axstack 0.20.9 → 0.20.11

package/docs/workflows.md

@@ -50,8 +50,8 @@ role.
 
 | Preset | Author | Ordered peer reviewers | Astra / Fable advisers | Auditor |
 | --- | --- | --- | --- | --- |
-| `mixed` | Sol medium | Sol medium; Opus medium | Astra high / Fable high | Luna max |
-| `codex-only` | Sol medium | Sol medium; Terra xhigh | Astra high / unavailable | Luna max |
+| `mixed` | Sol medium | Sol medium; Opus medium | Astra high / Fable high | Luna xhigh |
+| `codex-only` | Sol medium | Sol medium; Luna xhigh | Astra high / unavailable | Luna xhigh |
 | `claude-only` | Opus medium | Opus medium; Sonnet xhigh | unavailable / Fable high | Sonnet xhigh |
 
 The installed `<skills-dir>/axstack/roles.json` adds the selected preset name:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.20.9",
+  "version": "0.20.11",
   "description": "Axstack installer and setup CLI: installs owned chat skills and role data, configures supported harness settings, and checks Orca capabilities.",
   "keywords": [
     "claude-code",

package/profiles/presets/claude-only.json

@@ -23,7 +23,7 @@
       "id": "axstack-owner",
       "name": "Axstack PR owner",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
       "notes": "Persistent PR owner: one owner per PR, accountable for candidate, fixes, verification evidence, and monitoring. May delegate coding but never edits a worker-owned candidate concurrently. Launches eligible independent reviewers."
@@ -32,7 +32,7 @@
       "id": "axstack-author",
       "name": "Axstack author",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
       "notes": "Ordinary implementation and repairs. Uses strict red-green-refactor and remains the exclusive writer for a candidate. Validate configured availability at launch; hold affected work without fallback."
@@ -41,7 +41,7 @@
       "id": "axstack-reviewer-primary",
       "name": "Axstack reviewer (primary)",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
       "notes": "Primary reviewer in the ordered claude-only peer pair: Opus medium followed by Sonnet xhigh. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated."
@@ -68,7 +68,7 @@
       "id": "axstack-research-requirements",
       "name": "Axstack research requirements",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
       "notes": "Research requirements analyst: scopes bounded questions and acceptance for a research task. Validate configured availability at launch; hold affected work without fallback."
@@ -77,7 +77,7 @@
       "id": "axstack-research-code",
       "name": "Axstack research code",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
       "notes": "Research code investigator: verifies behavior against inspected code and executable evidence. Validate configured availability at launch; hold affected work without fallback."
@@ -167,10 +167,10 @@
       "id": "axstack-debug-investigator-1",
       "name": "Axstack debug investigator 1",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
-      "notes": "Debug investigator seat 1. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats claude-opus-5 at medium effort because it has fewer model families."
+      "notes": "Debug investigator seat 1. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats claude-opus-5-5 at medium effort because it has fewer model families."
     },
     {
       "id": "axstack-debug-investigator-2",
@@ -185,10 +185,10 @@
       "id": "axstack-debug-investigator-3",
       "name": "Axstack debug investigator 3",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Debug investigator seat 3. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats claude-opus-5 at high effort because it has fewer model families."
+      "notes": "Debug investigator seat 3. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats claude-opus-5-5 at high effort because it has fewer model families."
     },
     {
       "id": "axstack-debug-investigator-4",

