NeVibeCode · repository · 6 items
defending-code-reference-harness: a set by anthropics
The anthropics/defending-code-reference-harness repository on GitHub: 6 cards with a description and an install command.
threat-model
official skill Builds a threat model for a codebase in three modes and writes it to THREAT_MODEL.md. Use it before vulnerability discovery or a security review.
Claude Code CX Codex Cursor +1
1,200installs
quickstart
official skill Guides a first pass through the code-security repository, from threat modeling to a canary scan. It also answers repo-specific questions with cited sources.
Claude Code CX Codex Cursor +1
1,100installs
customize
official skill A skill to adapt the C/C++ vulnerability-finding pipeline to other languages, domains, and target shapes. Turns an opinionated demo into a template: swap the detector, prompts, and sandbox — and the pipeline hunts what you need.
Claude Code CX Codex Cursor +1
1,100installs
patch
official skill Generates candidate diffs for verified security findings and writes inert patches for manual review.
Claude Code CX Codex Cursor +1
1,100installs
triage
official skill This skill checks scanner findings, removes duplicates, and ranks vulnerabilities by derived exploitability. Use it for a file or directory of raw results.
Claude Code CX Codex Cursor +1
1,100installs
vuln-scan
official skill Static vulnerability scanner for source code. Reads a directory, spawns parallel review subagents per focus area, and writes findings to JSON and markdown for triage.
Claude Code CX Codex Cursor +1
1,100installs
