Defending Code Reference Harness
SkillOfficial Anthropic skills for defensive threat modeling, scanning, triage, and patching
by Anthropic Listed May 22, 2026
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Product badge
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
About Defending Code Reference Harness
Anthropic’s reference harness and skills for securing source code—threat modeling, scanning, triage, and patching with a customizable autonomous scan loop. Defensive security only.
No reviews yet
Used it? Write the first review.