JuliusBrussee/caveman
Repository JuliusBrussee/caveman with agent resources for prompt engineering and agent orchestration.
Not yet security-scanned. Listed for discovery only.
Community
What it helps with
Agent jobs: Any agent
Security scan and details
- Scan result
- Not yet security-scanned
- License
- Apache-2.0
- GitHub stars
- 113,273
- Last updated
- 2026-10-17
- Source
- github.com/JuliusBrussee/caveman
- Repo
- JuliusBrussee/caveman
Automated static scan of the source at a pinned commit (custom prompt-injection, malware and exfiltration rules plus semgrep, gitleaks and osv-scanner); flagged lines get a manual review. Hosted APIs with no code to scan stay at Needs review. A scan lowers risk; it doesn't prove safety.
Related
caveman-explore
Agent skill (SKILL.md) for software development, published in JuliusBrussee/caveman. Load it into Claude Code, Codex, Cursor or another SKILL.md-aware agent.
safe-refactor
Agent skill (SKILL.md) for refactoring, published in JuliusBrussee/caveman. Load it into Claude Code, Codex, Cursor or another SKILL.md-aware agent.
caveman-learn
Agent skill (SKILL.md) for software development, published in JuliusBrussee/caveman. Load it into Claude Code, Codex, Cursor or another SKILL.md-aware agent.
investigate-first
Agent skill (SKILL.md) for software development, published in JuliusBrussee/caveman. Load it into Claude Code, Codex, Cursor or another SKILL.md-aware agent.
migration
Agent skill (SKILL.md) for software development, published in JuliusBrussee/caveman. Load it into Claude Code, Codex, Cursor or another SKILL.md-aware agent.
Superpowers (obra)
Skills framework/methodology: verification-before-completion, writing-plans, executing-plans, systematic-debugging, TDD, subagent-driven development.
Comments
Comments are from visitors, not reviewed by Upskill, and never shown to agents.