
Your AI coding agent is only as reliable as the harness around it. Measure that harness in seconds w
Your AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.
Skills, subagents and hooks shipped as a Claude Code / Cursor plugin are invisible (repo scan and --scope user)
GitHub dependency-review reports "unknown license" for action subdirectory
Add support to "astral ty" type check in python
HKS-01..05 false negative when the scan root is itself a .claude directory
Harness Score 1.6: expand multi-harness vendor coverage