axstack 0.34.4 → 0.36.0

package/skills/axstack-implement/SKILL.md

@@ -27,6 +27,7 @@ edge into the lifecycle (including its audit hook), then apply shared routing:
 - [Shared routing](../axstack/references/routing.md)
 - [PR-shape policy](../axstack/references/pr-shape.md)
 - [Candidate publication](../axstack/references/candidate-publication.md)
+- [PR chains](../axstack/references/pr-chain.md)
 
 Independently confirm the applicable
 [proportional scope identity](../axstack/references/routing.md#proportional-scope-identity):
@@ -73,13 +74,9 @@ never edits concurrently. Only an explicit accepted transfer changes ownership;
 ordinary resume reconciles the same sessions and record.
 
 Fanout follows dependencies and capacity within configured limits. Queue
-conflicts and dependent work; use `gh stack`, starting each child from its
-reviewed parent. When the reviewed parent changes, hold reliance on
-stale child evidence and child merge readiness; rebase onto the new parent revision,
-re-run affected checks, and remeasure shape against it.
-Size growth alone is not an automatic hold.
-A parent need not wait for an
-independently reviewed child. Dispatch only when ownership, worktree, dependency
+conflicts; PR chains owns reviewed-parent branching, immediate child evidence
+invalidation, lazy merge updates and legacy rebasing. A parent need not wait
+for an independently reviewed child. Dispatch only when ownership, worktree, dependency
 revisions, writer exclusivity, and capacity agree with live state. Shape, split,
 fanout, and exceptions are autonomous driver decisions within the approved scope.
 Size alone never requires user approval.
@@ -178,6 +175,7 @@ If a PR changes a mapped feature, its author updates the feature file in the sam
 For a missing skill, add "suggest `axstack-verify create`" to the receipt's `Unverified:` line.
 Never generate a verification skill automatically.
 For a broken or stale recipe, report the gap.
+Report a broken or stale recipe as a `low` finding naming `axstack-verify maintain`.
 Never let a broken or stale recipe waive existing acceptance obligations.
 Keep browser recipes tool-neutral for the verifier.
 
@@ -195,12 +193,12 @@ Simplification: <applied | not-applicable> — evidence: <diff locations and che
 Acceptance: <checks + observed results>
 Dependencies: <parent revisions or none>
 Unverified: <boundaries + reasons>
-Next: <owner reconciles receipt, uses gh stack to push exact revision, confirms
+Next: <owner reconciles receipt, uses candidate-publication to push exact revision, confirms
 remote readback, then routes it to axstack-review>
 ```
 
 The author stops at that receipt and does not push. The driver reconciles it,
-uses `gh stack` to publish, confirms remote readback, and continues the loop
+uses candidate-publication to publish, confirms remote readback, and continues the loop
 without editing the candidate. No step grants merge authority.
 
 Every own PR description must contain exactly one `Revert` line.
@@ -211,8 +209,8 @@ for its format and classification.
 
 Inputs are one snapshotted small-change intent or an approved spec and ticket
 map. The unit is that accepted task/PR map: run independent PRs in parallel
-within the fanout rule; run a dependent `gh stack` bottom-up, each child from
-its reviewed parent. The driver is owner, sole record writer, dispatcher,
+within the fanout rule; run an ordinary dependent PR chain root-first under PR chains, each child
+from its reviewed parent; preexisting native stacks retain their legacy path. The driver is owner, sole record writer, dispatcher,
 publisher, and wait-holder for every loop PR it creates. Resume preserves an
 existing live owner absent an accepted transfer.
 
@@ -246,8 +244,8 @@ For each PR:
    findings to the same author for a new revision, increments `repairs`, and
    returns to step 1. `INCOMPLETE`, a provenance gap, unavailable model, serious
    risk, or the third review round with `REQUEST_CHANGES` and/or diligence
-   `FINDINGS` on one PR records `held`. A changed parent sends its child back
-   to step 1.
+   `FINDINGS` on one PR records `held`. A changed parent immediately invalidates affected child readiness; refresh
+   the next ready children as needed under PR chains before step 1.
    Merge-ready also requires a current diligence `PASS` at that head; diligence
    `FINDINGS` return to the same author within the review round.
    Diligence `UNKNOWN` records the PR as `held` with the reason in the run record
@@ -265,53 +263,24 @@ its maintain-mode chat-run watch under [Autopilot](../axstack/references/autopil
 That watch owns the bound T3 schedule wake; its runtime sets the cadence.
