axstack 0.34.3 → 0.35.0

package/README.md

@@ -22,7 +22,7 @@ coordination. You can start at the phase you need.
 ## Prerequisites
 
 Axstack supports only Linux hosts. You need Bun >=1.3.14, Git, the GitHub
-CLI (`gh`) with `gh stack`, and T3 Code `0.0.46-nightly.20261003.2610` or newer
+CLI (`gh`), and T3 Code `0.0.46-nightly.20261003.2610` or newer
 on PATH. The providers selected by your preset must be available inside T3.
 
 Choose one explicit preset (each contains all role IDs): [mixed](profiles/presets/mixed.json)

package/bin/axstack.js

@@ -51,7 +51,7 @@ Usage:
 Commands:
   install    Validate a skill bundle, then copy owned skills and selected role
              data and record ownership hashes.
-  check      Probe Bun, Git, gh stack, and the T3 Code version floor.
+  check      Probe Bun, Git, gh, and the T3 Code version floor.
              Driver preflight verifies MCP readiness inside a T3 thread.
   uninstall  Remove only unchanged Axstack-owned assets. User edits survive.
 

package/docs/getting-started.md

@@ -1,12 +1,14 @@
 # Getting started
 
+Linux is the only supported host OS.
+
 Install Axstack, check your host, then ask for one bounded task in T3 Code.
 For the mental model, read [concepts](concepts.md); for other journeys, use
 [guides](guides.md).
 
 ## Prepare your host
 
-You need Bun >=1.3.14, Git, the GitHub CLI with its `gh stack` extension, and
+You need Bun >=1.3.14, Git, the GitHub CLI, and
 T3 Code `0.0.46-nightly.20261003.2610` or newer. These executables must be on PATH.
 The providers required by your chosen preset must be available inside T3.
 See [installation](installation.md) for harness paths and
@@ -24,21 +26,21 @@ axstack check --harness codex
 ```
 
 Installation writes owned skills and instructions, preserving unrelated content,
-and fetches the pinned archify tool for explicit viewer requests. Reload the harness's skills in T3 after
-installation. Use the [installation reference](installation.md) for other
+and fetches the pinned archify tool for explicit viewer requests. Reload the
+harness's skills in T3 after installation. Use the [installation reference](installation.md) for other
 harnesses, source installs or conflicts.
 
-A successful check exits 0. Its five capability rows mean:
+A successful check exits 0. Its four capability rows mean:
 
 | Row | Meaning |
 | --- | --- |
 | `bun` | The running Bun version meets the floor. |
 | `git` | Git's version command succeeds. |
 | `gh` | The GitHub CLI's version command succeeds. |
-| `gh stack` | The extension's actual help command succeeds. |
 | `t3` | T3's version command succeeds and meets the floor. |
 
-With this harness target, check also validates the archify record/copy/SHA and
+The `gh stack` extension is needed only for preexisting native stacks; ordinary
+PRs/chains use Git and `gh pr`. With this harness target, check also validates the archify record/copy/SHA and
 reports the owned instruction binding. Missing Chrome is a warning. Any reported
 gap exits 1; follow [troubleshooting](installation.md#exit-codes-and-troubleshooting) before
 starting a task.

package/docs/guides.md

@@ -12,7 +12,7 @@ Invoke `$axstack-spec Write the agreed specification.` to record observable
 acceptance, exclusions and a revision for your approval. After approval,
 `$axstack-tickets Map the approved work into tasks.` prepares the dependency map.
 `$axstack-implement Build the approved tasks.` carries it through authors,
-exact-revision review and repairs. The driver publishes through `gh stack`
+exact-revision review and repairs. The driver publishes through scoped Git push and `gh pr create/edit`
 and records each candidate and its evidence.
 
 ## Small fix

package/docs/host-operations.md

@@ -134,10 +134,9 @@ messages under the accepted fleet risk.
 
 ## Chat-run watch activation
 
-A bound T3 schedule resumes the driver thread on a 30-minute fallback while
-native PR watches are armed and work and release are settled.
-Unsettled work or release, unavailable or unarmed native watches for any open
-member, or failed re-arming restore five minutes. Human-only waits use 60 minutes
+A bound T3 schedule wakes the driver thread on a normal 30-minute cadence.
+Unavailable or unarmed native watches for any open member, failed re-arming,
+or a resumed question run restore five minutes. Human-only waits use 60 minutes
 under [Chat-run watch runtime](../skills/axstack-watch/references/watch-runtime.md#chat-run-watch).
 A T3 "stopped watching" notice triggers a PR re-check and native re-arm in that same turn.
 The run record holds the schedule ID and driver thread.

package/docs/installation.md

@@ -1,11 +1,13 @@
 # Installation
 
+Linux is the only supported host OS.
+
 Axstack's Bun CLI installs owned chat skills plus one selected role snapshot and
 checks host capabilities. T3 Code is the only supported active runtime. The CLI
 does not dispatch agents, edit T3 settings, run a scheduler, or maintain a
 workflow database.
 
-Requirements: Bun >=1.3.14, Git, `gh`, the `gh stack` extension, and a running
+Requirements: Bun >=1.3.14, Git, `gh`, and a running
 T3 Code `0.0.46-nightly.20261003.2610` or newer. The driver is a T3 thread
 with the `t3-code` MCP. See the [T3 runtime boundary](../skills/axstack/references/t3-runtime.md).
 Axstack has no runtime package dependencies. Filesystem access uses Bun-backed
@@ -121,14 +123,14 @@ role store and no T3 configuration merge.
 axstack check [--bundle <dir>] [--instructions <file>] [--skills-dir <dir>|--harness <name>]
 ```
 
