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/datenoio/iterabledata/database-engine-implementationnpx skills add datenoio/iterabledata --skill database-engine-implementationgit clone --depth 1 https://github.com/datenoio/iterabledataWhat 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 | $0.00036 | $0.01999 |
| Opus 5 | $0.00018 | $0.01000 |
| Sonnet 5 | $0.00007 | $0.00400 |
| Haiku 4.5 | $0.00004 | $0.00200 |
Grade A, and why
database-engine-implementation scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
from urllib.parse import urlparse How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Engine Implementation Guide
Overview
Database engines provide read-only access to SQL and NoSQL databases as iterable data sources. They wrap database drivers to provide a unified BaseIterable interface.
Architecture
- DBDriver (
iterable/db/base.py) - Abstract base class for database drivers - DatabaseIterable (
iterable/db/iterable.py) - Wrapper that makes DBDriver work as BaseIterable - Driver Registry (
iterable/db/__init__.py) - Registry for mapping engine names to driver classes
Adding New Database Engines
Step-by-Step Process
- Create driver file:
iterable/db/<engine>.py - Implement DBDriver: Inherit from
DBDriveriniterable/db/base.py - Required methods:
connect(),iterate(),close()(close has default implementation) - Register driver: Call
register_driver()initerable/db/__init__.py - Add detection: Update
iterable/helpers/detect.pyto recognize database URLs - Create tests:
tests/test_db_engines.pyor add to existing test file - Update dependencies: Add optional dependency to
pyproject.toml - Update documentation: Add engine to docs
Implementation Pattern
from collections.abc import Iterator
from typing import Any
from ..types import Row
from .base import DBDriver
class NewEngineDriver(DBDriver):
"""Database driver for NewEngine.
Supports streaming queries using batch processing.
"""
def __init__(self, source: str | Any, **kwargs: Any) -> None:
"""Initialize driver.
Args:
source: Connection string/URL or existing connection object
**kwargs: Additional parameters:
- query: Query string or table name
- batch_size: Rows per batch (default: 10000)
- on_error: Error handling policy ('raise', 'skip', 'warn')
"""
super().__init__(source, **kwargs)
self._cursor: Any = None
def connect(self) -> None:
"""Establish database connection.
Raises:
ImportError: If required driver library is not installed
ConnectionError: If connection fails
"""
try:
import database_library
except ImportError:
raise ImportError(
"database-library is required. Install with: pip install database-library"
) from None
# Handle existing connection object
if hasattr(self.source, "cursor"):
self.conn = self.source
self._connected = True
return
# Parse connection string
if not isinstance(self.source, str):
raise ValueError("Source must be connection string or connection object")
try:
self.conn = database_library.connect(self.source, **self.kwargs.get("connect_args", {}))
self._connected = True
except Exception as e:
self._connected = False
raise ConnectionError(f"Failed to connect: {e}") from e
def iterate(self) -> Iterator[Row]:
"""Return iterator of dict rows.
Yields:
dict: Database row as dictionary
Raises:
RuntimeError: If not connected
"""
if not self._connected:
raise RuntimeError("Not connected. Call connect() first.")
self._start_metrics()
batch_size = self.kwargs.get("batch_size", 10000)
try:
query = self._build_query()
cursor = self.conn.cursor()
# Execute query with batching
cursor.execute(query)
while True:
rows = cursor.fetchmany(batch_size)
if not rows:
break
# Convert rows to dicts
column_names = [desc[0] for desc in cursor.description]
for row in rows:
row_dict = dict(zip(column_names, row))
self._update_metrics(rows_read=1)
yield row_dict
except Exception as e:
self._handle_error(e, "during iteration")
if self._on_error == "raise":
raise
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.
- 2d ago First seen · 312 lines · 36 tokens per session scan A e971e2bda971
database-engine-implementation is a skill published in the GitHub repository datenoio/iterabledata (37 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 1,999 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
fastapi
FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.
breaking-change-report
Run the japicmp binary-compatibility report for wiremock-core and produce a filtered summary covering only @PublishedAPI-annotated classes. Use this when asked to generate, refresh, or summarise the breaking-changes report.
geoserver-rest-api
Use when automating GeoServer management — programmatic workspace, datastore, and layer creation, style upload, service configuration via REST API. GeoServer REST API: manage GeoServer without GUI using curl, Python, or any HTTP client.
create-or-update-pr
Create a pull request for the current branch, or update the existing one if it already exists. Regenerates the title (Conventional Commits format) and the body (Objective + What was done) from the actual changes, in English. INVOKE when the user asks to "open a PR", "create a PR", "update the PR", "update PR…
adhx
ADHX - X/Twitter Post Reader workflow skill. Use this skill when the user needs Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required and the operator…
Data Analyzer
Statistical analysis and data transformation service for CSV and JSON datasets.