns across your data warehouse
You're managing multiple databases and need automated governance
You need compliance-ready tagging (GDPR, CCPA, HIPAA, SOX)

What This Skill Does

The Schema Auto-Tagger provides a complete end-to-end solution for automated schema tagging:

1. Automatic Detection

Scans for newly created tables and columns
Compares against baseline to identify changes
Tracks modifications and updates
Supports incremental and full database scans

2. Intelligent Analysis

Analyzes column names, data types, and metadata
Pattern matching: 50+ pre-built detection rules
Machine learning-style confidence scoring
Domain-specific rule application
Compliance-aware classification

3. Smart Tagging

Suggests tags across 5 categories:
- Data Classification: PII, Sensitive, Confidential, Public, Internal
- Business Domain: Customer, Product, Financial, Marketing, Operations
- Technical: Staging, Production, Experimental, Deprecated
- Compliance: GDPR, CCPA, HIPAA, SOX, PCI-DSS
- Governance: Validated, Monitored, Raw, Archived

4. Confidence-Based Workflow

HIGH confidence (90%+): Auto-approved, minimal review
MEDIUM confidence (70%): Recommended for human review
LOW confidence (50%): Flagged for investigation

5. Human Review & Approval

Beautiful human-readable reports
JSON exports for programmatic processing
Easy approve/reject/modify workflow
Full audit trail of all decisions

Read the full file on GitHub · 441 lines

Files

What ships with it

18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 441 lines · 62 tokens per session scan A a3881566554d

Subscribe to this mod's changes

schema-auto-tagger is a skill published in the GitHub repository treasure-data/td-skills (22 stars, last pushed 4d ago), licensed Apache-2.0. It adds 62 tokens to every session and 3,060 once invoked, about $0.0002 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 2026-08-30.

Databases Legal and compliance

dsar-fulfillment

Daily GDPR data-subject-access-request runbook. Verifies each incoming request from Gmail, locates the subject's data read-only across every relevant Postgres table, compiles an access-or-deletion report in Google Docs within the {{sladays}}-day SLA, and flags it to {{legalreviewchannel}} for a lawyer to approve.…

kortix-ai/suna · 85 tokens

bug-hunter

A news-analysis skill that looks for unreasonable details in a social or industry story, investigates possible causes and incentives, and suggests ways to address the problem.

digoal/blog · 202 tokens

db-temporal-history

Audit temporal and lifecycle modeling — soft-delete consistency and its uniqueness/query traps, presence and integrity of an audit/history trail, and retention / GDPR right-to-erasure handling (hard delete vs anonymization, retention windows). Module M8. Feeds the Design & Integrity score (Temporal category).

Hainrixz/claude-db · 63 tokens

opensearch-agent-right-to-be-forgotten

Fulfil GDPR "right to be forgotten" / erasure and CCPA deletion requests against OpenSearch by finding and removing a person's personal data — including INDIRECT contextual identification, where an individual is identifiable without their name, email, or ID ever appearing (e.g. "the solo frontend engineer on duty…

philterd/opensearch-agent-skill-right-to-be-forgotten · 208 tokens

lgpd-consent-schema

Design the database schema for a versioned, append-only consent ledger that satisfies LGPD Art. 8 (free, informed, unambiguous consent for a specific purpose) and Art. 9 (information rights). Use when user asks for "consent schema", "consent ledger", "schema de consentimento", "Prisma consentimento", "consent…

goul4rt/lgpd-skills · 128 tokens

data-retention-and-privacy-by-design

Use when the user asks to "design a new data model that stores personal data", "add a retention policy", "figure out how long to keep guest data", "handle a data deletion request", "design for GDPR compliance", or is adding any field/table that captures a name, email, phone, ID document, or payment detail. Guides…

shennawardana23/skillme · 109 tokens