-The capability report has five rows:
+The capability report has four rows; `gh stack` is required only for preexisting
+legacy native-stack operations, which probe `gh stack --help` separately:
 
 | Row | What it checks |
 | --- | --- |
 | `bun` | The `bun` row reports the already-validated running version, because Bun below 1.3.14 exits 1 before any row is printed. |
 | `git` | `git --version` succeeds. |
 | `gh` | `gh --version` succeeds. |
-| `gh stack` | `gh stack --help` succeeds, rather than merely finding an extension name. |
 | `t3` | `t3 --version` succeeds and its output meets the T3 version floor. |
 
 `--bundle` additionally validates the bundle and reports its skill-file count

package/docs/workflows.md

@@ -151,8 +151,7 @@ later installation changes without re-resolution.
 
 Peer roles use the stable IDs `axstack-reviewer-primary` and
 `axstack-reviewer-peer`; their provider/class mappings come only from the
-selected preset. The mixed cross-provider peer pair is Sol high followed by
-Opus medium. The mixed peer coordinator and review-lane binding
+selected preset and the ordered reviewer table above. The mixed peer coordinator and review-lane binding
 `axstack-owner` uses Sol high and never reviews. `axstack-reviewer-secondary`
 is used in the authored mapping and, alongside `axstack-reviewer-primary`,
 in codebase findings mode.
@@ -235,7 +234,7 @@ for explicit ownership transfer.
 - `axstack-implement` uses strict behavioral RED, GREEN, then refactor. The
   narrow accepted structure-preserving route uses old-green and the same check
   new-green. One author writes and returns a local receipt without pushing. The
-  owner reconciles it, publishes the unchanged commits through `gh stack`, and
+  owner reconciles it, publishes the unchanged commits through scoped Git push and `gh pr create/edit`, and
   confirms the remote SHA before review. Local green and CI green remain
   separate evidence. Authors apply the shared
   [test-value gate](../skills/axstack/references/test-value.md) to each new or
@@ -251,7 +250,7 @@ for explicit ownership transfer.
   authorized-maintenance scope. A changed head or comment is an event, not
   repair authority. Within an implementation run, fixes return to the original
   author and follow its publish-before-review loop. Manual adopted-PR repair
-  reviews the exact local SHA and reply bodies before `gh stack` publication
+  reviews the exact local SHA and reply bodies before scoped Git push and `gh pr create/edit` publication
   and remote readback.
 - `axstack-audit` separates execution outcome, procedure, and measurement
   coverage with evidenced denominators; it proposes but never self-edits.
@@ -394,7 +393,8 @@ that authored or repaired `merge-base..head` commits. Team approval also needs a
 counted non-author collaborator review at the current head. Axstack automation
 votes never count. Unknown or mixed provenance and manually authored PRs need a
 merge card. New heads need fresh authored review, diligence, and CI. A collaborator
-approval carries over only across an unchanged stable patch-id rebase, recorded
+approval carries over only across an unchanged stable patch-id rebase, base-update
+merge or base-only retarget, recorded
 for both heads, while the forge still counts it.
 
 Base classification uses repository docs and workflows, never the branch name
@@ -484,12 +484,35 @@ 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.
+
+New work uses ordinary PRs/chains under [PR chains](../skills/axstack/references/pr-chain.md).
+Record chain/native identity and direct dependencies; unknown or mixed routing
+holds affected operations. Children start from reviewed parents and merge
+parent/base updates without rewriting existing commits. Immediately invalidate
+affected child readiness, then refresh next ready children as needed, batching
+ancestor changes. A ready parent with independently deliverable approved scope
+can integrate before its children are published or ready. Only ready roots
+merge into integration targets; children never merge into open parent branches.
+
+Each root uses `gh pr merge <n> --merge --match-head-commit <sha>` under the full
+watch predicate, with merge commits enabled, no merge queue and auto-delete off.
+After confirmed parent merge, prove actual head equals reviewed head and is an
+ancestor of the integration result; reread direct child head/old base, change
+only base and read back unchanged head/new base. Unknown outcomes require lookup
+before retry; rewritten, squash/rebase or closed-unmerged parents hold dependents.
+The latest integration tip must enter child history before its merge. Retargeting
+or a base update requires fresh applicable review, diligence, shape, CI and
+approval evaluation bound to PR/head/base branch/base SHA. Branch retirement
+checks unpublished dependencies, active authors and complete open-PR inventory;
+unknown consumers hold deletion, not independent parent integration. Existing
+native stacks retain their full-stack, linear-history and no-retarget path.
+Singleton eligibility and user-only categories are unchanged.
 
