obielin

Agentic Alignment Toolkit — Security skill for Claude Code

Security community

Audit autonomous AI agents for goal drift, oversight gaps, and value misalignment.

How to install Agentic Alignment Toolkit

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

What Agentic Alignment Toolkit does

Audit autonomous AI agents for goal drift, oversight gaps, and value misalignment. Python package with CLI, 5 evaluators, EU AI Act alignment, and full test suite.

Alternatives in Security

Azure Key Vault Python — Azure Key Vault for Python 1.8k ★
Clawsec — Security skill suite with drift detection, automated audits, and skill integrity verification 798 ★
SEO Audit Skill — English · 中文可复用的单页面 SEO 审计 Agent Skill 235 ★

README

⚙️ agentic-alignment

**A Python toolkit for evaluating goal-alignment, value drift, and oversight gaps in autonomous AI agent pipelines.**

[![CI](https://github.com/obielin/agentic-alignment-toolkit/actions/workflows/ci.yml/badge.svg)](https://github.com/obielin/agentic-alignment-toolkit/actions/workflows/ci.yml) [![Python](https://img.shields.io/badge/Python-3.10%2B-blue?style=flat-square&logo=python)](https://python.org) [![License](https://img.shields.io/badge/License-Apache%202.0-green?style=flat-square)](LICENSE) [![PyPI](https://img.shields.io/badge/PyPI-agentic--alignment-orange?style=flat-square&logo=pypi)](https://pypi.org/project/agentic-alignment/) [![LinkedIn](https://img.shields.io/badge/-Linda_Oraegbunam-blue?logo=linkedin&style=flat-square)](https://www.linkedin.com/in/linda-oraegbunam/) [![Twitter](https://img.shields.io/badge/-@Obie__Linda-black?logo=x&style=flat-square)](https://twitter.com/Obie_Linda)

Autonomous AI agents are increasingly deployed in high-stakes contexts — healthcare, finance, public sector — yet the tools to audit their alignment with human intent remain immature.

**`agentic-alignment`** provides a structured, extensible framework for evaluating agent execution traces across five alignment dimensions: goal consistency, human oversight, value compliance, corrigibility, and reasoning transparency.

It supports both **LLM-powered analysis** (via Anthropic Claude) and **heuristic-only mode** (no API key required), making it suitable for CI/CD pipelines, pre-deployment audits, and research contexts.

🚀 Installation

pip install agentic-alignment

Or install from source:

git clone https://github.com/obielin/agentic-alignment-toolkit.git
cd agentic-alignment-toolkit
pip install -e ".[dev]"

⚡ Quickstart

from agentic_alignment import AlignmentEvaluator, AgentTrace, AgentStep

# 1. Define your agent trace
trace = AgentTrace(
    agent_id="procurement-agent",
    goal="Revie