**Degree of freedom: MIXED** — Fit, presence, and adopt/defer `[HIGH freedom]`; Phase 0 topology probes `[LOW freedom — run exactly]`. Never mark a pattern Missing if its tier is N/A.

**Degree of freedom: MIXED** — Offender triage and swap choice `[HIGH freedom]`; Phase 1 production build + analyser `[LOW freedom — run exactly]`.

**Degree of freedom: MIXED** — Phases 0–2 `[HIGH freedom]`; Phase 3 high-risk hand-trace `[LOW freedom — run exactly]`. Do not re-run the transform.

**Degree of freedom: MIXED.**

**Degree of freedom: HIGH** — quantify and plan. Phase 2 stays plan-only until approved. Never propose a cut that weakens backups (`plan-backup-dr`).

**Degree of freedom: MIXED** — Phases 0–1 `[HIGH freedom]`; Phase 2 sandbox `[LOW freedom — run exactly]`, sandbox only: a real purchase charges a real card and cannot be undone from here.

**Degree of freedom: MIXED** — Scope, matrix, and severity `[HIGH freedom]`; Phase 0 detection searches `[LOW freedom — run exactly]`. **Do not write exploit or payment-fraud PoCs** — quote the missing control, never a replay or spoof recipe.

Read-only conformance audit of a full-stack app against RealWorld ("Conduit"): API spec, shared E2E suite, closest-stack reference. Use when "audit against RealWorld", "Conduit conformance", or "is my full-stack app complete?".

Read-only production-resilience audit: timeouts, bounded retries, circuit breakers, idempotency, rate limits, graceful degradation, PII in logs. Use when "resilience audit" or "will this survive real traffic?".

**Degree of freedom: MIXED** — Phases 0–1 `[HIGH freedom]`; Phase 2 routing dry-run `[LOW freedom]` — skip explicitly if the harness cannot show selection. The retired `audit-responsive-layout` name appears in your report only as a dangling-reference finding, never as a handoff.

**Degree of freedom: MIXED** — Steps 1–3 judgment `[HIGH freedom]`; Step 0 `gh` inventory and Step 4 deletes `[LOW freedom — run exactly]`.

Closure mode for one approved plan: finish every open item and connected deferral, verify each acceptance criterion, require completion-judge PASS. Use when "complete everything", "don't defer", "fix out of scope too", or a plan was falsely marked done.

Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.

**Degree of freedom: MIXED.** Which query/index/N+1 to fix `[HIGH freedom]`; existing-index probes and EXPLAIN ANALYZE `[LOW freedom — run exactly]`.

**Degree of freedom: MIXED** — Steps 0, 1, 3 `[HIGH freedom]`; Steps 2 and 4 MCP/SQL probes `[LOW freedom — run exactly]` (run the query; do not invent a schema).

**Degree of freedom: MIXED.** Root-cause judgment `[HIGH freedom]`; the red feedback loop and verify-green re-run `[LOW freedom — run exactly]`.

**Degree of freedom: MIXED.** Copy and layout judgment `[HIGH freedom]`; stack detect, markup, send, and preview `[LOW freedom — run exactly]`.

**Degree of freedom: MIXED.** Heuristic mapping `[HIGH freedom]`; three-viewport capture, DOM forensics `[LOW freedom — run exactly]`.

**Degree of freedom: MIXED.** Recovering the model `[HIGH freedom]`; do-not-invent, shrink-only baseline, and deliberate-violation probes `[LOW freedom — run exactly]`.

**Degree of freedom: MIXED.** Sequence content and cadence `[HIGH freedom]`; trigger-before-timer rule, exit conditions, consent, idempotent sends, and event names `[LOW freedom — run exactly]`.