 Never auto-merge PRs authored by anyone other than the user or the user's agents.
 Test sources stay eligible.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.34.3",
+  "version": "0.35.0",
   "description": "Axstack installer and setup CLI: installs owned chat skills and role data, configures supported harness settings, and checks T3 Code capabilities.",
   "keywords": [
     "claude-code",

package/skills/axstack/references/automations.md

@@ -210,10 +210,12 @@ through a broad `TMPDIR` glob, sweep a shared temporary root, or wipe a general
 cache. Preserve evidence and any temporary path with uncertain ownership or
 containment.
 
-An unchanged exact head and unchanged event identity creates no job; an
+An unchanged exact head, base branch identity, base SHA and event identity
+creates no job; an
 unchanged exact head with a new event identity remains actionable. Event
 identity includes the applicable review ID and body digest, request identity, or other current GitHub event
-receipt. Dedupe from current GitHub state,
+receipt. A base-only retarget or base update is a new evidence identity under
+[PR chains](pr-chain.md). Dedupe from current GitHub state,
 native T3 task and thread/run state, and the existing compact run record; do
 not create machine cursor files or a queue engine. Record enough to resume: PR,
 head, base, event identity, mode, owner and worker receipts, verdict,

package/skills/axstack/references/autopilot.md

@@ -89,7 +89,7 @@ Never require a manual `axstack-watch` invocation.
 The driver remains the single owner and sole run-record writer.
 Never create a per-PR session or an ownership hand-off.
 Read the [T3 runtime boundary](t3-runtime.md) and use its bound
-`schedule_task` wake (`everyMs:300000`), recording the scheduledTaskId.
+`schedule_task` wake (`everyMs:1800000`), recording the scheduledTaskId.
 Follow [Native PR links and watches](t3-runtime.md#native-pr-links-and-watches)
 alongside that bound schedule.
 Apply [Chat-run watch runtime](../../axstack-watch/references/watch-runtime.md#chat-run-watch)
@@ -97,7 +97,8 @@ cadence conditions before ending the turn.
 An explicitly adopted PR joins only with its maintenance snapshot.
 The original driver alone routes work; one author writes each
 candidate. Until a PR is merge-ready, wakes feed implement §6 step 4. After
-merge-ready, watch §5 maintenance repairs feedback, rebases when the base moves,
+merge-ready, watch §5 maintenance repairs feedback, updates the base under
+[PR chains](pr-chain.md),
 keeps CI green, and checks approvals without re-requesting human review.
 
 Maintain is the default mode for run-created PRs.
@@ -168,20 +169,9 @@ instructions, always win.
 
 Follow [Provider bindings](t3-runtime.md#preflight-and-binding) for driver account re-selection on start, resume and run-watch wakes.
 
-Use the run's recorded Notification policy through `axstack-relay`.
-Decision holds, including spec and npm approval, are always eligible.
-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.
+Follow [Watch notifications](../../axstack-watch/SKILL.md#4-route-each-wake)
+under the recorded Notification policy. Decision holds, including spec and npm
+approval, are always eligible.
 Across implementation and release, peer PR merge-ready and merged notifications
 together are capped at two per run; deduplicate by purpose and revision. Healthy ticks stay
 quiet. A failed or uncertain delivery preserves the underlying hold. A relay

package/skills/axstack/references/candidate-publication.md

@@ -1,25 +1,27 @@
 # Candidate publication
 
-This is the author-to-review boundary for an owned candidate. The author stops
-after returning its revision-bound implementation receipt and does not push.
-Within recorded PR-scoped publication authority, the owner reconciles that
-receipt against the actual local candidate SHA and base. The owner does not edit
-the author's candidate; required code changes return to the author.
+For an owned candidate, the author returns its revision-bound implementation
+receipt and stops without pushing. Under recorded PR-scoped publication authority,
+the owner reconciles author receipt with actual local candidate SHA/base. The owner
+does not edit the candidate; code changes return to its author.
 
 Before publication, dispatch `axstack-diligence` under
 [Diligence](diligence.md) to check the author receipt against its evidence
 folder: red/green logs exist, and counts, SHAs, and paths match. Resolve
 `FINDINGS` with the same author before publishing.
 