 A turn with unsettled launched threads must end only under the bound-watch rule in the T3 runtime contract.
 With settled threads, end a turn only when every required PR is `merge-ready` or `held`.
-Under the recorded Notification policy, `axstack-relay` follows the categories
-below; serious risks relay immediately and genuine blocked operations needing
-user intervention relay after bounded safe recovery.
-Routine questions stay in the T3 driver thread. Progress, CI pending, and completion always stay
-in the T3 driver thread.
-Relay eligibility is limited to user-decision holds, serious-risk holds, the
-60-minute blocked ping, unresolved-rating notice and capped peer PR milestones
-under the Notification policy.
-Under the recorded Notification policy, `verification not proven` is a
-user-decision hold. The 60-minute blocked ping is a notification-only category
-under the Notification policy. The unresolved-rating notice is a notification-only
-category under the Notification policy, deduplicated per comment and head.
-The unresolved-rating notice grants no reply authority.
-The unresolved-rating notice never clears the hold.
-Never send routine merge-ready or merged relays
-for own PRs. Notifications for peer PRs are unchanged, including at most two
-merge-ready/merged milestones per run, deduplicated across implementation and release.
-
-Merge-ready opens the merge boundary.
-For own PRs, automatic merge is the default under the
-[watch predicate](../axstack-watch/SKILL.md#5-state-readiness-precisely).
+Follow [Watch notifications](../axstack-watch/SKILL.md#4-route-each-wake)
+under the recorded Notification policy, retaining its relay categories,
+deduplication and driver-thread fallback. Serious risks relay immediately.
+
+Merge-ready opens the merge boundary. Own PRs default to automatic merge under
+[watch §5](../axstack-watch/SKILL.md#5-state-readiness-precisely).
 The merge actor is the recorded owning watch thread (`axstack-owner` for
 standalone authorized maintenance), including small and adopted work.
-Missing or idle ownership follows lifecycle reconciliation and explicit transfer first.
 Apply `axstack-watch` §5's merge card and full predicate; an approval alone
-never grants merge authority.
-Personal own PRs, including `deploying` bases, follow automatic merge under
-watch §5. Work promotion PRs and `deploying` or unknown bases are merged by the
-user on the forge. Peer PRs are merged by the user on the forge.
-User merges are bottom-up for a stack.
+never grants merge authority. Re-read every predicate term under watch §5
+before merging; follow its guarded ordinary-root/singleton or legacy-native
+merge path and PR chains retarget/retirement proof.
+Personal own PRs, including `deploying` bases, follow automatic merge under watch §5.
+Work promotion PRs and `deploying` or unknown bases are merged by the user on the forge.
+Peer PRs are merged by the user on the forge. User merges are bottom-up for a stack.
 A manager, worker, reviewer, monitor, or nightly triage must never merge.
-Observation-only and peer watches never merge.
-Watch §5 owns provider provenance, approval carryover, eligible bases, every
-planned stack member's publication, proven verification, escalation, and card-reply exceptions.
 This policy grants no release, npm publish, or host install authority.
-Re-read every predicate term under watch §5 before merging. Confirm merge
-commits are allowed, `delete_branch_on_merge` is false, and the base has no
-merge queue; otherwise hold for the user. For a singleton, use
-`gh pr merge <n> --merge --match-head-commit <sha>` and add `--delete-branch`
-only when no open PR uses its branch as base. For a native `gh stack`, merge
-only the whole stack through `merge-async`: pass the top reviewed head as `sha`,
-`merge_method: merge`, and `merge_action: direct_merge`, then poll its UUID.
-Reconcile HTTP 200 or 409 against the intended request, verify every merged
-member's actual head equals its reviewed head and is an ancestor of the merge
-result, and hold unknown or failed outcomes; watch §5 owns the detailed rule.
-Never retarget, delete a stack branch, or rebase a reviewed stack member for
-merging. A failing push run on the target base after an automated merge holds
+A failing push run on the target base after an automated merge holds
 further automated merges run-wide. The driver resumes on the user's next
 message, `/axstack-watch`,
 or the armed chat-run watch wake; verify merge state through the forge on wake.

package/skills/axstack-improve/SKILL.md

@@ -16,9 +16,9 @@ improvement is a valid result.
 Before acting, load [Standing contracts](../axstack/references/contracts.md),
 then follow its lifecycle and audit pointers. Immediately before any useful
 role dispatch, load the [T3 runtime
-sequence](../axstack/references/t3-runtime.md). Use existing
-`axstack-explore-codebase` or `axstack-research-code` roles only when their
-specialization materially helps; create no new profile.
