audit-instructions
Purpose
Audit whether the instructions you have written for Claude Code are still earning their context cost against current model capability. As models improve, prior-model-era scar tissue accretes: workarounds for mistakes the model no longer makes, prescriptive step lists that now constrain more than they help, bare prohibitions, and show-your-thinking directives. This skill sweeps the locally-owned instruction surfaces, cites each finding to current official prompting doctrine, tiers it by how confident the evidence can be, and packages proposed removals or rewrites as a human-gated diff — so instruction surfaces shrink as models get better instead of only ever growing.
The check catalog — the checks I1–I16, their evidence tier, authority tag, severity, per-surface
applicability, and the OPINION-tier enablement policy — lives in
reference/criteria.md; the deterministic pre-scan is
${CLAUDE_PLUGIN_ROOT}/skills/audit-instructions/scripts/instruction-scan.sh.
One check has a different unit of judgment — do two surfaces contradict each other? — and Phase B2
answers it against reference/conflict-criteria.md.