-Publish the existing commits through `gh stack`. Prefer a fast-forward push.
-Before a history rewrite, confirm the expected-old remote SHA and use lease
-protection; a mismatch holds publication. If the push outcome is ambiguous,
+Follow [PR chains](pr-chain.md) for recorded membership and base-bound evidence.
+For ordinary PRs, use `git push origin HEAD:refs/heads/<owned branch>` and
+`gh pr create` or `gh pr edit` with the actual parent or integration base.
+Never use routine force push for ordinary PRs. For legacy native `gh stack`,
+prefer a fast-forward push of existing commits, preserving unrelated entries.
+Before a history rewrite, confirm expected-old remote SHA and use a narrowly
+justified lease; a mismatch holds publication. If push outcome is ambiguous,
 inspect remote state before retrying.
 
-Before reviewer dispatch, read the remote ref back and confirm that it resolves
-to the candidate SHA; also pin the current base.
-Before reviewer dispatch, refresh the PR body counts and base from the confirmed
-candidate SHA and current base under [PR shape](pr-shape.md).
+Before reviewer dispatch, read the remote ref back, confirm its SHA equals candidate SHA, pin
+current base and refresh PR body counts and base from confirmed candidate SHA
+and that base under [PR shape](pr-shape.md).
 After every push, before post-push diligence or merge-ready, compare the PR body's
 stated head SHA with `Confirmed remote SHA` and record `PR body head SHA: <sha or none>`.
 Accept `none` for a PR body without a stated head SHA.
@@ -32,6 +34,7 @@ Record:
 
 ```text
 Candidate: <sha>
+Base branch: <branch>
 Base: <sha>
 Remote ref: <branch>
 Expected-old remote SHA: <sha | absent>
@@ -41,11 +44,8 @@ PR: <url>
 CI: <run ID or URL and triggered/pending/completed status>
 ```
 
-Local green is not CI green: immediately after publication CI is pending until
-its required checks complete. Review may run in parallel with CI only after the
-remote confirmation. Reviewers inspect a detached immutable checkout of the
-confirmed candidate SHA and pinned base, never only the movable branch name.
-Any author repair creates a new revision and repeats this boundary.
+Local green is not CI green: CI is pending after publication until required checks complete. Review may run alongside CI only after remote confirmation. Follow [Immutable checkout shape](#immutable-checkout-shape) for review.
+Author repairs create new revisions and repeat this boundary.
 After verified publication readback, follow
 [Native PR links and watches](t3-runtime.md#native-pr-links-and-watches).
 
@@ -67,18 +67,17 @@ step, subject to recorded release authority and human npm stage approval.
 ## Immutable checkout shape
 
 The driver creates the immutable review checkout with `git worktree add --detach <run>/checkouts/<key> <sha>` at the confirmed candidate SHA and pinned base.
-Follow [T3 runtime](t3-runtime.md) for async `delegate_task` and exact attempt
-identity. The checkout is disposable, made from the existing repository; never
-register a duplicate repository or replace it with a movable branch checkout.
+Follow [T3 runtime](t3-runtime.md) for async `delegate_task`.
+Bind disposable checkout to exact attempt identity.
+Use the existing repository; never register a duplicate or use a movable branch.
 Delegated reviewers must `cd` into their separate detached checkout; tracked candidate files remain read-only and outputs go to their private evidence folder.
-Snapshot driver HEAD and full status, including untracked entries, before dispatch.
+Snapshot driver HEAD and full status (including untracked) before dispatch.
 After each delegated completion, compare the driver HEAD and `git status --porcelain` with their pre-dispatch values; any change holds advancement.
-Each peer reviewer has a separate checkout and evidence folder with no first-pass
-cross-read. Later review gets a fresh checkout.
+Peer reviewers have separate checkouts/evidence without first-pass cross-read.
+Later review gets a fresh checkout.
 Before removing a reviewer checkout, read back its report and supporting evidence, then use exact `git worktree remove <run>/checkouts/<key>` without force.
-Verify Git worktree absence under [Workspace hygiene](workspace-hygiene.md);
-reviewer retirement preserves the separate author candidate until merge or closure.
-Release checks use the same driver-made SHA-pinned detached-checkout procedure.
+Verify absence under [Workspace hygiene](workspace-hygiene.md); retain the author
+candidate until merge/closure. Release checks use same driver-made SHA-pinned detached-checkout procedure.
 
 For a release PR, dispatch `axstack-diligence` under
 [Diligence](diligence.md) to check the release PR body

package/skills/axstack/references/contracts.md

@@ -125,12 +125,11 @@ remain a serious-risk hold.
 - One T3 host/server owns a run. No fixed active-PR count; fanout is dependency-
   and capacity-driven within host resource and spending limits. Reduce fanout for
   recorded rework, review backlog, or resource pressure. Queue conflicts and
-  dependencies; use `gh stack` for dependent PRs. Routine shape, split, fanout, and
+  dependencies; follow [PR chains](pr-chain.md). Routine shape, split, fanout, and
   exception choices within approved scope are autonomous driver decisions; size alone never
   requires user approval.
 - Exactly one writer per candidate; one persistent accountable PR owner. Each PR has one theme and measured size under [PR shape](pr-shape.md). Report unknown capacity
-  metrics; never a telemetry prerequisite or blocker. Parent changes invalidate
-  affected child evidence; refresh it against the new parent.
+  metrics; never a telemetry prerequisite or blocker. PR chains owns child evidence invalidation and refresh.
 - Own PRs default to automatic merge under [watch §5](../../axstack-watch/SKILL.md).
   Review approval and reviewer votes alone never grant mutation or merge authority.
   User merges are bottom-up for a stack.

package/skills/axstack/references/lifecycle.md

@@ -24,7 +24,7 @@ binding state and receipts to exact revisions.
 