package/profiles/presets/codex-only.json

@@ -23,7 +23,7 @@
       "id": "axstack-owner",
       "name": "Axstack PR owner",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "high",
       "notes": "Persistent PR owner: one owner per PR, accountable for candidate, fixes, verification evidence, and monitoring. May delegate coding but never edits a worker-owned candidate concurrently. Launches eligible independent reviewers."
@@ -32,7 +32,7 @@
       "id": "axstack-author",
       "name": "Axstack author",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "medium",
       "notes": "Ordinary implementation and repairs. Uses strict red-green-refactor and remains the exclusive writer for a candidate. Validate configured availability at launch; hold affected work without fallback."
@@ -41,25 +41,25 @@
       "id": "axstack-reviewer-primary",
       "name": "Axstack reviewer (primary)",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "medium",
-      "notes": "Primary reviewer in the ordered codex-only peer pair: Sol medium followed by Terra xhigh. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated."
+      "notes": "Primary reviewer in the ordered codex-only peer pair: Sol medium followed by Luna xhigh. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated."
     },
     {
       "id": "axstack-reviewer-secondary",
       "name": "Axstack reviewer (secondary)",
       "provider": "codex",
-      "model": "gpt-5.6-terra",
+      "model": "gpt-6-luna",
       "modeId": "full-access",
       "thinkingOptionId": "xhigh",
-      "notes": "Secondary reviewer in the ordered codex-only peer pair: Sol medium followed by Terra xhigh. Eligible authored reviewer for a Sol-authored candidate. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated."
+      "notes": "Secondary reviewer in the ordered codex-only peer pair: Sol medium followed by Luna xhigh. Eligible authored reviewer for a Sol-authored candidate. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated."
     },
     {
       "id": "axstack-checker",
       "name": "Axstack tracker checker",
       "provider": "codex",
-      "model": "gpt-5.6-luna",
+      "model": "gpt-6-luna",
       "modeId": "full-access",
       "thinkingOptionId": "low",
       "notes": "Report-only discrepancy checker for the selected external tracker (Linear or GitHub Issues). Never mutates the tracker; the driver independently verifies evidence before applying updates. A null model means explicit user selection is required before dispatch and must never launch a provider default."
@@ -77,7 +77,7 @@
       "id": "axstack-research-code",
       "name": "Axstack research code",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "medium",
       "notes": "Research code investigator: verifies behavior against inspected code and executable evidence. Validate configured availability at launch; hold affected work without fallback."
@@ -86,7 +86,7 @@
       "id": "axstack-research-web",
       "name": "Axstack research web",
       "provider": "codex",
-      "model": "gpt-5.6-terra",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "low",
       "notes": "Research web reader: gathers primary-source facts efficiently. Validate configured availability at launch; hold affected work without fallback."
@@ -113,7 +113,7 @@
       "id": "axstack-explainer",
       "name": "Axstack explainer",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "high",
       "notes": "Complex visual explanation author: traces systems, changes, and implementation gaps in requested artifacts and verifies rendered behavior where applicable. Validate configured availability at launch; hold affected work without fallback."
@@ -122,16 +122,16 @@
       "id": "axstack-explainer-review",
       "name": "Axstack explainer reviewer",
       "provider": "codex",
-      "model": "gpt-5.6-luna",
+      "model": "gpt-6-luna",
       "modeId": "full-access",
-      "thinkingOptionId": "max",
+      "thinkingOptionId": "xhigh",
       "notes": "Independent visual explanation reviewer: checks the exact artifact for source fidelity and rendered behavior where warranted. Any artifact change invalidates its review. Validate configured availability at launch; hold affected work without fallback."
