verify-llm-artifacts

# Verify LLM Artifacts Findings Second-pass verification for `.beagle/llm-artifacts-review.json`. The detection pass optimizes for recall; this pass optimizes for **precision** so agents do not remove or “clean” code that is still required. ## When to run - After `/beagle-core:review-llm-artifacts` (especially full-project scans). - Before `/beagle-core:fix-llm-artifacts` when findings include **deletions**, **dead code**, or **High** risk. - Whenever past runs flagged artifacts that should not have been removed. ## Inputs - **Required:** `.beagle/llm-artifacts-review.json` from a completed review. - **Optional:** `$ARGUMENTS` — `--priority-only` (verify `dead_code` and any `fix_action` of `delete` first; then others), `--id N` (single finding id). If the review file is missing, exit with: `Run /beagle-core:review-llm-artifacts first.` ## Prerequisite skills 1. Load `Skill(skill: "beagle-core:review-verification-protocol")` — general anti–false-positive discipline. 2. Load `Skill(skill: "beagle-core:llm-artifacts-detection")` — category criteria for what counts as a real issue. ## Instructions ### Hard gates Objective pass conditions before you claim verification is done: 1. **Input parse:** The JSON load command in step 1 exits 0 (no traceback). **Pass:** valid JSON on disk at `.beagle/llm-artifacts-review.json`. 2. **Evidence before verdict:** For each finding you adjudicate, you have applied [references/verification-checklist.md](references/verification-checkli...