 Prefer parallel independent bounded work; no redundant workers. Fanout is dependency- and
 capacity-driven within host/spending limits. [PR shape](pr-shape.md) covers
-theme/size; queue dependencies through `gh stack`.
+theme/size; queue dependencies under [PR chains](pr-chain.md).
 
 ## Ownership
 
@@ -70,7 +70,7 @@ Store receipt references, not raw output, in the [Run record](run-record.md).
   role; reuse on resume.
 - Acceptance receipt: sender/recipient, accepted scope/authority, timestamp,
   and ownership session receipt.
-- Review receipt: mode, provenance, reviewer, SHA/base,
+- Review receipt: mode, provenance, reviewer, PR/head/base branch/base SHA,
   verdict (`APPROVE | REQUEST_CHANGES | INCOMPLETE`), coverage, limitations and
   findings. Changed code needs a new receipt. Codebase: revision/scope,
   `COMPLETE | INCOMPLETE` coverage, no PR verdict.

package/skills/axstack/references/pr-chain.md

@@ -0,0 +1,51 @@
+# Ordinary PR chains
+
+Record ordinary-chain or legacy-native-stack identity and direct dependencies.
+Ordinary PRs/chains are default. Unknown/mixed identity holds
+affected operations. Use `gh stack` only for legacy-native-stack operations,
+probe `gh stack --help` first. Preserve publication, linear-history, full-stack
+merge, pinning and no-retarget rules under
+[watch §5](../../axstack-watch/SKILL.md#5-state-readiness-precisely).
+No automatic live unstacking. Singleton eligibility unchanged.
+
+Children start from reviewed parent. For ordinary chains, merge parent
+or base into owned child preserving existing commits. Immediately
+invalidate affected child readiness. Refresh next ready children and direct
+dependencies as needed, batching ancestor changes. Re-run affected checks and
+remeasure shape against new base; size growth alone is not an automatic hold.
+Legacy children retain reviewed-parent rebasing and revalidation.
+Ordinary chains/legacy stacks: repair lowest affected ancestor first,
+then refresh/revalidate children as needed.
+
+## Integration
+
+Only ready chain roots merge into integration targets. Never merge a child into
+an open parent branch. Ready parent can merge before child publication or
+readiness for independently deliverable approved scope. Apply watch §5, including
+personal/work eligibility and user-only categories. Latest integration tip
+must enter child history before merge.
+
+After confirmed parent merge, verify reviewed head equals actual head and
+is reachable from integration result. Mismatch: serious-risk hold.
+Direct children: reread old head and base, change only base, read back
+unchanged head and new base. Use `gh pr edit <child> --base <integration>` only
+after confirming old base is parent branch and recorded head matches.
+Retarget direct children only; prove forge auto-retargeting likewise.
+Unknown retarget outcome: lookup before retry. Closed without merge,
+rewritten parents, external squash or rebase, and missing ancestry hold dependents.
+
+Bind evidence to PR, head, base branch identity and base SHA. Base-only retarget
+or base update needs fresh applicable review, diligence, shape, CI and
+approval evaluation. Check new-base workflow coverage at unchanged heads;
+never reuse old-base receipts. Carryover compares stable patch-id at both recorded
+head/base
+identities and requires a forge-counted human approval under watch §5. Never
+automatically request human rereview.
+
+## Retirement
+
+Branch retirement checks published and unpublished dependencies, active authors
+and complete open-PR inventory. Unknown consumers hold deletion, never safe
+independent parent integration. Resolve/read back all consumers before deletion.
+Keep auto-delete off; omit
+merge-time deletion for present/uncertain consumers.

package/skills/axstack/references/run-record.md

@@ -136,7 +136,8 @@ Record the reason for each driver-elected repair in `Decisions`.
 
 Record concise IDs, SHAs, URLs, status, timestamps, next actions, and evidence
 references. Private records include the checkout, evidence and worktree paths
-that the schema requires. Include no tokens, transcripts, full worker output,
+that the schema requires. Include no other machine-specific paths in private records.
+Include no tokens, transcripts, full worker output,
 credentials or private prompts. Publication of a sanitized summary needs separate
 authority.
 
