No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by datachain-ai · Codex Skill · ★ 2.8k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is datachain safe to install? View the security audit →
DataChain - Data Context Layer for Object Storage DataChain is a data context layer for object storage. It gives AI agents and pipelines a typed, versioned, queryable view of your files - what exists, what schema it has, what's already been computed - without copying data or loading it into memory. Metadata queries across 100M+ files execute in milliseconds against a backend database Pipelines checkpoint - re-running the same script resumes compute without duplicating expensive LLM-call or ML scoring makes re-runs incremental — only new or changed files are processed Every registers a named, versioned dataset with schema and lineage A generated knowledge base () reflects the operational layer as markdown for agents to read before writing code Works with S3, GCS, Azure, and local filesystems. bash pip
| Stars | 2,820 |
| Forks | 157 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 62.3698151356239/100 |
| Open Issues | 101 |
| Last Updated | 2026-09-18 |
| Created | 2024-06-25 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~16k |
These tools work well together with datachain for enhanced workflows:
Looking for a datachain alternative? If you're comparing datachain with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-callin
Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control
Explore other popular codex skill tools:
datachain is The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure. It is categorized as a Codex Skill with 2.8k GitHub stars.
datachain is primarily written in Python. It covers topics such as ai-agents, claude-code, codex.
You can find installation instructions and usage details in the datachain GitHub repository at github.com/datachain-ai/datachain. The project has 2.8k stars and 157 forks, indicating an active community.
datachain is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to datachain on Agent Skills Hub include OpenContext, cursor-talk-to-figma-mcp, pilot-shell. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: