work-auditlisted

# Work / 7. Audit Audit without changing source files. Keep the parent orchestrator accountable for scope, verification, decisions, and any later edits. Read [../QUALITY.md](../QUALITY.md) first. Apply its quality bar, never preserve backwards compatibility, and treat concrete evidence as the handoff requirement. ## Fixed route - Launch exactly one `gpt-5.6-sol` subagent at `xhigh` effort with `fork_turns: none`. - Give it a fun call sign, the exact task statement, complete read-only brief, exact ownership, source of truth, risk axes, exclusions, acceptance checks, and validation requirements. - Keep early hypotheses independent and require concrete locations, reproductions, traces, or commands; reject status reports and unsupported “routine” conclusions. - Require it to register the exact goal before inspection and complete it only after its checks pass. - Let the analyst run until it returns findings, a real blocker, or a user-input request. Do not cancel it because a polling window or arbitrary wall-clock interval elapsed; a wait timeout is not a failure. - The analyst must not edit, commit, deploy, spawn, or delegate. - Report the successful launch as a compact table with `Agent`, `Working on`, `Goal`, `Ownership`, and `Model`. ## Audit 1. Resolve the target: working tree, commit, branch comparison, artifact, runtime flow, or named files. 2. Identify the source of truth and material risk axes: correctness, regressions, security, data loss, accessibility, performance