     },
     {
       "id": "axstack-explore-codebase",
       "name": "Axstack codebase explorer",
       "provider": "codex",
-      "model": "gpt-5.6-terra",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "xhigh",
       "notes": "Codebase mapper: explores repository structure and interfaces for research and handoff context. Validate configured availability at launch; hold affected work without fallback."
@@ -140,7 +140,7 @@
       "id": "axstack-explore-execution",
       "name": "Axstack execution explorer",
       "provider": "codex",
-      "model": "gpt-5.6-terra",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "low",
       "notes": "Execution explorer: runs bounded checks of runtime behavior where authorized. Validate configured availability at launch; hold affected work without fallback."
@@ -149,7 +149,7 @@
       "id": "axstack-monitor",
       "name": "Axstack monitor",
       "provider": "codex",
-      "model": "gpt-5.6-terra",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "low",
       "notes": "Optional independent read-only observer for a standalone PR watch. Reads GitHub, feedback, and checks, persists event IDs, and wakes the owner only for a new actionable event. Never sends, authors, reviews, replies, or acts as either reusable PR manager. Healthy snapshots stay quiet."
@@ -158,46 +158,46 @@
       "id": "axstack-auditor",
       "name": "Axstack auditor",
       "provider": "codex",
-      "model": "gpt-5.6-luna",
+      "model": "gpt-6-luna",
       "modeId": "full-access",
-      "thinkingOptionId": "max",
+      "thinkingOptionId": "xhigh",
       "notes": "Read-only end-of-run and checkpoint auditor. Collects scope and outcome evidence with counts and denominators and reports PASS, FAIL, or UNKNOWN without inventing numbers. Never edits, merges, activates, or audits itself."
     },
     {
       "id": "axstack-debug-investigator-1",
       "name": "Axstack debug investigator 1",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "medium",
-      "notes": "Debug investigator seat 1. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats gpt-5.6-sol at medium effort because it has fewer model families."
+      "notes": "Debug investigator seat 1. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats gpt-6-sol at medium effort because it has fewer model families."
     },
     {
       "id": "axstack-debug-investigator-2",
       "name": "Axstack debug investigator 2",
       "provider": "codex",
-      "model": "gpt-5.6-terra",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "low",
-      "notes": "Debug investigator seat 2. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats gpt-5.6-terra at low effort because it has fewer model families."
+      "notes": "Debug investigator seat 2. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats gpt-6-sol at low effort because it has fewer model families."
     },
     {
       "id": "axstack-debug-investigator-3",
       "name": "Axstack debug investigator 3",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "high",
-      "notes": "Debug investigator seat 3. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats gpt-5.6-sol at high effort because it has fewer model families."
+      "notes": "Debug investigator seat 3. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats gpt-6-sol at high effort because it has fewer model families."
     },
     {
       "id": "axstack-debug-investigator-4",
       "name": "Axstack debug investigator 4",
       "provider": "codex",
-      "model": "gpt-5.6-terra",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "xhigh",
-      "notes": "Debug investigator seat 4. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats gpt-5.6-terra at xhigh effort because it has fewer model families."
+      "notes": "Debug investigator seat 4. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats gpt-6-sol at xhigh effort because it has fewer model families."
     },
     {
       "id": "axstack-arena-judge-astra",