@@ -182,6 +183,7 @@ Deploying bases: <base -> integration | deploying; docs/workflow evidence>
 PR digest watermarks: <repo -> absolute path of its per-repository JSON file inside the private run directory> | none
 Release: <AGENTS.md file:line + tag-triggered workflow path + named install hosts> | not applicable (<reason>)
 Source base: <exact revision or source identity>
+PR membership: <PR -> ordinary-chain | legacy-native-stack; direct dependencies incl unpublished; active authors; head/base branch/base SHA>
 IDs: <projectId + driver threadId/runId + dispatch identity receipt pointers>
 Runtime: <host + T3 version + installed Axstack SHA + installed Axstack version/check time + last reference read time + capabilities JSON path>
 Schedules: <scheduledTaskIds of every watch and manager schedule>

package/skills/axstack/references/t3-runtime.md

@@ -238,15 +238,24 @@ the failed attempt's branch is kept until salvage. Unknown liveness holds
 replacement; reconcile the old writer before admitting another.
 
 With an unsettled launched thread, the driver turn must end only while a bound
-`schedule_task` with `bindToCurrentThread:true`, `everyMs:300000` is armed and
-its ID recorded. Each wake must reconcile all unsettled runs, including a
+`schedule_task` with `bindToCurrentThread:true` is armed at the default
+`everyMs:1800000` or for its 5-minute recovery cases in
+[Chat-run watch runtime](../../axstack-watch/references/watch-runtime.md#chat-run-watch),
+with its ID recorded. Each wake must reconcile all unsettled runs, including a
 writer that died without sending; failed runs hold incomplete work. The watch
 inherits the driver model/workspace and adds no runtime of Axstack's own.
 T3 queues a scheduled wake even while the driver is busy, so copies pile up.
-At the start of each run-watch wake, the driver must cancel every other queued
-copy of its own run-watch prompt with `t3_queue_list` and `t3_queue_cancel`,
-keeping every other queued message, including user and worker messages.
+After a provider error, server restart or Stop, T3 holds the queue: held
+messages do not start, and later queued messages are held too.
+At the start of each run-watch wake, the driver lists every queued message with
+`t3_queue_list` and treats it as stranded.
+The driver must cancel every queued copy of its own run-watch prompt.
 One wake reconciles all those copies.
+For each stranded worker receipt or PR-watch update, the driver must read it
+with `t3_queue_read`, act on it in that wake, then cancel it with `t3_queue_cancel`.
+A queued user message is a pending local action, so the driver must keep every
+queued user message and report it in its reply even on an otherwise unchanged
+wake, because only the user resumes a held queue.
 
 Once nothing remains unsettled the driver must `delete_scheduled_task` for the
 run watch and use `list_scheduled_tasks` to read back its absence; an uncertain
@@ -255,12 +264,12 @@ delete preserves the hold and recorded ID.
 ## Native PR links and watches
 
 After verified publication readback or adoption of an own PR, the driver calls
-`link_pull_request` with the full PR URL for every layer of a `gh stack`.
+`link_pull_request` with the full PR URL for every layer of an ordinary-chain or legacy `gh stack`.
 Before finishing PR work, including watch end or Close-out, the driver calls
 `list_thread_pull_requests` and links every missing run PR.
 Never link unrelated PRs.
 
-After verified publication readback of an own PR, for every layer of a `gh stack`,
+After verified publication readback of an own PR, for every layer of an ordinary-chain or legacy `gh stack`,
 the driver also calls `t3_thread_update` with `action: link_pull_request`,
 `pullRequest` containing its number, repository and full PR URL, and `threadId`
 set to the author thread, then reads back the PR link with
@@ -291,10 +300,10 @@ If re-arming fails, restore the bound 5-minute schedule.
 When the run waits only on a user decision or a human-only step, including a
 user merge, with no unsettled worker and no PR needing watch events, change
 the run watch cadence to 60 minutes at once.
-When work restarts, restore the normal 5-minute cadence.
+When work restarts, restore the normal 30-minute cadence.
 Keep native PR watches.
 For chat-run cadence changes, follow [Chat-run watch runtime](../../axstack-watch/references/watch-runtime.md#chat-run-watch)
-for 30-minute fallback eligibility, 5-minute recovery, and schedule update read-back.
+for the normal 30-minute cadence, 5-minute recovery, and schedule update read-back.
 The schedule still reconciles author and review tasks, readiness, and release.
 When a PR merges or closes, or its watch is torn down, call `unwatch_pull_request`
 and keep its link.

package/skills/axstack/references/test-audit-weekly.md

@@ -57,7 +57,7 @@ The weekly test audit is a named exception to Implement's publish-then-review
 order: it requires review-before-publication.
 Obtain independent review using Implement's configured authored-review roles and
 verify the exact candidate's checks before publication. The driver uses
-`gh stack` and opens at most one test-audit PR per week after independent review;
+[Candidate publication](candidate-publication.md) and opens at most one test-audit PR per week after independent review;
 for own PRs, automatic merge is the default under the
 [watch predicate](../../axstack-watch/SKILL.md#5-state-readiness-precisely).
 

package/skills/axstack/references/ui-verification.md

@@ -1,6 +1,6 @@
 # UI verification
 
-Every Playwright, browser, or rendered-UI check outside the three named author
+Every Playwright, browser, or rendered-UI check outside the three named browser
 exceptions, including a "confirm it in the browser" step, goes through async
 `delegate_task` to `axstack-ui-verifier` from the run's role snapshot. Give it the exact build, URL, or artifact and the private
 dispatch's evidence folder. The verifier is read-only: it never edits source.
@@ -8,21 +8,16 @@ The PR writer remains the sole writer.
 
