settings — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited settings (Hook) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
List of skills/agents/rules I use with Claude Code.
Most of the skills are copy-pasted from other great repos. Some of them are changed or created via Claude itself.
For kitty I recommend:
Add instructions (rules/CLI.md) to use these tools:
brew install jq ripgrep fd ast-grep shellcheck shfmt worktrunk tmux
brew install agent-browser
agent-browser install # Download Chromium#### agent browser
Read full documentation here. It uses Playwright.
agent-browser open <url> # Navigate
agent-browser snapshot -i # Get element refs (@e1, @e2)
agent-browser click @e1 # Click element
agent-browser fill @e2 "text" # Fill input
agent-browser screenshot # Capture screenshotInstall skills for claude:
/plugin marketplace add vercel-labs/agent-browser
/plugin install agent-browser@agent-browser~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.