dmdhrumilmistry

A multi-agent application-security review harness for Claude Code (and, later, other AI agents). One router skill dispatches to a full offensive-security pipeline that maps a codebase, hunts vulnerabilities with a per-class knowledge base, chains findings into escalations, verifies real impact, and reports to README/JSON/SARIF/doc/PDF.

1 plugin · dmdhrumilmistry/security-harness

Make local Ollama coding models measurably better without training: S*/CodeT/self-debug test-time enhancements, ExPO weight updates, autotuning, Claude Code plugin

1 plugin · dmdhrumilmistry/tvashtr