 Before using a PR preview URL, the UI verifier must read [PR previews](preview.md).
 
-The first named author browser exception is archify `finalize` as a headless build gate.
+The first named browser exception is archify `finalize` as a headless build gate.
 Keep finalize outputs only in the private evidence folder.
 Never replace the verifier's rendered pass with finalize.
 
-The second named author browser exception is the driver's two `html_preview`
+The second named browser exception is the driver's two `html_preview`
 runs at 728px dark and 360px light.
-Scan the exact bytes of every page for remote src, srcset, and href on loaded
-resources, `@import`, `url()`, `fetch`, XHR, WebSocket, EventSource, and meta refresh.
-Reject scan matches except local url(#id) references such as SVG markers and gradients.
-Require correct layout, theme, zero console errors, empty `missingImages`,
-height, network, and word count.
 Never replace the verifier's interaction pass with `html_preview`.
 Follow [Inline pages](../../axstack-explain/references/inline-pages.md) for the page checks.
 
-The third named author browser exception permits dispatched roles to use
+The third named browser exception permits dispatched roles to use
 `html_preview` as a non-publishing self-check.
 Dispatched-role self-checks never replace the driver's two previews or the `axstack-ui-verifier` pass.
 Dispatched roles never call `html_render`.
@@ -36,8 +31,8 @@ Candidate browser and visual checks must run in the delegated `axstack-ui-verifi
 For every interactive page, require a real-browser `axstack-ui-verifier` interaction pass.
 Give the evidence path and SHA-256 of the exact bytes in the verifier brief.
 The verifier serves the exact bytes on loopback.
-Open the page with `preview_open` using `open:false`.
-Check clicks, keyboard, focus order, screen-reader names, expanded states, and reduced motion.
+The verifier opens the page with `preview_open` using `open:false`.
+The verifier checks clicks, keyboard, focus order, screen-reader names, expanded states, and reduced motion.
 Require that `performance.getEntriesByType('resource')` is empty.
 The detached-checkout rule does not apply to a page without a candidate.
 
@@ -57,7 +52,8 @@ Keep browser recipes tool-neutral for the verifier.
 
 ## Proof standards
 
-Apply these standards to the verifier's candidate checks and inline-page interaction pass.
+Apply these standards wherever referenced, including the verifier's candidate checks
+and inline-page interaction pass.
 
 Drive the real user path.
 Capture the action, the resulting state and its side effects.

package/skills/axstack-diagram/SKILL.md

@@ -13,7 +13,7 @@ Use archify HTML only on an explicit viewer request.
 The configured `axstack-explainer` authors the viewer; follow [Archify](references/archify.md).
 Use inline SVG or CSS inside inline pages.
 Never use Mermaid in inline pages.
-Use Mermaid for chat fallback, GitHub, and docs.
+Use Mermaid for chat, GitHub, and docs.
 Include `accTitle` and `accDescr` in each Mermaid view.
 Never use theme init in Mermaid.
 Split large Mermaid diagrams into views.
@@ -23,5 +23,6 @@ Explain owns evidence, claim labels, the word cap, dispatch, and delivery.
 Diagram owns format and visual rules.
 Never call explain.
 For direct use, keep fidelity and rendered QA.
+For direct viewer requests, follow [Explain's declared launch path](../axstack-explain/SKILL.md#2-choose-proportional-output).
 
 Ideas: [archify](https://github.com/tt-a1i/archify), [diagram-design](https://github.com/cathrynlavery/diagram-design), [visual-explainer](https://github.com/nicobailon/visual-explainer), [Matt Pocock](https://github.com/mattpocock/skills), and [poteto](https://github.com/poteto/how); guidance uses Axstack's own words.

package/skills/axstack-explain/SKILL.md

@@ -71,11 +71,11 @@ Diagram never calls explain.
    Each card has at most 40 words and cites its source, as defined in
    [Archify](../axstack-diagram/references/archify.md).
    Count node labels, headings, captions, and all non-card text.
-2. Use chat only for an explicit chat request, an answer without a Q2 trigger,
-   or inline-page fallback. Q2 triggers are the conditions in the description.
+2. Use chat only for an explicit chat request, an answer outside the description's conditions,
+   or inline-page fallback.
    Use a compact diagram when useful.
    For chat answers, never dispatch an agent when applying its Mermaid rules inline.
-3. For a Q2 trigger, create an inline page by default.
+3. For the conditions in the description, create an inline page by default.
    Honor an explicitly requested artifact format.
    Use archify only on an explicit viewer request, through the configured
    `axstack-explainer`. The reply adds only what the page omits.

package/skills/axstack-explain/references/inline-pages.md

@@ -48,7 +48,7 @@ Scan for `@import`, `url()`, `fetch`, XHR, WebSocket, EventSource, and meta refr
 Reject scan matches except local `url(#id)` references such as SVG markers and gradients.
 
