bug-hunter
Adversarial code audits with verified findings and safe fixes
All Skills in This Repository (11)
Pure Emerald Level Indicatorsbug-hunter
Audit code for vulnerabilities and bugs using a multi-agent pipeline.
hunter
Analyze code for logic errors, vulnerabilities, race conditions, and runtime bugs.
fixer
Apply minimal code fixes for verified bugs using documentation lookups.
referee
Verify bug reports and assign CVSS scores with proof-of-concept examples.
skeptic
Review reported vulnerabilities in code to identify false positives.
threat-model-generation
Generate STRIDE-based threat models and security configurations for code repositories.
commit-security-scan
Scan code changes for security vulnerabilities using STRIDE context.
vulnerability-validation
Validate security findings for exploitability and reachability using Bug Hunter artifacts.
doc-lookup
Retrieve verified documentation for libraries, frameworks, and APIs via Context Hub and Context7.
recon
Map codebase architecture and classify files by risk priority for security analysis.
security-review
Execute STRIDE-based security reviews with dependency vulnerability scanning and threat model analysis.
Frequently Asked Questions
FAQPage SchemaHow to install Bug Hunter?▼
Run `npx skills add codexstar69/bug-hunter --all -g -y` in your terminal to install the full skill suite globally.
How does Bug Hunter reduce false positives?▼
A Skeptic role challenges every reported bug against the actual code and verified framework docs, then a Referee issues the final verdict, so only evidence-backed findings are confirmed.
Does Bug Hunter edit my code automatically?▼
No. It is scan-only and single-pass by default; fixing, autonomous edits, and commits each require an explicit flag such as --fix or --autonomous.
Which coding agents work with Bug Hunter?▼
It supports Claude Code, Codex, Cursor, GitHub Copilot, Kiro, Windsurf, OpenCode, and Factory Droid CLI through a standard SKILL.md install.
Can Bug Hunter run security reviews on pull requests?▼
Yes. Use the --pr-security flag for diff-scoped security scans, --threat-model for STRIDE threat modeling, and --security-review for full repository audits.
Related Repositories in Software Engineering
View All in Software Engineering→openclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core