package/profiles/presets/mixed.json

@@ -23,7 +23,7 @@
       "id": "axstack-owner",
       "name": "Axstack PR owner",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
       "notes": "Persistent PR owner: one owner per PR, accountable for candidate, fixes, verification evidence, and monitoring. May delegate coding but never edits a worker-owned candidate concurrently. Launches eligible independent reviewers."
@@ -32,7 +32,7 @@
       "id": "axstack-author",
       "name": "Axstack author",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "medium",
       "notes": "Ordinary implementation and repairs. Uses strict red-green-refactor and remains the exclusive writer for a candidate. Validate configured availability at launch; hold affected work without fallback."
@@ -41,7 +41,7 @@
       "id": "axstack-reviewer-primary",
       "name": "Axstack reviewer (primary)",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "medium",
       "notes": "Primary reviewer in the ordered mixed peer pair: Sol medium followed by Opus medium. Eligible authored reviewer for an Opus-authored candidate. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated."
@@ -50,7 +50,7 @@
       "id": "axstack-reviewer-secondary",
       "name": "Axstack reviewer (secondary)",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
       "notes": "Secondary reviewer in the ordered mixed peer pair: Sol medium followed by Opus medium. Eligible authored reviewer for a Sol-authored candidate. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated."
@@ -68,7 +68,7 @@
       "id": "axstack-research-requirements",
       "name": "Axstack research requirements",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
       "notes": "Research requirements analyst: scopes bounded questions and acceptance for a research task. Validate configured availability at launch; hold affected work without fallback."
@@ -77,7 +77,7 @@
       "id": "axstack-research-code",
       "name": "Axstack research code",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "medium",
       "notes": "Research code investigator: verifies behavior against inspected code and executable evidence. Validate configured availability at launch; hold affected work without fallback."
@@ -86,7 +86,7 @@
       "id": "axstack-research-web",
       "name": "Axstack research web",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "low",
       "notes": "Research web reader: gathers primary-source facts efficiently. Validate configured availability at launch; hold affected work without fallback."
@@ -122,9 +122,9 @@
       "id": "axstack-explainer-review",
       "name": "Axstack explainer reviewer",
       "provider": "codex",
-      "model": "gpt-5.6-luna",
+      "model": "gpt-6-luna",
       "modeId": "full-access",
-      "thinkingOptionId": "max",
+      "thinkingOptionId": "xhigh",
       "notes": "Independent visual explanation reviewer: checks the exact artifact for source fidelity and rendered behavior where warranted. Any artifact change invalidates its review. Validate configured availability at launch; hold affected work without fallback."
     },
     {
@@ -140,7 +140,7 @@
       "id": "axstack-explore-execution",
       "name": "Axstack execution explorer",
       "provider": "codex",
-      "model": "gpt-5.6-terra",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "low",
       "notes": "Execution explorer: runs bounded checks of runtime behavior where authorized. Validate configured availability at launch; hold affected work without fallback."
@@ -149,7 +149,7 @@
       "id": "axstack-monitor",
       "name": "Axstack monitor",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
       "notes": "Optional independent read-only observer for a standalone PR watch. Reads GitHub, feedback, and checks, persists event IDs, and wakes the owner only for a new actionable event. Never sends, authors, reviews, replies, or acts as either reusable PR manager. Healthy snapshots stay quiet."
@@ -158,16 +158,16 @@
       "id": "axstack-auditor",
       "name": "Axstack auditor",
       "provider": "codex",
-      "model": "gpt-5.6-luna",
+      "model": "gpt-6-luna",
       "modeId": "full-access",
-      "thinkingOptionId": "max",
+      "thinkingOptionId": "xhigh",
       "notes": "Read-only end-of-run and checkpoint auditor. Collects scope and outcome evidence with counts and denominators and reports PASS, FAIL, or UNKNOWN without inventing numbers. Never edits, merges, activates, or audits itself."
     },
     {
       "id": "axstack-debug-investigator-1",
       "name": "Axstack debug investigator 1",
       "provider": "claude",
-      "model": "claude-opus-5",
+      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
       "notes": "Debug investigator seat 1. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity."
@@ -176,7 +176,7 @@
       "id": "axstack-debug-investigator-2",
       "name": "Axstack debug investigator 2",
       "provider": "codex",
-      "model": "gpt-5.6-sol",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "medium",
       "notes": "Debug investigator seat 2. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity."
@@ -194,7 +194,7 @@
       "id": "axstack-debug-investigator-4",
       "name": "Axstack debug investigator 4",
       "provider": "codex",
-      "model": "gpt-5.6-terra",
+      "model": "gpt-6-sol",
       "modeId": "full-access",
       "thinkingOptionId": "low",
       "notes": "Debug investigator seat 4. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity."

package/skills/axstack/references/automations.md

@@ -238,6 +238,9 @@ or send outcome, not pending CI. Waiting state belongs in GitHub and the compact
 record, never in an idle model, per-PR timer, or polling loop.
 Follow the [private evidence archive](evidence-archive.md) when evidence is the
 only local state to preserve; archive success does not relax any other guard.
+For a completed, forge-merged PR-job, classified reviewer scratch may instead
+follow [axstack-cleanup](../../axstack-cleanup/SKILL.md)'s compact receipt and
+exact-path guards. This does not release active jobs or manager pass workspaces.
 
 ## Review and repair authority
 
@@ -307,6 +310,8 @@ terminals, unknown liveness, `user_takeover`, and ambiguous publication state.
 Never classify all dirt as evidence. If explicitly classified evidence is the
 last retention reason, apply and verify the [private evidence archive](evidence-archive.md),
 update durable continuity, and read it back before native retirement.
+The completed, forge-merged PR-job reviewer scratch exception above uses
+axstack-cleanup; it never changes manager pass preservation or retirement guards.
 
