laithalsaadoon

Atif SQL — Data skill for Claude Code

Data community

ATIF-native analytics over Claude Code agent trajectories: convert sessions to ATIF, materialize a corpus, query it with DuckDB.

How to install Atif SQL

This entry records only its repository, not the path inside it, so there is no exact command to give. Open laithalsaadoon/atif-sql and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Atif SQL does

ATIF-native analytics over Claude Code agent trajectories: convert sessions to ATIF, materialize a corpus, query it with DuckDB.

Alternatives in Data

  • LLM Redteam — LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil 4.5k ★
  • 12 Services Layer — Prompt 12: Wire Up Services Layer (Analytics, Policy, Settings, Sessions) 2.3k ★
  • Query Token Info — Search tokens and fetch metadata, real-time market data, and K-Line candlestick charts by keyword or contract 483 ★

README

atif-sql

[![CI](https://github.com/laithalsaadoon/atif-sql/actions/workflows/check.yml/badge.svg?branch=main)](https://github.com/laithalsaadoon/atif-sql/actions/workflows/check.yml) [![security](https://github.com/laithalsaadoon/atif-sql/actions/workflows/security.yml/badge.svg?branch=main)](https://github.com/laithalsaadoon/atif-sql/actions/workflows/security.yml) [![CodeQL](https://github.com/laithalsaadoon/atif-sql/actions/workflows/codeql.yml/badge.svg?branch=main)](https://github.com/laithalsaadoon/atif-sql/actions/workflows/codeql.yml) [![Scorecard](https://github.com/laithalsaadoon/atif-sql/actions/workflows/scorecard.yml/badge.svg?branch=main)](https://github.com/laithalsaadoon/atif-sql/actions/workflows/scorecard.yml) ![Python 3.13+](https://img.shields.io/badge/python-3.13%2B-blue.svg) [![License Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)

ATIF-native analytics over agent trajectories.

Claude Code sessions (`~/.claude/projects/**/*.jsonl`) and Codex CLI rollouts (`~/.codex/sessions/**/rollout-*.jsonl`) are converted to ATIF (Harbor's Agent Trajectory Interchange Format, see the Harbor ATIF RFC: RFC-0001 in ), materialized as a corpus, and queried through DuckDB views. Converting once at the boundary — with an explicit, tested fidelity policy for what upstream drops — beats re-deriving trajectory semantics inside every SQL view. Both agents land in the same views, and `sessions.agent` says which one a row came from.

Install

One command, one package, every capability. Conversion, materialization, the DuckDB surface, the LLM analytics pipelines, and semantic search are all in the box — there are no extras to choose and nothing to install afterwards to make a command work.

uv tool install atif-sql     # the CLI on PATH
uvx atif-sql schema          # or run it without installing

Python 3.13 or newer. The install is substantial and deliberately so: 113 runtim