+sequence](../axstack/references/t3-runtime.md). For broad codebase mapping,
+use `axstack-scout`. Use `axstack-research-code` only when its specialization
+materially helps. Do not create a new profile.
 When dispatching `axstack-research-code`, dispatch `axstack-research-code-sol`
 independently on the same bounded brief without cross-reading. The driver
 reconciles findings per claim and never averages them. Record an intentionally

package/skills/axstack-research/SKILL.md

@@ -50,7 +50,8 @@ is part of research.
    - `axstack-research-web`: web and external sources.
    - `axstack-research-web-google`: Google-Search-grounded web sources via Gemini/Antigravity.
    - `axstack-research-x`: X (Twitter) posts and threads via Grok; cite post URLs and dates.
-   - `axstack-explore-codebase`: broad codebase mapping.
+   - For broad codebase mapping, use `axstack-scout`.
+     Never dispatch `axstack-explore-codebase` directly for broad mapping.
    - `axstack-explore-execution`: execution and runtime traces.
    - `axstack-explore-execution-sol`: independent Sol execution investigation.
 

package/skills/axstack-review/SKILL.md

@@ -28,7 +28,9 @@ Before reviewing, load [Standing contracts](../axstack/references/contracts.md),
 then [Lifecycle and receipts](../axstack/references/lifecycle.md) so its required
 audit edge remains active. Load [Shared routing](../axstack/references/routing.md)
 to select the mode and scope identity. For PR modes, apply the shared
-[PR-shape policy](../axstack/references/pr-shape.md). For an owned implementation candidate,
+[PR-shape policy](../axstack/references/pr-shape.md) and
+[PR chains](../axstack/references/pr-chain.md) for PR/head/base-branch/base-SHA
+evidence identity. For an owned implementation candidate,
 load and verify the
 [candidate-publication boundary](../axstack/references/candidate-publication.md).
 When the caller is a bounded review-manager PR job, load
@@ -328,6 +330,14 @@ This section applies to peer and authored PR modes.
    mode-required receipt records concrete evidence and consequences, coverage,
    limitations, and findings without a finding quota.
 
+   If a `verify-<app>` skill covers affected behavior, the authored reviewer runs its base-revision Launch and Doctor against the pinned final head in its detached checkout.
+   For an `axstack-verify create` PR, the reviewer drives the candidate's recipe because the base has none.
+   The author never performs this review drive.
+   The reviewer drives each affected feature and records that drive as the `Final-head check`.
+   Delegate browser drives to `axstack-ui-verifier` with the feature file path.
+   Running the applicable surface counts as spin-up; a CLI run qualifies.
+   Use loopback and isolated instances under [axstack-verify](../axstack-verify/SKILL.md#isolate-every-attempt).
+
    For each finding, name its defect class and list every instance of that
    class in the pinned diff and dependent surfaces: callers, sibling docs,
    README, and tests. A later instance of an already-named class is a coverage
@@ -391,6 +401,7 @@ Authored receipt requirements:
   Report Coverage: COMPLETE | INCOMPLETE with covered angles, acceptance and executable evidence.
   Tag each limitation leaving changed behavior unexercised or unverified, in whatever words, changed-behavior: unproven.
   Record Final-head check: <command> -> <log path> for a check the reviewer ran at the final head; keep the log in the run's evidence folder.
+  Applicable verify-<app>: Final-head check records the reviewer's local drive of each affected feature at the pinned final head. Use n/a — <reason> when no skill covers the affected behavior.
   Record a Safety fact: about the change itself rather than the review process.
   Rate each non-agent comment at the current head above low | low | addressed | uncertain.
   Re-rate each non-agent comment at every new head.
@@ -418,6 +429,7 @@ Verdict: <APPROVE | REQUEST_CHANGES | INCOMPLETE>
 Coverage: COMPLETE | INCOMPLETE — <angles + acceptance + executable evidence checked>
 Limitations: <unverified boundaries + why; tag each limitation leaving changed behavior unexercised or unverified, in whatever words, changed-behavior: unproven>
 Final-head check: <command> -> <log path> — <check the reviewer ran at the final head; log kept in the run's evidence folder>
+Applicable verify-<app>: <Final-head check records the reviewer's local drive of each affected feature at the pinned final head>. Use n/a — <reason> when no skill covers the affected behavior.
