Install one skill. Tell Claude to scan your app. Get findings, evidence, and AI-assisted fixes -- without leaving your terminal.
claude plugin marketplace add TeemuSo/launchguard-skill && claude plugin install launchguard@launchguard-skillPaste into your terminal, then open a new Claude Code session
One command adds the skill to Claude Code. It reads your project files to find deployment URLs and Supabase credentials automatically.
claude plugin marketplace add TeemuSo/launchguard-skill && claude plugin install launchguard@launchguard-skillTell Claude to scan your app. It runs an external security audit from our servers -- probing every surface an attacker would reach.
/launchguard scan myapp.comClaude presents findings with severity, evidence, and impact. Then it offers to fix the issues directly in your codebase -- RLS policies, key rotation, bucket permissions.
Missing RLS, open read/write, row counts
Service role keys in client JavaScript
Publicly listable buckets and files
Server functions callable without auth
Open to anonymous callers
Found via PostgREST error hints
Every finding includes evidence -- actual data from the probe, not guesswork. Write tests use PostgREST's tx=rollback so nothing is persisted.
Deploy-triggered monitoring (Pro) + free manual re-scan
After fixing issues, Claude can connect Guard for continuous monitoring (Pro). Guard re-scans automatically on every deploy and emails you only when something breaks. Free users get a manual re-scan button and a heartbeat of the last verified state.
Free: the full scan, AI-authored fix (free signup), and HTTP red-green verdict. Pro: the remembered layer. Continuous re-scan on every deploy, regression history, credential custody, browser testing, and governance.
Follows the Agent Skills open standard
Scan your app in 40 seconds
Free security scanning. No signup. No config.