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.
npx agentmods add skills/altimateai/altimate-code/pii-auditnpx skills add AltimateAI/altimate-code --skill pii-auditgit clone --depth 1 https://github.com/AltimateAI/altimate-codeWrote 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/skills/altimateai/altimate-code/pii-audit)<a href="https://agentmods.dev/skills/altimateai/altimate-code/pii-audit"><img src="https://agentmods.dev/badge/skills/altimateai/altimate-code/pii-audit.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00934 |
| Opus 5 | $0.00023 | $0.00467 |
| Sonnet 5 | $0.00009 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
pii-audit 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 4d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PII Audit
Requirements
Agent: any (read-only analysis) Tools used: altimate_core_classify_pii, altimate_core_query_pii, schema_detect_pii, schema_inspect, read, glob
When to Use This Skill
Use when the user wants to:
- Scan a database schema for PII columns (SSN, email, phone, name, address, credit card, IP)
- Check if a specific query exposes PII data
- Audit dbt models for PII leakage before production deployment
- Generate a PII inventory for compliance (GDPR, CCPA, HIPAA)
Do NOT use for:
- SQL injection scanning -> use
sql-review - General SQL quality checks -> use
sql-review - Access control auditing -> finops role tools in
cost-report
Workflow
1. Classify Schema for PII
Option A — From schema YAML/JSON:
altimate_core_classify_pii(schema_context: <schema_object>)
Analyzes column names, types, and patterns to detect PII categories:
- Direct identifiers: SSN, email, phone, full name, credit card number
- Quasi-identifiers: Date of birth, zip code, IP address, device ID
- Sensitive data: Salary, health records, religious affiliation
Option B — From warehouse connection:
First index the schema, inspect it, then classify:
schema_index(warehouse: <name>)
schema_inspect(warehouse: <name>, database: <db>, schema: <schema>, table: <table>)
schema_detect_pii(warehouse: <name>)
schema_detect_pii scans all indexed columns using pattern matching against the schema cache (requires schema_index to have been run).
2. Check Query PII Exposure
For each query or dbt model, check which PII columns it accesses:
altimate_core_query_pii(sql: <sql>, schema_context: <schema_object>)
Returns:
- Which PII-classified columns are selected, filtered, or joined on
- Risk level per column (HIGH for direct identifiers, MEDIUM for quasi-identifiers)
- Whether PII is exposed in the output (SELECT) vs only used internally (WHERE/JOIN)
3. Audit dbt Models (Batch)
For a full project audit:
glob models/**/*.sql
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.
- 4d ago First seen · 118 lines · 46 tokens per session scan A 455a77106f36
pii-audit is a skill published in the GitHub repository AltimateAI/altimate-code (803 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 934 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
data-divergence
Investigate why two datasets that should agree don't — two pipelines writing the same logical table, a rollup vs the detail it aggregates, a dashboard vs its source, one environment vs another. Use when row counts, totals, or date ranges disagree and the question is what happened rather than just what differs. Covers…
sql-diagram
Diagram a SQL query and explain what it shows — either its execution steps (mode=plan) or its column lineage (mode=lineage) — then trace it through small data so the defects the picture cannot show become visible. Use when asked to visualize, diagram, explain or review what a query does, how it joins its tables, or…
explore
Use this whenever you need to know what is actually in a database, warehouse, or DuckDB file before you trust it: ranked inventory of what exists, column profiles, PII detection, grain and data-quality problems, verified join inference, Mermaid ER diagrams, guarded ad-hoc SQL probes, and k-means segmentation…
maintain
Use this to keep a dbt project correct as the warehouse and the business change. It detects drift on four axes and proposes the fix: schema drift (source columns and tables added, dropped, retyped, or renamed), volume drift (a row count that collapsed, a table that emptied, a load that half-failed), grain drift (a key…
hugging-face-datasets
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.
bigquery-graph
Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph. Includes path finding, multi-hop traversal, topological connection, shortest path, node reachability, edge connectivity, and semantic graph queries.