 Findings: <severity + evidence + consequence each>
 Revert: <declared line + diff-based assessment in authored mode>
 Agent-authored comment and thread IDs: <receipt-recorded IDs or none>

package/skills/axstack-scout/SKILL.md

@@ -0,0 +1,84 @@
+---
+name: axstack-scout
+description: When an agent needs codebase evidence across several areas or unfamiliar code, use axstack-scout to gather cited findings.
+---
+
+# Scout
+
+On driver entry, sweep under [Workspace hygiene](../axstack/references/workspace-hygiene.md); dispatched workers do not sweep.
+For every dispatch brief, name its private `<run dir>/evidence/<dispatch>/` folder.
+
+Before acting, load [Standing contracts](../axstack/references/contracts.md)
+and follow its lifecycle and audit pointers. Immediately before dispatch,
+read the [T3 runtime boundary](../axstack/references/t3-runtime.md) and
+[Role roster](../axstack/references/role-roster.md). A Scout call from an
+ordinary chat creates a run with `run-init`.
+
+## 1. Bound the exploration
+
+Use Scout for questions spanning several codebase areas, unfamiliar code, or
+claims that something does not exist. A single factual lookup stays in the
+current chat. Ordinary file reading also stays in the current chat.
+Only a driver or PR owner dispatches Scout. Workers, authors and reviewers
+request exploration from their driver; they do not launch a fan-out.
+
+Split the question into 1–3 facets, with each facet searching the whole
+repository for its concern, such as definitions, callers, tests or config.
+Facet briefs must never restrict the search to one directory. Scale by facet
+count; keep every required seat within each facet.
+
+## 2. Dispatch independent seats
+
+Use the run's selected preset and role snapshot. Give seats for one facet the
+same brief without cross-reading; the optional Flash seat searches the whole
+question for missed boundaries and counterexamples.
+
+- In mixed, each facet requires an independent Haiku and Luna pair: one
+  `axstack-explore-codebase` (Haiku 5.5 high) and one
+  `axstack-explore-codebase-luna` (Luna xhigh).
+- In codex-only, each facet requires an independent Sol and Luna pair:
+  `axstack-explore-codebase` (Sol high) and
+  `axstack-explore-codebase-luna` (Luna xhigh).
+- In claude-only, each facet requires one Haiku seat:
+  `axstack-explore-codebase` (Haiku 5.5 high).
+
+In mixed, dispatch one optional `axstack-explore-codebase-flash` for the Scout
+call, for at most seven seats across three facets.
+
+Sol and Luna agreement is not cross-family corroboration. An unavailable or
+rejected required seat holds Scout without substitution. The first dispatch
+for each provider/model/effort must reach a running or completed run before
+siblings launch, and its rejection stops siblings of that configuration.
+
+A Flash launch failure, trust/login prompt, or prompt block records
+`absent (<reason>)` and Scout continues with the required seats. Fence the
+failed attempt and name its absence once in the next read-back. A Flash model
+missing from saved capabilities holds that seat under the existing unavailable
+model rule, without substitution. A Flash hold covers only the Flash seat,
+and Scout returns the other seats' summary while naming that hold. An
+uncertain dispatch is reconciled, not recorded absent.
+
+## 3. Pin evidence and report
+
+Pin each brief to the working tree's content identity. Content identity pins
+HEAD SHA, SHA-256 of `git diff --binary HEAD` when dirty, and a path and
+SHA-256 for each untracked, non-ignored file from
+`git ls-files -o --exclude-standard`. Ignored files are outside the search
+scope. Seats search the pinned working tree. Each seat is read-only and
+writes only to its private evidence folder.
+
+Each seat report has at most about 15 claims, each labeled `verified`,
+`inference`, or `unverified` using Research labels. Every present claim
+cites `file:line` evidence. A not-found claim says `not found in <scope>`
+and includes the exact search command, scope, and content identity; it never
+claims absence beyond that scope.
+
+The driver reconciles per claim without averaging and names disagreements.
+Cross-family agreement corroborates but does not prove a claim. Before
+relying on an answer-changing not-found claim, the driver rechecks its search.
+Reuse findings only while content identity, including untracked file contents,
+is unchanged; any identity change requires re-scouting all facets still needed.
+
+Return a compact summary to the driver and store seat reports in the run's
+evidence folder. Scout adds no mandatory gate to other phases; they may use
+its evidence when useful.

package/skills/axstack-verify/SKILL.md

@@ -69,7 +69,8 @@ Keep that folder outside scratch selected for deletion.
 Clean up owned resources by literal absolute paths.
