Plugin

forge

Description: Adversarial code hardening for Claude Code. Forge spawns two agents — a Builder and a Breaker — that iterate against each other until the code is unbreakable. The Builder implements a feature, the Breaker writes adversarial tests to prove bugs, and the Builder must fix the implementation without deleting or weakening the tests. The loop continues until the Breaker can't produce a failing test. The result is battle-tested code with a permanent adversarial test suite. Key features: - Evidence-based, not opinion-based. Every issue the Breaker raises must have a failing test that proves the bug. No test, no break. This eliminates false positives and subjective feedback. - Iterative adversarial loop. Builder and Breaker are separate agents that go back and forth for up to N rounds. The Builder cannot dismiss feedback; it must make the failing tests pass. - Adversarial tests are permanent. The Breaker's tests stay in the repo under tests/adversarial/ as a regression suite. Future changes are protected by the same tests that originally caught the bugs. - Automatic checkpoint. Creates a git tag before starting so the entire forge session can be rolled back with one command. - Configurable rounds. Default 5 rounds, adjustable with --rounds N. Stops early if the Breaker can't find issues. - Auto-detects project stack. Reads config files to determine language, test framework, and conventions. Works with Python, TypeScript, Rust, Go, Ruby, and anything with a test runner.

• Published source
• Repository

Analysed

11 October 2026

Last observed

12 October 2026

What the code does

Static analysis found none of the capabilities we track, such as shell commands, network requests or file writes, in the latest version.

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.