DBI

DBI is a skill for Claude Code, Codex from LeoLin990405/r-analytics-skill. It costs 23 tokens per session (759 once invoked), scanned A, original, MIT.

An R package interface for connecting to and querying different databases through similar commands. It includes examples for SQLite, PostgreSQL, and MySQL or MariaDB.

In plain words
What is it for?
Use it to connect to databases, run queries and updates, list tables, and process large query results in chunks.
Why use it?
It reduces the need to learn a completely different R interface for each supported database and includes parameterized queries for safer inputs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

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 skills/leolin990405/r-analytics-skill/dbi
Any agent
npx skills add LeoLin990405/r-analytics-skill --skill dbi
Clone the repo
git clone --depth 1 https://github.com/LeoLin990405/r-analytics-skill

Made for: Claude Code, Codex.

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.

agentmods badge for DBI

README.md
[![agentmods](https://agentmods.dev/badge/skills/leolin990405/r-analytics-skill/dbi.svg)](https://agentmods.dev/skills/leolin990405/r-analytics-skill/dbi)
Your own site
<a href="https://agentmods.dev/skills/leolin990405/r-analytics-skill/dbi"><img src="https://agentmods.dev/badge/skills/leolin990405/r-analytics-skill/dbi.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 759 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 5.1 $0.00023 $0.00759
Opus 5 $0.00012 $0.00380
Sonnet 5 $0.00005 $0.00152
Haiku 4.5 $0.00002 $0.00076

Measured 6d ago against content hash c04b8d6e25c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

DBI 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 6d 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.

sub-skills/r-data/r-data-database/DBI/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DBI

Database interface.

Connection

library(DBI)

# SQLite
con <- dbConnect(RSQLite::SQLite(), "database.sqlite")
con <- dbConnect(RSQLite::SQLite(), ":memory:")

# PostgreSQL
con <- dbConnect(
  RPostgres::Postgres(),
  dbname = "mydb",
  host = "localhost",
  port = 5432,
  user = "user",
  password = "password"
)

# MySQL/MariaDB
con <- dbConnect(
  RMariaDB::MariaDB(),
  dbname = "mydb",
  host = "localhost",
  user = "user",
 password = "password"
)

# Disconnect
dbDisconnect(con)

Queries

# Execute query
result <- dbGetQuery(con, "SELECT * FROM table WHERE x > 10")

# Execute statement (no return)
dbExecute(con, "UPDATE table SET x = 1 WHERE id = 5")
dbExecute(con, "DELETE FROM table WHERE id = 5")

# Parameterized queries (safe from SQL injection)
dbGetQuery(con, "SELECT * FROM table WHERE id = ?", params = list(5))
dbGetQuery(con, "SELECT * FROM table WHERE name = $1", params = list("John"))

# Send query (for large results)
res <- dbSendQuery(con, "SELECT * FROM large_table")
while (!dbHasCompleted(res)) {
  chunk <- dbFetch(res, n = 1000)
  # Process chunk
}
dbClearResult(res)

Tables

# List tables
dbListTables(con)

# Check if table exists
dbExistsTable(con, "table_name")

# Read table
df <- dbReadTable(con, "table_name")

# Write table
dbWriteTable(con, "new_table", df)
dbWriteTable(con, "table", df, append = TRUE)
dbWriteTable(con, "table", df, overwrite = TRUE)

# Remove table
dbRemoveTable(con, "table_name")

# List fields
dbListFields(con, "table_name")

Transactions

# Begin transaction
dbBegin(con)

tryCatch({
  dbExecute(con, "INSERT INTO table VALUES (1, 'a')")
  dbExecute(con, "INSERT INTO table VALUES (2, 'b')")
  dbCommit(con)
}, error = function(e) {
  dbRollback(con)
  stop(e)
})

# With transaction helper
dbWithTransaction(con, {
  dbExecute(con, "INSERT INTO table VALUES (1, 'a')")
  dbExecute(con, "INSERT INTO table VALUES (2, 'b')")
})

Metadata

# Connection info
dbGetInfo(con)

# Query info
res <- dbSendQuery(con, "SELECT * FROM table")
dbGetInfo(res)
dbColumnInfo(res)
dbGetRowCount(res)
dbGetRowsAffected(res)
dbClearResult(res)

Read the full file on GitHub · 150 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. 6d ago First seen · 150 lines · 23 tokens per session scan A c04b8d6e25c0

Subscribe to this mod's changes

DBI is a skill published in the GitHub repository LeoLin990405/r-analytics-skill (5 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 759 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 2026-08-31.

Related

Other skills, from other repositories

databricks-live-unity-catalog-grant-guard-at-azure

Mutating-runtime live guard for Unity Catalog privilege management on Azure Databricks. Executes exactly ONE GRANT or REVOKE of a single privilege on a single Unity Catalog securable (schema, table, or volume) to a single principal — with explicit written human approval, dry-run preflight, prior-state capture, and a…

VincentChuWaiChow/vanguard-frontier-agentic · 113 tokens

alibaba-live-rds-polardb-mutation-guard

Gate RDS/PolarDB instance deletion, spec downgrade, and backup policy removal — database deletion without verified backup is permanently destructive.

VincentChuWaiChow/vanguard-frontier-agentic · 39 tokens

alibaba-waf-reliability-review

Assess Alibaba Cloud workload reliability: multi-AZ ECS topology, SLB/ALB/NLB load balancing, Auto Scaling health policies, RDS/PolarDB HA failover, backup and cross-region DR, and Cloud Monitor/ARMS observability coverage.

VincentChuWaiChow/vanguard-frontier-agentic · 61 tokens

alibaba-analyticdb-realtime

Operate AnalyticDB for MySQL and PostgreSQL, Hologres real-time OLAP analytics, and DAS real-time diagnostics for sub-second interactive analytics workloads.

VincentChuWaiChow/vanguard-frontier-agentic · 40 tokens

azure-cosmosdb-performance-investigator

Use this skill for Azure Cosmos DB performance investigation, especially RU spikes, query latency, throttling, hot partitions, indexing inefficiency, partition-skew analysis, request-charge profiling, diagnostic-log review, and evidence-driven remediation planning.

VincentChuWaiChow/vanguard-frontier-agentic · 0 tokens

alibaba-polardb-rds-dba

Operate PolarDB (MySQL/PG/Oracle) clusters and RDS instances — DAS diagnostics, database proxy, Global Database Network, backup strategy, and performance tuning.

VincentChuWaiChow/vanguard-frontier-agentic · 44 tokens