Plugin

nxtg-forge

Structural governance for AI coding agents. 33 agents, 23 commands, 32 skills, 8 MCP governance tools, and 7 hooks that enforce a core rule: verifier.agent != task.agent — no agent grades its own homework. Adds health scoring (A-F grades across 8 dimensions), live drift detection, quality gates, cross-agent verification, and shared memory to any Claude Code project. Optional Rust orchestrator (4MB binary) for file locking and multi-tool coordination across Claude Code, Codex CLI, and Gemini CLI. 4,579 tests across the trilogy. Built from 23 years of global program delivery. MIT licensed.

• Published source
• Repository

Analysed

11 October 2026

Last observed

12 October 2026

What the code does

• Runs shell commands Code that starts system commands on the machine it runs on.
• Starts other processes Code that launches separate programs.
• Refers to credential files Code that names files such as SSH keys or cloud credentials.
• Downloads and runs code Code that fetches a script and pipes it into a shell.
• Evaluates code at runtime Code that builds and runs code while it executes.
• Runs hooks automatically Hooks that execute without being called explicitly.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.