 Follow [Safe deletion](../axstack/references/workspace-hygiene.md#safe-deletion).
 
-For a peer PR, read the Launch recipe and helpers from the base revision and execute against the pinned candidate.
+For a peer PR or a review run, read the Launch recipe and helpers from the base revision and execute against the pinned candidate.
+For an `axstack-verify create` PR, the reviewer drives the candidate's recipe because the base has none.
 Keep trusted base helpers separate from the candidate's recipe files.
 Bind evidence to the served SHA.
 Report an unavailable candidate run as unverified.

package/skills/axstack-watch/SKILL.md

@@ -182,6 +182,9 @@ deploy to production.
 Re-read approval mode and base classification immediately before each automated
 merge and at every watch resume.
 
+Follow [PR chains](../axstack/references/pr-chain.md) for membership, dependencies,
+retargeting and retirement. Bind readiness to PR, head, base branch identity
+and base SHA, including an unchanged head after retargeting.
 For each current head and base SHA, every merge-ready term must hold:
 
 - Approval: in `solo` mode, authored-review `APPROVE` plus diligence `PASS`, both
@@ -200,7 +203,7 @@ For each current head and base SHA, every merge-ready term must hold:
   Reviews carrying an Axstack automation marker never count.
   A later `CHANGES_REQUESTED` blocks until resolved; a stale or dismissed
   approval does not count.
-  A collaborator approval carries over only across a rebase with unchanged
+  A collaborator approval carries over only across a rebase, base-update merge or base-only retarget with unchanged
   patch-id recorded for both heads while the forge still counts it.
   Require fresh authored review, diligence, and CI on every new head.
   Refresh authored review, diligence and CI evidence at the current head and base after every head or base change; base updates return to the same author under the existing repair route.
@@ -220,7 +223,7 @@ For each current head and base SHA, every merge-ready term must hold:
   unsettled author Dispatch, or task, PR, dependency, run-wide, or serious-risk
   hold affects this merge. Apply the comment holds below.
   The current target base head must be an ancestor of the singleton head or
-  bottom stack member head; unknown ancestry holds. A CI re-run does not restore
+  ordinary chain root head or legacy bottom stack member head; unknown ancestry holds. A CI re-run does not restore
   this freshness after the base moves. Update the branch and refresh head-bound
   evidence instead.
 - Proven verification: apply every receipt and acceptance term below, or its
@@ -249,8 +252,9 @@ Agents never resolve or dismiss non-agent items.
 Agent-authored threads with only `low` findings can stay open.
 Apply any repository rule that requires conversation resolution.
 
-Under authorized own-PR maintenance, keep repairing and rebasing onto the base
-when it moves, then re-run checks, until the head is rebased on the current base,
+Under authorized own-PR maintenance, keep repairing and merging the base
+when it moves for ordinary PRs (legacy native stacks retain rebasing), then
+re-run checks, until the head contains the current base,
 the comment holds above are cleared, the approval term holds, and required CI is
 green; only then record merge-ready.
 Never re-request a collaborator's review while its approval still counts under
@@ -274,6 +278,9 @@ Proven verification is required for every own PR. Use the authored receipt:
   Earlier-head red-to-green evidence in the PR's patch lineage counts only when
   the reviewer records that it still applies to the final change.
   An applicable `verify-<app>` passing result is required for the changed behavior.
+  The passing result must come from the reviewer's or `axstack-ui-verifier`'s local drive at that head.
+  The author's log alone never satisfies this requirement.
+  A preview URL never satisfies this requirement.
 - Verification requires no limitation tagged `changed-behavior: unproven`.
   The reviewer tags every limitation leaving changed behavior unexercised or
   unverified, in whatever words, `changed-behavior: unproven`.
@@ -318,12 +325,12 @@ Personal and work PRs remain eligible whatever files they change, including
 branch-protection or ruleset config, `CODEOWNERS`, `AGENTS.md`, and non-clean
 revert lines such as `Revert: steps`.
 
-For a `gh stack`, only the bottom member's base must be eligible.
+For a legacy native `gh stack`, only the bottom member's base must be eligible.
 Each other member's base must be the next-lower member's branch at its reviewed head.
 Every member must meet every other term.
-A stack holds until every member of its approved plan (the ticket map or the
+A legacy native stack holds until every member of its approved plan (the ticket map or the
 adopted stack's recorded members) is published.
-Reviewed members are never retargeted to become eligible.
+Reviewed legacy native-stack members are never retargeted to become eligible.