 For the manager pass only, verify native run/workspace identity, exclusive
 automation ownership, no unsettled descendants, and a fresh terminal inventory

package/skills/axstack/references/orca-runtime.md

@@ -95,8 +95,13 @@ owner. Remove only that exact validated owned path, with no glob or parent-root
 deletion; never wipe a general cache. Uncertain temporary files are preserved
 for later reconciliation. Incidental tool-managed caches are not review evidence.
 Before removing a reviewer worktree, preserve its report and supporting evidence
-in the driver's Orca workspace and update the run record's paths. Terminal
-release alone is not permission to discard evidence or remove the worktree.
+in the driver's Orca workspace and update the run record's paths. For a settled
+merged run with a confirmed forge merge, the compact durable receipt in
+[axstack-cleanup](../../axstack-cleanup/SKILL.md) satisfies this preservation
+rule only after its classification, readback, and removal guards pass. Preserve
+active or unmerged review evidence and unique evidence whose bytes must survive;
+uncertain ownership or evidence holds. Terminal release alone is not permission
+to discard evidence or remove the worktree.
 
 ## Consume, settle, and recover
 

package/skills/axstack/references/routing.md

@@ -34,10 +34,10 @@ Role IDs:
 
   | Preset | Author | Reviewer (model/effort) |
   | --- | --- | --- |
-  | `mixed` | Codex / Sol (`codex/gpt-5.6-sol`) | `axstack-reviewer-secondary` (`claude/claude-opus-5` medium) |
-  | `mixed` | Claude / Opus (`claude/claude-opus-5`) | `axstack-reviewer-primary` (`codex/gpt-5.6-sol` medium) |
-  | `codex-only` | Codex / Sol (`codex/gpt-5.6-sol`) | `axstack-reviewer-secondary` (`codex/gpt-5.6-terra` xhigh) |
-  | `claude-only` | Claude / Opus (`claude/claude-opus-5`) | `axstack-reviewer-secondary` (`claude/claude-sonnet-5` xhigh) |
+  | `mixed` | Codex / Sol (`codex/gpt-6-sol`) | `axstack-reviewer-secondary` (`claude/claude-opus-5-5` medium) |
+  | `mixed` | Claude / Opus (`claude/claude-opus-5-5`) | `axstack-reviewer-primary` (`codex/gpt-6-sol` medium) |
+  | `codex-only` | Codex / Sol (`codex/gpt-6-sol`) | `axstack-reviewer-secondary` (`codex/gpt-6-luna` xhigh) |
+  | `claude-only` | Claude / Opus (`claude/claude-opus-5-5`) | `axstack-reviewer-secondary` (`claude/claude-sonnet-5` xhigh) |
 - `axstack-advisor-astra` and `axstack-advisor-fable` advise independently
   and author align arena candidates; `axstack-arena-judge-astra` and
   `axstack-arena-judge-fable` judge them. `axstack-auditor` audits;

package/skills/axstack-audit/SKILL.md

@@ -25,7 +25,7 @@ immediately before an actual auditor profile or session dispatch. Ordinary
 audit reading and record writing do not load it, and the auditor never
 dispatches.
 
-Core owns the `axstack-auditor` profile (codex/gpt-5.6-luna max) and its
+Core owns the `axstack-auditor` profile (codex/gpt-6-luna xhigh) and its
 invocation. This skill governs what that auditor reads, measures, and proposes.
 The user-chosen improvement mode is a tested, independently reviewed PR that a
 human merges.

package/skills/axstack-cleanup/SKILL.md

@@ -34,8 +34,8 @@ Never clean a manual chat, the current driver, `user_takeover`, an active or
 unknown worker, an unsettled descendant, or a resource with ambiguous ownership.
 Preserve dirty or unknown files, unpushed commits, unmerged useful work,
 ambiguous publication, and evidence that has not been durably preserved. Do not
-force, bulk-clean, override a hook failure, edit a runtime database, or add a
-scheduler, daemon, or state machine.
+force native removal, bulk-clean, override a hook failure, edit a runtime
+database, or add a scheduler, daemon, or state machine.
 
