Architectural invariants and code quality analysis, enforced inside your AI agent's edit loop. MCP server + CLI + Claude Code plugin. TypeScript, JavaScript, Go.
Cyclomatic complexity, but for LLM prompts. Static analysis that finds the business logic hidden in your prompts, scores it, and gates it in CI. Python, TypeScript, JavaScript, PHP.
Architecture linter for Go: import rules, tiers, deep-scan method calls and dependency injection — declared as code in a Go DSL spec (YAML legacy), checked on every CI run. Hexagonal/onion/DDD-friendly.
🐳 Fast, stack-aware Dockerfile linter — flags image bloat and bad-practice patterns with stable rule IDs and CI-friendly JSON. Single Go binary, zero dependencies.
Laravel-aware static analysis for the debt AI coding agents leave behind. 24 rules, git-diff review, a Rector and Pint fix pass, Pest expectations, CI annotations, agent rulesets and an MCP server. Deterministic, local, no LLM.
Scan your codebase for AI slop. Get a Slop Score. Ship clean. A zero-dependency CLI (85 detectors: security, performance, code-quality, design tells) + a 181-pattern Anti-Slop Protocol for AI coding agents.