dxkit-looplisted

# dxkit-loop This skill owns the **loop pack**: the deterministic preflight/postflight layer that keeps an autonomous coding loop from declaring "done" while it has introduced net-new findings. Reach for it to set the gate up, to explain a block, or to tune the posture. ## What the loop pack is When Claude Code runs in a loop (it keeps working until it decides to stop), a **Stop hook** runs `vyuh-dxkit hook stop-gate` every time the agent tries to stop. The gate re-runs the guardrail check against the baseline and: - **net-new findings → blocks the stop** and feeds the exact findings back to the model so it repairs them, then tries to stop again; - **clean → allows the stop** (optionally after a configured test command passes); - **gate can't run (no baseline / config error) → blocks once for the operator** (a problem the model can't fix), then allows on the next attempt to avoid thrashing. Every Stop event is appended to an audit trail at `.dxkit/loop/ledger.jsonl`. The value is **predictability, not a new scanner**: the gate bounds the "loop shipped debt and never fixed it" failure mode to zero. It uses the same findings, baseline, and identity contract as the rest of dxkit — it does not detect anything new. ## See it first (no setup) ```bash # No API key, no Claude Code, no scanners — runs the real gate over an example # finding and shows the block → repair → clean flow offline. npx vyuh-dxkit demo loop-guardrail ``` ## Setup ```bash # Register the Stop hook + CL