 
 Never auto-merge PRs authored by anyone other than the user or the user's agents.
 Test sources stay eligible.
@@ -386,9 +393,14 @@ Apply the existing [escalation threshold](../axstack/references/contracts.md#dri
 Confirm merge commits are allowed, `delete_branch_on_merge` is false, and the
 base has no merge queue; otherwise hold for the user. For a singleton PR, use
 `gh pr merge <n> --merge --match-head-commit <sha>`; add `--delete-branch` only
-when no open PR uses its branch as base. A failed head guard or uncertain merge
+when no open PR uses its branch as base and PR chains retirement proves no
+unpublished dependency, active author or unknown consumer. For an ordinary
+chain root use `gh pr merge <n> --merge --match-head-commit <sha>` without
+branch deletion until retirement is proven. After merge, verify actual head
+equals reviewed head and is an ancestor of the integration result before
+retargeting direct children under PR chains. A failed head guard or uncertain merge
 result holds for fresh reconciliation. If the target base moves after final
-readback, the singleton head guard or stack top `sha` decides whether the merge
+readback, the singleton/ordinary-root head guard or legacy stack top `sha` decides whether the merge
 proceeds; the push run on the merge result decides any further-merge hold.
 
 For a native `gh stack`, automate only a whole-stack merge: the top is the

package/skills/axstack-watch/references/repair-publication.md

@@ -1,67 +1,52 @@
 # Repair and publication
 
-Read this only for authorized maintenance of an adopted own PR. Observation-only
-and peer modes stop with a report before this branch.
-
-## 1. Confirm the repair boundary
-
-Re-read the accepted maintenance snapshot, writable ownership, publication
-authority, remote head and base, and current feedback. Route an accepted fix to
-the original author session only when the run itself launched that session and
-evidence permits. Record the repair author's actual provenance before
-selecting the reviewer, because the authored-review pairing follows the actual
-provenance of the repair, never the PR's historical author. A missing,
-stale, or materially changed boundary holds the repair while read-only
-monitoring continues.
-
-Record the exact defect, allowed files and actions, current revision, feedback
-IDs, and actual author without expanding scope.
-Follow [Feedback routing](../SKILL.md#feedback-routing) to launch an adopted
-repair author and pair its reviewer.
-
-## 2. Produce a reviewable candidate
-
-The author prepares the smallest in-scope repair and the exact public reply
-bodies, each keyed to its feedback ID and bound to the candidate revision.
-The candidate is committed locally in the owned worktree. Obtain an
-independent review of the exact local candidate SHA in an isolated detached
-checkout against the pinned base, including the exact reply bodies, before
-publication; nothing is pushed for review. Both code and
-reply bodies receive the one complete eligible non-author/non-owner review
-required by the authored review rule in `axstack-review`.
-
-Publication stays held until the current authored review receipt covers the
-exact new revision and base, all six angles, applicable acceptance, the reply
-body identities, and every affected boundary, with no unresolved material
-finding or urgent hold. A serious-risk escalation preserves the local candidate
-and exact context, records the hold in the run record and a durable GitHub or
-user-owned conversation, and sends only an authorized deduplicated notification.
-Publication remains held until the user decides at that durable location and
-all exact inputs are revalidated.
+For authorized maintenance of an adopted own PR only. Observation-only and peer
+modes stop at a report.
+
+## 1. Repair boundary
+
+Re-read accepted maintenance snapshot, writable ownership, publication authority,
+remote head/base and feedback. Missing, stale or materially changed boundaries
+hold repair; continue read-only monitoring. Return fixes to the original author
+only if this run launched it and evidence permits; otherwise follow
+[Feedback routing](../SKILL.md#feedback-routing) for a new adopted author.
+Record defect, allowed files/actions, revision, feedback IDs and actual repair
+provenance; pair review from that provenance, never historical authorship.
+
+## 2. Reviewable candidate
+
+The author commits the smallest in-scope repair and exact public reply bodies in
+the owned worktree, keyed to feedback IDs and candidate revision. Obtain
+independent review of the exact local candidate SHA and replies in an isolated
+detached checkout against the pinned base before publication.
+Nothing is pushed for review. Publication is held until the current authored review receipt covers
+the exact new revision and base, code/replies, all six angles, applicable acceptance,
+affected boundaries and exact reply identities with no unresolved material finding or urgent hold.
+The authored review rule in `axstack-review` requires exactly one complete
+eligible non-author/non-owner reviewer.
