Quote:Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
A reference implementation for autonomous vulnerability discovery and remediation with Claude, based on our learnings from partnering with security teams at several organizations since launching Claude Mythos Preview.
Saw this on a site & a few comments mentioned that it may be best to fork this and adapt to your own workflow, due to how easy it is to rewrite 100s of files to fit your needs nowadays by using AI.
Here's the repo if you are interested in forking, or just using it as-is:
https://github.com/anthropics/defending-...ce-harness
Claude Code skills:
Quote:/quickstart, /threat-model, /vuln-scan, /triage, /patch, /customize: interactive scoping, scanning, triage, and patching. Open this repo in Claude Code and run /quickstart to get oriented.
harness/: the autonomous reference pipeline (recon → find → verify → report → patch), configured for finding C/C++ memory vulnerabilities using Docker and ASAN. This harness is a reference, not a product. The general shape, prompts, and sandboxing are reusable, but the harness will not work on every codebase out of the box. Run /customize to port it to your language, detector, or vuln class.
More usage examples:
Quote:# Pin every subagent to the model you want
export CLAUDE_CODE_SUBAGENT_MODEL=<model-id>
claude
# 0. intro + guided first run
> /quickstart
# 1. Build a threat model (aim before you shoot)
> /threat-model bootstrap targets/canary
# 2. Run a static scan, scoped by that threat model
> /vuln-scan targets/canary
# 3. Verify, dedupe, and rank what came back
> /triage targets/canary/VULN-FINDINGS.json
# 4. Generate candidate fixes for the verified findings
> /patch ./TRIAGE.json --repo targets/canary