# Pack Quality Bar

Every `/audit` check pack must clear this bar before being shipped. The goal is uniform signal quality across packs: an agent running any pack should get deterministic, well-scoped prompts — not guesswork.

A pack meets the quality bar when its `checks.md` contains a filled-in Scope section (one focused paragraph stating what is and is not covered), an `applies_when` rationale table with one row per gating condition, and a per-check block for every check declared in `pack.json`. Each per-check block must name the detection mode (`tool`, `llm`, or `hybrid`), include a full LLM instruction for any LLM or hybrid check (specific enough that two different agents would reach the same finding set), cite a real spine tool for any tool or hybrid check, provide severity and confidence rationale grounded in impact and precision rather than vague intuition, and supply at least one true-positive fixture alongside one true-negative fixture to prevent prompt drift across pack versions. Additionally, `scripts/lint-pack.py` must pass cleanly against the pack, and once `schemas/severity-rubric.json` exists (Epic 1.5), every check-id must have a rubric entry — packs with orphaned check-ids will fail linting. Incomplete fields, placeholder comment text, or a missing `## Quality Checklist` section are all linting failures.