AL-JANEF

Janef One — Security skill for Claude Code

Security community

Agent orchestration kernel for Claude Code, Codex, Gemini CLI, Cursor & OpenCode — routing, WorkGraphs, state, skill security, authorization, evidence and verification.

How to install Janef One

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

What Janef One does

Agent orchestration kernel for Claude Code, Codex, Gemini CLI, Cursor & OpenCode — routing, WorkGraphs, state, skill security, authorization, evidence and verification.

Alternatives in Security

Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
Claude Bootstrap — Opinionated project initialization with security-first guardrails, spec-driven atomic todos, LLM testing patte 536 ★
OpenTag — Open-source, channel-native agent gateway for Slack 499 ★

README

JANEF ONE

One kernel. Every agent.

A portable Agent Skill and hardened Python runtime for routing, state, WorkGraphs, skill security, multi-agent planning, authorization, evidence, and reproducible verification.

العربية · English

What JANEF ONE is

JANEF ONE is a **master orchestration layer** for agentic work. Instead of stacking dozens of generic skills into the context window, it keeps one small kernel in control and loads specialized capabilities only when they add unique value.

USER / PROJECT INTENT
        │
        ▼
┌──────────────────────────┐
│        JANEF ONE         │
│  resolve • route • gate  │
└────────────┬─────────────┘
             │
   ┌─────────┼─────────┐
   ▼         ▼         ▼
Research   Coding    Tools / Files / Browser
   │         │         │
   └─────────┼─────────┘
             ▼
       WorkGraph / Agents
             ▼
      Critic + Verifier
             ▼
     Evidence-backed result

JANEF ONE does **not** override a host model's system instructions, safety controls, permissions, or actual tool availability. It operates at the user/project orchestration layer.