 ## Reconcile each candidate
 
@@ -57,13 +57,51 @@ Classify exact evidence files individually. Save the compact cleanup decision
 and identities in the private run record or another configured durable private
 location outside disposable worktrees. When the evidence archive applies, use
 its helper with either the existing PR identity or the non-PR Run and Task
-identity; never invent a PR number. Read back both the durable record and the
-archive manifest, including hashes and exact identities, before removing any
-source copy or workspace.
+identity; never invent a PR number. Read back the durable record and, when an
+archive is used, its manifest, including hashes and exact identities, before
+removing any source copy or workspace.
 
 Archive success proves only preservation of the listed bytes. It does not prove
 settlement, exit, ownership, a clean worktree, publication, or removal safety.
 
+For a settled merged run whose forge merge is confirmed, generated reviewer
+scratch is disposable after a compact durable receipt is written outside the
+review worktree and read back. Bind that receipt to the exact repository, Run,
+Task, Dispatch, reviewer workspace and terminal, exact head SHA and base SHA,
+review verdict, coverage and limitations, test and CI result pointers, and the
+user authorization and scope for cleanup. A raw reviewer report may be discarded
+after its verdict and limitations are compacted into that read-back receipt;
+use the private evidence archive for unique evidence whose exact bytes must
+survive. Raw reproducible probes and logs need not be archived solely to retire
+a completed review worktree.
+
+Use only a named run-owned scratch prefix recorded with the Dispatch. Require
+`git status --porcelain=v1 -z --untracked-files=all` to show all dirt as
+untracked files inside that run-owned scratch prefix; any tracked, staged,
+unmerged or unpushed work, dirty source, or dirt outside it holds. Validate that
+the detached checkout still matches the reviewed head and check local commits
+against recorded remote refs; unknown divergence holds. Validate that
+the exact reviewed scratch prefix names the recorded directory inside the exact
+reviewer worktree, never a repository-root target or symlink. Inspect every
+descendant for symlinks, hard links, special files, unknown content, user-owned
+files, or ignored files; any mismatch holds. Active or `user_takeover` terminals
+also hold.
+
+List the exact scoped path and all descendants with their types, confirm each
+belongs to generated reviewer scratch, and record that inventory. Dry-run the
+exact scoped path from the reviewer worktree root with
+`git clean -nd -- <exact reviewed scratch prefix>`
+with the concrete reviewed relative prefix substituted for the angle-bracket
+notation. Compare its sole target to the classified directory; an empty,
+partial, or different result holds. Re-read the compact receipt, complete Git
+status, directory contents, native ownership and liveness immediately before
+removal; any change holds. Then run `git clean -fd -- <same exact prefix>` with
+the identical concrete path and recheck clean Git status, recording the path and
+outcome. Use no unresolved variable as a destructive target. Never use `-x`, a
+glob, a repository-root target, extra force, or broad clean.
+This scratch decision does not waive any other preservation or native removal
+guard.
+
 ## Apply distinct native operations
 
 Treat these operations as separate decisions and receipts:

package/skills/axstack-explain/SKILL.md

@@ -48,12 +48,24 @@ immediately before an actual profile dispatch.
 