 Before publishing, run `html_preview` at 728px dark and 360px light.
-The driver's two previews are an author exception to delegated browser checks.
+The driver's two previews are a named browser exception to delegated browser checks.
 Require correct layout, theme, height, network, word count, zero console errors,
 and empty `missingImages`.
 Check every claim against its source.
@@ -59,8 +59,6 @@ For every interactive page, require a real-browser `axstack-ui-verifier` pass
 for clicks, keyboard, and expanded states.
 Give the evidence path and SHA-256 of the exact bytes in the verifier brief.
 Follow [UI verification](../../axstack/references/ui-verification.md) for that pass.
-The pass covers focus order, screen-reader names, reduced motion, and an empty
-`performance.getEntriesByType('resource')` list.
 
 ## Publish or fall back
 

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.
@@ -195,12 +192,12 @@ 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 +208,8 @@ 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 +243,8 @@ 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 +262,24 @@ 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-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

package/skills/axstack-watch/SKILL.md

@@ -78,7 +78,7 @@ load. When the watch needs a new owner or automated observation, first read
 [T3 runtime](../axstack/references/t3-runtime.md). Reconcile before creating
 anything. Task-owned observations use their recorded wakes and expiry.
 `axstack-monitor` stays an optional read-only observer for standalone watch
-that never sends. For own open PRs in chat-run mode, use the 30-minute fallback when eligible under
+that never sends. For own open PRs in chat-run mode, use the normal 30-minute cadence under
 [Chat-run watch runtime](references/watch-runtime.md#chat-run-watch);
 the bound T3 schedule resumes the original driver thread. One read-only PR observation needs
 neither. Start no automation for a read-only check.
@@ -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
@@ -318,12 +322,12 @@ 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 +390,14 @@ 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

@@ -34,7 +34,7 @@ after verified readback, subject to the user's explicit publication boundary.
 
 The initiating T3 thread remains the sole driver and `progress.md` writer.
 Initially use the bound run watch from [T3 runtime](../../axstack/references/t3-runtime.md):
-`schedule_task` with `bindToCurrentThread:true`, `everyMs:300000`, a stable
+`schedule_task` with `bindToCurrentThread:true`, `everyMs:1800000`, a stable
 `clientRequestId`, and the authorized watch prompt. Record the schedule ID,
 driver thread, chosen mechanism and native schedule lifetime; the watch inherits the driver binding at creation.
 Follow [Provider bindings](../../axstack/references/t3-runtime.md#preflight-and-binding) before arming the watch and for schedule recreation on self-switch.
@@ -45,20 +45,17 @@ Use `update_scheduled_task` on the recorded schedule ID for cadence changes and
 When the run waits only on a user decision or a human-only step, including a
 user merge, with no unsettled worker and no PR needing watch events, change
 the run watch cadence to 60 minutes at once.
-When work restarts, restore the normal 5-minute cadence.
+When work restarts, restore the normal 30-minute cadence.
 Keep native PR watches.
-Only while every open watched PR has an armed native `watch_pull_request`, all
-launched work is settled, and the release step is settled or inapplicable, use
-the bound chat-run schedule as a 30-minute fallback (`everyMs:1800000`).
-Because delegated tasks deliver native completion wakes, unsettled delegated
-tasks alone keep the 30-minute fallback eligible.
+Because launched writers, delegated tasks and native PR watches deliver their
+own wakes, use the normal 30-minute cadence (`everyMs:1800000`) even while
+launched work or the release step is unsettled.
 A resumed `AXSTACK-QUESTION` child run lacks a native completion wake, so it
 keeps the 5-minute cadence (`everyMs:300000`) until its result is accepted.
 If native `watch_pull_request` is unavailable or unarmed for any open member,
 or re-arming fails, restore the bound chat-run schedule to 5 minutes (`everyMs:300000`).
 On the next event on a watched PR, re-evaluate the wake cadence against the
 fallback conditions in the same turn.
-If launched work or the release step becomes unsettled, restore the 5-minute cadence (`everyMs:300000`).
 Apply these conditions before ending each driver turn, including after initial
 arming or a work restart; the 60-minute human-only wait rule above still applies.
 Read back each schedule update and record its receipt; an uncertain update holds affected work.
@@ -111,36 +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
@@ -149,8 +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;