+Record a serious-risk hold in both the run record and a durable GitHub or user-owned
+conversation, preserving candidate/exact context;
+only an authorized deduplicated notification sends. Publication waits for the
+user's decision at that durable location and exact-input revalidation.
 
 ## 3. Revalidate immediately before publication
 
-Confirm fresh remote head and base, feedback freshness, reply body identity,
-and the exact revision covered by the mode-required review receipt. Before a history
-rewrite, confirm the expected-old SHA; a mismatch holds publication.
-
-All publication inputs must still match their reviewed values at the final
-readback.
+At final readback, confirm every input matches its reviewed value: fresh remote
+head/base, feedback, reply body identity and exact revision/base. Before a history
+rewrite, confirm expected-old SHA; a mismatch holds publication.
 
 ## 4. Publish idempotently
 
-After the local review and final remote revalidation, publish through `gh stack`
-for the adopted PR only, preserving unrelated stack entries.
-Bind the operation to the exact reviewed revision, then verify the submission
-receipt and remote state.
-
-If the send outcome is unknown, inspect remote IDs, bodies, and actor before any
-retry. Remain blocked while the outcome is ambiguous; retry only after
-confirming the intended operation is absent.
-
-Publication ends with a remote receipt proving that the reviewed revision and
-exact replies landed once, or a recorded hold naming the unmatched input and
-next owner.
-
-After verified publication of an own PR, the owner must follow
-[PR previews](../../axstack/references/preview.md) to decide on or restart its preview.
+After local review and remote revalidation, publish through
+[Candidate publication](../../axstack/references/candidate-publication.md)
+for the adopted PR only, preserving unrelated entries. Follow
+[PR chains](../../axstack/references/pr-chain.md) for scoped push and base-bound
+evidence; legacy native stacks use `gh stack`.
+Bind every publication operation to the exact reviewed revision, then verify the
+submission receipt and remote state.
+Unknown or ambiguous publication stays blocked; retry only after lookup of
+remote IDs, bodies and actor proves absence.
+Publication ends with either a receipt proving reviewed revision and exact replies
+landed once or a recorded hold naming unmatched input and next owner.
+After verified publication, follow
+[PR previews](../../axstack/references/preview.md) to decide on or restart a preview.

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

@@ -108,36 +108,21 @@ an uncertain wake. Wake only the exact live original driver.
 A busy, missing, protected (user-taken-over) or permission-held driver is never interrupted or replaced.
 
 The driver records one Notification policy for `axstack-relay` Telegram home.
-Relay eligibility is limited to user-decision holds, serious-risk holds, the
-60-minute blocked ping, unresolved-rating notice and capped peer PR milestones
-under the Notification policy.
-Under the recorded Notification policy, `verification not proven` is a
-user-decision hold. The 60-minute blocked ping is a notification-only category
-under the Notification policy. The unresolved-rating notice is a notification-only
-category under the Notification policy, deduplicated per comment and head.
-The unresolved-rating notice grants no reply authority.
-The unresolved-rating notice never clears the hold.
-Never send routine merge-ready or merged relays
-for own PRs. Notifications for peer PRs are unchanged, including at most two
-merge-ready/merged milestones per run, deduplicated across implementation and release.
-Quiet ticks never notify.
+Follow [Watch notifications](../SKILL.md#4-route-each-wake) for categories,
+deduplication and driver-thread fallback. Quiet ticks never notify.
 
 The driver alone routes repair.
-The driver routes rebases and review feedback to the PR's author for repair.
-For an adopted PR whose author this run did not launch, use a new author attempt under the
-[adoption rules](../SKILL.md#feedback-routing).
-The watch never writes candidate source.
-Re-read remote head/base and T3 ownership.
-Independent PRs may repair in parallel in separate T3 writer worktrees within
-measured host capacity. Two issues on the same PR use one author and one
-candidate; never create competing writers. A stack parent change invalidates
-child evidence and merge readiness; repair the lowest affected ancestor first,
-then rebase and revalidate children. Run-launched implementation PRs follow
-`axstack-implement`: driver publishes and reads back before independent authored
-review. Explicitly adopted own PRs follow [Repair and
-publication](repair-publication.md): independent exact-local-SHA review precedes
-driver-owned `gh stack` publication and remote readback. The driver never
-self-reviews.
+The driver routes base updates and review feedback to the PR's author for repair.
+For an adopted PR whose author this run did not launch, use a new author attempt
+under the
+[adoption rules](../SKILL.md#feedback-routing). The watch never writes candidate
+source. Re-read remote head/base and T3 ownership. Independent PRs may repair in
+parallel within capacity; two issues on the same PR use one author and candidate.