 ## 2. Choose proportional output
 
-1. For a simple request, answer concisely in the current chat. Use a compact
+1. Keep the primary reader-facing explanation to a maximum of 700 words in
+   chat, HTML, and every other requested format. Preserve in that primary view
+   the answer or purpose, key rationale, meaningful alternatives, main data or
+   operational boundary, status and uncertainty, and live reader questions
+   with evidence-supported answers, labeling any question the inspected
+   evidence does not answer as **unknown** or **open** rather than inventing an
+   answer. Count the primary artifact's reader-visible words, including
+   headings, table text, and diagram or figure labels and captions. An appendix
+   or collapsible content in the same artifact counts toward the 700-word
+   maximum. If the draft is longer, compress repetition first and move only
+   supporting detail to a separate linked ticket or appendix. Essential answers
+   must not be hidden behind links, and evidence must not be silently discarded.
+2. For a simple request, answer concisely in the current chat. Use a compact
    diagram when useful. This needs no mandatory agent or intermediate artifact.
-2. For a complex visual, use the configured `axstack-explainer` role to create
+3. For a complex visual, use the configured `axstack-explainer` role to create
    self-contained HTML, or use the requested artifact format. An explicit user
    theme wins; otherwise use the dark default.
-3. Profile IDs are presets, not availability proof. Before dispatch, follow the
+4. Profile IDs are presets, not availability proof. Before dispatch, follow the
    launch sequence and preserve the configured model, mode, and effort. Report
    an unavailable route; never substitute a model.
 

package/skills/axstack-review/SKILL.md

@@ -116,10 +116,10 @@ owns the event and settles after its skill-owned reviewers settle.
 
      | Preset | Actual author provider/model | Reviewer role (configured model/effort) |
      | --- | --- | --- |
-     | `mixed` | Codex / Sol (`codex/gpt-5.6-sol`) | `axstack-reviewer-secondary` (`claude/claude-opus-5` medium) |
-     | `mixed` | Claude / Opus (`claude/claude-opus-5`) | `axstack-reviewer-primary` (`codex/gpt-5.6-sol` medium) |
-     | `codex-only` | Codex / Sol (`codex/gpt-5.6-sol`) | `axstack-reviewer-secondary` (`codex/gpt-5.6-terra` xhigh) |
-     | `claude-only` | Claude / Opus (`claude/claude-opus-5`) | `axstack-reviewer-secondary` (`claude/claude-sonnet-5` xhigh) |
+     | `mixed` | Codex / Sol (`codex/gpt-6-sol`) | `axstack-reviewer-secondary` (`claude/claude-opus-5-5` medium) |
+     | `mixed` | Claude / Opus (`claude/claude-opus-5-5`) | `axstack-reviewer-primary` (`codex/gpt-6-sol` medium) |
+     | `codex-only` | Codex / Sol (`codex/gpt-6-sol`) | `axstack-reviewer-secondary` (`codex/gpt-6-luna` xhigh) |
+     | `claude-only` | Claude / Opus (`claude/claude-opus-5-5`) | `axstack-reviewer-secondary` (`claude/claude-sonnet-5` xhigh) |
 
      Provenance is matched on provider/model ID; record effort, but never use
      effort to create a mapping. Any other author provenance for the

package/src/roles.js

@@ -6,14 +6,14 @@ const PROVIDER_BOUNDS = Object.freeze({
 
 const AUTHORED_ROUTES = Object.freeze({
   mixed: {
-    'codex/gpt-5.6-sol': ['axstack-reviewer-secondary', 'claude/claude-opus-5', 'medium'],
-    'claude/claude-opus-5': ['axstack-reviewer-primary', 'codex/gpt-5.6-sol', 'medium'],
+    'codex/gpt-6-sol': ['axstack-reviewer-secondary', 'claude/claude-opus-5-5', 'medium'],
+    'claude/claude-opus-5-5': ['axstack-reviewer-primary', 'codex/gpt-6-sol', 'medium'],
   },
   'codex-only': {
-    'codex/gpt-5.6-sol': ['axstack-reviewer-secondary', 'codex/gpt-5.6-terra', 'xhigh'],
+    'codex/gpt-6-sol': ['axstack-reviewer-secondary', 'codex/gpt-6-luna', 'xhigh'],
   },
   'claude-only': {
-    'claude/claude-opus-5': ['axstack-reviewer-secondary', 'claude/claude-sonnet-5', 'xhigh'],
+    'claude/claude-opus-5-5': ['axstack-reviewer-secondary', 'claude/claude-sonnet-5', 'xhigh'],
   },
 });