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 skills add danielrosehill/Claude-Data-Analyst-plugin --skill type-consistency-sweepgit clone --depth 1 https://github.com/danielrosehill/Claude-Data-Analyst-pluginWrote 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/danielrosehill/claude-data-analyst-plugin/type-consistency-sweep)<a href="https://agentmods.dev/skills/danielrosehill/claude-data-analyst-plugin/type-consistency-sweep"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-data-analyst-plugin/type-consistency-sweep.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 5.1 | $0.00081 | $0.01771 |
| Opus 5 | $0.00041 | $0.00886 |
| Sonnet 5 | $0.00016 | $0.00354 |
| Haiku 4.5 | $0.00008 | $0.00177 |
Grade A, and why
type-consistency-sweep 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 8d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Type Consistency Sweep
Hybrid analysis + wrangling. Find the type inconsistencies that silently break joins, skew aggregations, and cause COPY INTO failures when the user tries to load the dataset into Postgres / DuckDB / BigQuery / a graph store. Then fix them — directly for trivial cases, or by handing off to the right specialist skill.
Inputs
- Path to a dataset file, folder, or DuckDB database.
- Optional: intended destination (
postgres,duckdb,bigquery,neo4j,parquet,none) — affects strictness. - Optional: whether the user wants fixes applied, or just the report. Default: report first, then ask.
Scope of inconsistencies to detect
Within a single column
- Mixed types: column inferred as
VARCHARbut >80% of values parse as numeric — a few stray strings are poisoning the type. - Stringified numbers:
"1,234","$19.99","3.14 "— numeric intent, string storage. - Stringified dates: dates held as strings with inconsistent formats (
2024-01-15,15/01/2024,Jan 15 2024all in one column). - Stringified booleans:
"Y"/"N","true"/"false","1"/"0","yes"/"no"— sometimes mixed. - Inconsistent null sentinels: mix of actual NULL, empty string,
"NA","N/A","null","-","-999". - Integer stored as float with all-zero fractional parts (
1.0,2.0, ...) — will break joins to an integer key. - Unicode / encoding drift: same logical value with different whitespace, case, or unicode form (NFC vs NFD).
Across columns / files
- Same logical field (customer_id, country_code, date) typed differently in different files or tables — one file has it as
INTEGER, another asVARCHAR, a third zero-padded. - Join keys where one side is
"001"and the other is1. - Date/time columns with inconsistent timezone handling across files.
- Currency columns without a currency code, stored as plain numbers, and differing across files.
Relative to destination
- Destination is Postgres / BigQuery: flag VARCHAR columns that should be
NUMERIC/DATE/BOOLEAN; nested JSON in a column if destination is relational and not JSON-aware. - Destination is graph store (Neo4j, etc.): flag inconsistent node-id types across files that would prevent relationship creation.
- Destination is Parquet / Arrow: flag mixed-type columns (Arrow requires typed columns).
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.
- 8d ago First seen · 120 lines · 81 tokens per session scan A a376d6758d25
type-consistency-sweep is a skill published in the GitHub repository danielrosehill/Claude-Data-Analyst-plugin (11 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 1,771 once invoked, about $0.0004 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
fetch-data
A workflow that turns a plain-language request for business data into a database query, runs it in a data warehouse or lake, and returns the results for analysis.
query-odps
A set of rules for writing and running read-only MaxCompute, also called ODPS, SQL queries. MaxCompute is a cloud data-warehouse service; the workflow covers query structure, partitions, filtering, joins, performance, and recovery from failures.
jcdb
A read-only database lookup skill that checks real tables, columns, definitions, and selected data before SQL or code is written. Its documentation is in Chinese.
data-analysis
A business-data analysis assistant for MySQL databases and CSV or Excel files. It helps explain business measures such as sales value, daily active users, conversion, retention, repeat purchases, and customer groups.
mimic-patient-analysis
Comprehensive patient analysis using the MIMIC-IV clinical database. Use this skill whenever asked to analyze, summarize, or investigate a patient's medical history, hospital admissions, diagnoses, medications, procedures, or clinical course from a MIMIC-IV SQLite database. Triggers on prompts like "Analyze patient…
alibabacloud-data-agent-mcp-skill
Alibaba Cloud Data Agent MCP skill (alibabacloud-data-agent-mcp-skill, data-agent MCP) for enterprise database/file analysis. Use when the user asks (in any language, including Chinese) to query/analyze DMS-managed databases, run SQL/data analysis, start quick-query (lite) or deep-analysis (pro/ultra) sessions…