drskill adds trace-based auditing for agent loadouts, skills, and MCP triggers
dbreunig · x · 2026-07-25
The author says drskill is becoming a useful tool for debugging agent loadouts, skills, MCP development, and CI security for contexts.
The new capability lets users audit how MCPs and Skills are triggered globally or within a project by analyzing traces. The screenshots show scans that detect missing skill descriptions, duplicate skills, and an audit view of which skills were invoked in a session.
More from coding & agent
- Hyperagent says Opus 5 is stronger, but GPT-5.6 Sol is cheaper to deploy — TawohAwa · 2026-07-25
- Open-source Sana.ai MCP tool syncs meeting transcripts to local agent workflows — --lael-- · 2026-07-25
- Study finds async AI coding agents drive far bigger output gains than autocomplete — NathanpmYoung · 2026-07-25
- Developers still struggle to get SM 12.0 GPUs into CI and GitHub Actions — SkyLi0n · 2026-07-25
- Token compression can miss the real bill: transcript resend and cache writes dominate — KitchenAmoeba4438 · 2026-07-25
- Open-weight coding-agent router hits 79.8% on Terminal-Bench 2.1 for $76 — kimmonismus · 2026-07-25