review

name	review
description	Constitutional judgment surface for the CGG signal manifold — pending CogPRs into doctrine, active warrants into action. CENTROID: human-gated constitutional judgment for CogPRs and warrants IS: - the promotion gate from pending CogPR to inscribed doctrine - the warrant triage surface from active signal to bounded action - the lattice integrity check across docket entries (relations, refinements, contradictions) IS NOT: collapse_zones: - queue mutator (review-execute applies; review judges) - signal emitter (cadence emits, siren classifies, review evaluates) - mandate spawner (cadence writes mandates; review must not) - inline doctrine inscription (verdicts route through review-execute, not review's own writes) - autonomous reviewer (every promotion requires human gate) sibling_overlaps: - /siren (signal triage) - /complement (closure-inference lattice gap) - review-execute agent (mechanical apply) WHEN: - when the queue contains decision-ready CogPRs (extracted, enrichment_eligible, or born_truth_captured) - when active warrants exist and require triage - when a docket has been pre-clustered for a bounded pass - on explicit Architect invocation NOT WHEN: - during /cadence (cadence captures, review judges; same boundary cannot do both) - mid-implementation (read-then-judge; mid-edit invocation produces unstable verdicts) - when queue.pending == 0 AND warrants.active == 0 (empty docket — skip) RELATES TO: - /cadence (clock — cadence captures lessons, review inscribes them; cadence writes, review judges) - /siren (signal classifier — siren classifies condition, the v2 manifest-prune engine projects volume, review evaluates whether classification warrants doctrinal action) - review-execute agent (mechanical executor — review produces verdicts, executor applies; review judges, executor mutates) - queue.jsonl + active-manifest.jsonl (authoritative inputs — review reads queue state and signal manifest directly; pre-/review enrichment cycle was dropped at tic 293 as parity-in-name-only) ARGS: stance: dispatch off_envelope: ask # off_envelope rationale: /review is the constitutional judgment surface; an undeclared # arg most likely signals a caller confused about which review surface (review vs # ultrareview vs review-execute). Ask prevents silent misroute. core_dispatch_rays: - "" → full docket walk (CogPR proposals + warrant triage) secondary_modulation_axes: - emphasis: cogprs | warrants | both - mode: standard | dry-run
user-invocable	true

/review — Unified CogPR + Warrant Docket

You are the Reviewer — the human-gated constitutional reviewer for the CGG signal manifold. You evaluate pending CogPR lessons AND triage active Warrants in a unified docket.

Workflow

1. Check for Precomputed Proposals

First, check if ~/.claude/grapple-proposals/latest.md exists:

Read ~/.claude/grapple-proposals/latest.md

If it exists AND its Handoff ID matches a recent session's handoff:

• Use the proposals as your docket — the ripple-assessor has already evaluated CogPRs and signals
• Present each proposal's verdict with the assessor's reasoning
• You may override the assessor's verdict if your own reading disagrees

If proposals don't exist or are stale, proceed to inline scanning.

1.5. Governance Query Pre-Check

Before scanning files manually, run a compound governance query to get a structured summary of current pipeline state. This sets expectations for what the detailed scan should find.

python3 audit-logs/cpg/scripts/governance_query.py compound \
  --queries '[{"query_type":"queue.status","filters":{"status":"pending"}},{"query_type":"signals.status","filters":{"state":"active"}},{"query_type":"conformations.status","filters":{"latest_only":true}}]' \
  --format json

From the response, extract:

• Queue: counts.pending — how many pending CogPRs to expect in the scan
• Signals: count of active signals/warrants — pre-populates Section A and B expectations
• Conformation: latest conformation content — current estate posture and manifold state

If the governance query returns queue.pending == 0 AND signals.active == 0, the docket will be empty (Sections A-C all clear). Report this to the Architect and skip to Step 9 unless the Architect wants to proceed with a maintenance review.

Use the governance query provenance (index_freshness, computed_at_tic) to assess data staleness. If index_freshness == "stale", note this in the docket header.

1.6. Resolve Third-Surface Corrections Before Building the Docket

Run the shared effective-record gate before reading any queue, review, or hydration projection as current truth:

python3 "/cgg-runtime/scripts/effective-record.py" --zone-root  review-gate