generation-auditlisted

# generation-audit — harness audit at a model generation change The procedure for Scaffold Dissolution's (`rules/common/akc-cycle.md`) **third trigger = model generation change**. One run performs two checks, carrying line fixes through to application and asset-level verdicts through to the stocktakes. | Check | Compared against | Engine | |---|---|---| | runtime cross-check (Phase 1–2) | the system prompt and tool descriptions actually loaded at inference time | this skill | | dated-pattern scan (Phase 3) | the outdated writing patterns listed in the target model's official guide | `/claude-api prompt-audit` | Anthropic updates the dated-pattern table and the target model's behavior inside the `/claude-api` skill with each model release, so they are not copied here — this skill holds only this harness's scope, exclusions, application conventions, and recording, plus the runtime cross-check that prompt-audit does not have. Asset-level verdicts (Retire / Merge, etc.) are owned by the stocktake for each asset class (ADR-0022); this skill stands on the side that supplies the evidence. ## Phase 0 — Target model and scope - **Target model**: the model newly assigned to a role in this harness. When models differ by role, look at an asset through the model of the role that reads it (task-triage's packet template → build role; rules / CLAUDE.md / output style → every session; judge-role skills → judge role) - **Scope**: the prompt surface of `~/.claude` — `rules/common/`, `C