What is load-to-sqlite?

A loader that imports a taxonomy file into SQLite, a small database stored in a local file. It creates a table and chooses suitable column types from CSV data.

Use it to create or update a SQLite database from a CSV taxonomy in replace, upsert, or append mode, optionally with stricter type enforcement.

It removes the manual work of designing a table and supports different ways to handle existing rows when loading data.

load-to-sqlite — Skill for Claude Code by danielrosehill

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 danielrosehill/Claude-Taxonomy-Creation-Plugin --skill load-to-sqlite

Clone the repo

git clone --depth 1 https://github.com/danielrosehill/Claude-Taxonomy-Creation-Plugin

Made for: Claude Code.

Or install taxonomy-creation, the plugin that ships this one along with the rest of its 9 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/danielrosehill/claude-taxonomy-creation-plugin/load-to-sqlite/github.svg)](https://agentmods.dev/skills/danielrosehill/claude-taxonomy-creation-plugin/load-to-sqlite)

Your own site

<a href="https://agentmods.dev/skills/danielrosehill/claude-taxonomy-creation-plugin/load-to-sqlite"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-taxonomy-creation-plugin/load-to-sqlite/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/danielrosehill/claude-taxonomy-creation-plugin/load-to-sqlite"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-taxonomy-creation-plugin/load-to-sqlite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 649 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	$0.00036	$0.00649
Opus 5.5	$0.00014	$0.00260
Sonnet 5.5	$0.00007	$0.00130
Haiku 4.5	$0.00004	$0.00065

Measured 2mo ago against content hash aed97fc314c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

load-to-sqlite 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 2mo 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.

skills/load-to-sqlite/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Load Taxonomy to SQLite

Load a taxonomy into SQLite with full schema generation, type inference, and multiple load modes.

When to use

"Load the taxonomy into SQLite"
"I want this in a local .db file"
"Create a SQLite database with the taxonomy"

Inputs to gather

Database file path: Absolute path to .db file (will be created if missing).
Table name: What to call the table.
Taxonomy file path: Absolute path to CSV or auto-discover from data/<name>/<name>.csv.
Load mode: replace, upsert, append.
Strict mode?: Use STRICT tables (SQLite ≥3.37) for stronger type enforcement.

Procedure

Check SQLite version: Run sqlite3 --version; if ≥3.37, offer STRICT table option (recommended).
Generate DDL: Infer column types from CSV:
- code → TEXT PRIMARY KEY.
- label / name → TEXT.
- Numeric columns → INTEGER or REAL.
- Timestamps → TEXT (ISO 8601 string) or INTEGER (Unix epoch).
- parent_code → TEXT with FOREIGN KEY (SQLite supports FK but must enable PRAGMA foreign_keys = ON).
- For STRICT tables, append STRICT; to the CREATE TABLE statement.
Show user the DDL for approval.
Handle load mode:
- replace: DELETE FROM <table>; .import --csv <csv_path> <table>
- upsert: Use Python sqlite3 or raw SQL INSERT … ON CONFLICT(code) DO UPDATE SET … (SQLite 3.24+).
- append: .import --csv <csv_path> <table> directly.
Enable constraints: Run PRAGMA foreign_keys = ON; before any load if hierarchical.
Load via sqlite3 CLI (fast for CSV) or Python sqlite3 module (for typed inserts and error handling).
Log the operation: Write to state/loads/<timestamp>-<filename>.log with timestamp, mode, row count, status.

Output / side effects

SQLite database with populated table.
Load logged to state/loads/<timestamp>-<filename>.log.

Safety / constraints

STRICT tables: Recommended for type safety on SQLite ≥3.37; omit for older versions.
Foreign key support: Must explicitly PRAGMA foreign_keys = ON; to enforce; disabled by default.
Type flexibility: SQLite is dynamically typed; STRICT mitigates but doesn't guarantee type discipline.

Read the full file on GitHub · 53 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.

2mo ago First seen · 53 lines · 36 tokens per session scan A aed97fc314c0

Subscribe to this mod's changes

load-to-sqlite is a skill published in the GitHub repository danielrosehill/Claude-Taxonomy-Creation-Plugin (3 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 649 once invoked, about $0.0001 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 2026-08-31.

Databases

load-to-sqlite next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
load-to-sqlitedanielrosehill/Claude-Taxonomy-Creation-Plugin	Skill	3	6mo ago	MIT	A	36	Claude Code
create-prprisma/orm	Skill	48k	yesterday	Apache-2.0	A	48	Claude Code, Codex
schema-explorationlangchain-ai/deepagents	Skill	31k	today	MIT	A	57	Claude Code, Codex
atlas-mssqlariga/atlas	Skill	8.8k	2d ago	Apache-2.0	A	163	Claude Code
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex
nornicdb-cypher-queriesorneryd/NornicDB	Skill	924	today	MIT	A	79	Claude Code, Codex
volcengine-rds-postgresqlbytedance/agentkit-samples	Skill	484	yesterday	Apache-2.0	A	63	Claude Code, Codex