Sheriff

This server turns SARIF static analysis reports into a managed work queue for AI agents. It exposes a single tool with seven actions: load reports from tools like Semgrep or ESLint, pull the next batch of issues grouped by file, mark them as fixed or won't-fix, check progress, and export results. The batching solves a real problem where dumping 100+ issues into context overwhelms the agent, and the persistent state means your progress survives context compaction or session restarts. Reach for this when you're drowning in linter output and want the AI to systematically work through it file by file instead of losing its place halfway through.