AgentLint
Claude Code plugin that lints a repo for AI-agent compatibility with 33 evidence-backed checks across 5 dimensions.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for AgentLint, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
AgentLint scans a repository for how agent-friendly it is, running 33 evidence-backed checks across five dimensions (structure, docs, tooling, etc.). It surfaces issues that make a repo hard for AI agents to work in and packages the checks as a Claude Code plugin with commands.
Key features and capabilities
- 33 evidence-backed agent-readiness checks
- 5 scoring dimensions
- Repo-level lint report
Use cases
- Audit a repo for AI-agent compatibility
- Improve a codebase so agents work more reliably