+Follow [PR chains](../../axstack/references/pr-chain.md) for invalidation and
+updates. Run-launched PRs follow `axstack-implement`: publication/readback before
+independent review. Adopted PRs follow [Repair and publication](repair-publication.md):
+independent exact-local-SHA review precedes scoped publication/readback.
+The driver never self-reviews.
 For own PRs, automatic merge is the default under the
 [watch predicate](../SKILL.md#5-state-readiness-precisely).
 Observation alone grants no repair or
@@ -146,8 +131,8 @@ public-reply authority.
 On new comments, failed checks, or base movement, repeat repair, the
 mode-specific publication and independent review steps above, current-head
 checks, and the full readiness decision for each member until every merge-ready
-predicate is satisfied or a concrete hold is recorded. Rebase the root PR against an advanced
-base, re-run checks, address actionable comments, and revalidate stacked descendants after
+predicate is satisfied or a concrete hold is recorded. Merge the advanced base
+into an ordinary root PR, re-run checks, address actionable comments, and revalidate affected descendants as needed after
 ancestor changes. Never assume historical approvals or threads have cleared;
 re-read all feedback and approvals at the current head before readiness.
 Re-reading approvals checks current state, not re-requesting review from a

package/src/capabilities.js

@@ -17,15 +17,13 @@ const CHECK_LABELS = {
   bun: 'bun >= 1.3.14 runtime',
   git: 'git CLI',
   gh: 'gh CLI',
-  'gh-stack': 'gh stack extension',
   't3-binary': `T3 Code CLI >= ${T3_FLOOR}`,
 };
 
-// Run the extension command itself, not a substring in an extension listing.
+// Ordinary PRs need Git and gh; legacy native-stack operations probe separately.
 export const PROBE_COMMANDS = {
   git: ['git', ['--version']],
   gh: ['gh', ['--version']],
-  'gh-stack': ['gh', ['stack', '--help']],
   't3-binary': ['t3', ['--version']],
 };
 
@@ -86,7 +84,7 @@ export async function runRealCheck(name) {
 }
 
 export async function checkCapabilities(exec) {
-  const names = ['bun', 'git', 'gh', 'gh-stack', 't3-binary'];
+  const names = ['bun', 'git', 'gh', 't3-binary'];
   const checks = [];
   for (const name of names) {
     let result;

package/src/roles.js

@@ -92,8 +92,8 @@ export function assessRoleReadiness(roles, preset) {
     (preset === 'mixed' && role.id === 'axstack-research-x' && role.provider === 'grok') ||
     (preset === 'mixed' && role.id === 'axstack-arena-candidate-grok' && role.provider === 'grok') ||
     (preset === 'mixed' && role.id === 'axstack-arena-candidate-antigravity' && role.provider === 'antigravity') ||
-    (preset === 'codex-only' && ['axstack-advisor-opus', 'axstack-escalation-fable', 'axstack-arena-judge-opus', 'axstack-research-web-google', 'axstack-research-x', 'axstack-arena-candidate-grok', 'axstack-arena-candidate-antigravity'].includes(role.id)) ||
-    (preset === 'claude-only' && ['axstack-advisor-astra', 'axstack-arena-judge-astra', 'axstack-research-web-google', 'axstack-research-x', 'axstack-arena-candidate-grok', 'axstack-arena-candidate-antigravity', 'axstack-auditor-sol', 'axstack-research-code-sol', 'axstack-explore-execution-sol'].includes(role.id))
+    (preset === 'codex-only' && ['axstack-advisor-opus', 'axstack-escalation-fable', 'axstack-arena-judge-opus', 'axstack-research-web-google', 'axstack-research-x', 'axstack-arena-candidate-grok', 'axstack-arena-candidate-antigravity', 'axstack-explore-codebase-flash'].includes(role.id)) ||
+    (preset === 'claude-only' && ['axstack-advisor-astra', 'axstack-arena-judge-astra', 'axstack-research-web-google', 'axstack-research-x', 'axstack-arena-candidate-grok', 'axstack-arena-candidate-antigravity', 'axstack-auditor-sol', 'axstack-research-code-sol', 'axstack-explore-execution-sol', 'axstack-explore-codebase-luna', 'axstack-explore-codebase-flash'].includes(role.id))
   );
   for (const role of roles) {
     if (!bounds.has(role.provider)) {