axstack 0.25.1 → 0.25.3

package/docs/workflows.md

@@ -265,9 +265,13 @@ one theme and a measured size under the shared
 For own PRs, automatic merge is the default under the
 [watch predicate](../skills/axstack-watch/SKILL.md#5-state-readiness-precisely).
 Review approval alone never grants merge authority.
-For the rationale band, the autonomous driver records a cohesion rationale. The exception band
-requires a reasonable split attempt and full exception record. These are
-autonomous driver choices; size alone never requires user approval.
+Treat size flags as informational only.
+Size alone must never block review, reject a PR, require split attempts or
+cohesion/exception rationale, or hold approval.
+Review the actual footprint, complexity, and required context, incrementally when needed.
+Approval requires sufficient review coverage.
+Report INCOMPLETE when required coverage is missing.
+Shape choices remain autonomous driver decisions; size alone never requires user approval.
 
 ## Explicit handoff
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.25.1",
+  "version": "0.25.3",
   "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/autopilot.md

@@ -67,6 +67,8 @@ 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:600000`), recording the scheduledTaskId.
+Follow [Native PR links and watches](t3-runtime.md#native-pr-links-and-watches)
+alongside that bound schedule.
 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

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

@@ -44,6 +44,8 @@ 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.
+After verified publication readback, follow
+[Native PR links and watches](t3-runtime.md#native-pr-links-and-watches).
 
 ## Revert line
 

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

@@ -12,16 +12,15 @@ Total additions + deletions over all files. Disclose moves detected by `-M`;
 report binaries by count and purpose, never estimated lines. Disclose generated,
 lockfile, and formatter-only bulk buckets alongside the total.
 
-The full total controls the level: ≤2000 is the target. The 2001–2500 rationale
-band requires only a recorded cohesion rationale, with no split-attempt record.
-The >2500 exception band requires the full exception record below. Bulk may
-support either rationale only with a reproducible recorded command. Never
-automatically subtract bulk or shift bands; silent exclusion is forbidden; no file-count hard metric.
+Flag totals above 2500 changed lines as informational only.
+Never automatically subtract bulk from the full total; silent exclusion is forbidden; no file-count hard metric.
+Disclose each bulk bucket with a reproducible recorded command.
+There is no universal safe LOC limit or fixed token percentage.
 
 ## Theme
 One behavior or component may include the callers, tests, types, docs, and
 migrations that must change together to stay green and reviewable.
-This is not a folder restriction. Unrelated themes split even under the target.
+This is not a folder restriction. Unrelated themes split regardless of size.
 Smaller cohesive PRs are encouraged; no padding.
 
 ## PR body
@@ -29,16 +28,13 @@ Smaller cohesive PRs are encouraged; no padding.
 Every own PR description must contain exactly one `Revert` line.
 Follow [Revert line](candidate-publication.md#revert-line) for its format and classification.
 
-## Exception band
-The driver attempts a reasonable split first. If each tried split materially
-compromises atomicity, green state, or independent reviewability, or inseparable
-reproducible bulk dominates, record and proceed autonomously within the approved
-spec. The mandatory record includes the full total, bulk buckets with their
-reproducible command, measured head and base, split attempts tried, and why each
-fails on atomicity, green state, or reviewability. “Already written,” deadlines,
-and rebase pain are not reasons.
-Size alone never requires user approval. Review verifies the measurement and
-whether the stated split failure is real under angle 6, not the number itself.
-Missing rationale blocks approval; weak rationale returns to the author through
-the normal split/rework loop, never to the user. Escalate only for an existing
-material-scope, security, downtime, data-loss, major-design-risk, or unavailable-model hold.
+## Review and decisions
+Size alone must never block review, reject a PR, require split attempts or
+cohesion/exception rationale, or hold approval.
+Review the actual footprint, complexity, and required context, incrementally when needed.
+Approval requires sufficient review coverage.
+Report INCOMPLETE when required coverage is missing.
+Routine shape decisions remain autonomous driver decisions within approved scope;
+size alone never requires user approval.
+Escalate only for an existing material-scope, security, downtime, data-loss,
+major-design-risk, or unavailable-model hold.

package/skills/axstack/references/routing.md

@@ -85,7 +85,14 @@ step (3) for user routing: no substitution or same-provider review.
 - Codebase review -> `axstack-review` codebase mode, report only.
 - A status question about an own open PR or stack ("check now", "what's left",
   "are we done", or "is it approved") -> `axstack-watch` observation-only
-  mode. Explicit "address", "patch", or "fix" grants authorized maintenance.
+  mode when it does not ask to watch.
+- A user request to watch, babysit, keep watching, maintain, address, patch, or fix
+  own PRs authored by the authenticated `gh api user` login or the user's agents
+  grants authorized maintenance by default.
+  Snapshot the maintenance intent once without extra approval.
+  Observation-only applies only to explicit observe-only requests, status
+  questions without a watch request, or peers' PRs.
+  Explicit observe-only includes "monitor only" or "do not change anything".
 - Chat-run PR watch -> `axstack-watch`: original driver; verified run PRs and
   explicit adoptions only.
 - Other own PR work -> `axstack-review` authored mode or `axstack-watch`

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

@@ -9,7 +9,8 @@ delegated tasks, messaging and native schedules.
 The driver must be a T3 thread, save `orchestrator_capabilities` JSON under
 the run record, and follow the advertised tool schema; discovery alone proves
 neither provider readiness nor successful execution. Missing capability holds
-the affected operation, without a substitute runtime.
+the affected operation, without a substitute runtime. Native PR watch absence
+uses the schedule fallback below.
 
 From installed `skills/axstack/roles.json`, the driver must snapshot the selected
 preset and stable role IDs, requested provider/model/class/mode/effort, resolved
@@ -224,6 +225,31 @@ 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
 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`.
+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.
+
+For every watched own PR in chat-run or standalone adopted maintenance, when
+available the driver calls `watch_pull_request` for T3 wakes on check completion,
+new comments from others, or branch conflicts, then ends the turn.
+Never poll or keep a model active between native PR wake events.
+When T3 reports it stopped watching a PR, the next wake re-checks the PR and
+calls `watch_pull_request` again.
+This includes a stop after T3 could not read the PR for 15 minutes.
+Route native PR wake events through watch §4 and the unchanged §5 readiness predicate.
+
+If `watch_pull_request` is unavailable, fall back to the bound 10-minute schedule
+and `scripts/pr-digest.js` without a hold.
+Keep the schedule cadence unchanged while a native PR watch is active,
+including the existing 7-day quiet relaxation.
+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.
+
 ## Evidence, prompts and authority
 
 Put the [Safe-deletion rule](workspace-hygiene.md#safe-deletion) in every worker brief.

package/skills/axstack-audit/SKILL.md

@@ -117,10 +117,10 @@ counts with denominators plus the evidence behind the count:
 - Rework cycles with causes.
 - Avoidable user interventions where records support the call, and no call where they do not.
 - Parallelizable tasks identified versus dispatched, judged with dependency and writer isolation.
-- PRs within band / total PRs using the actual denominator. Apply the level
-  matching the measured total. For the rationale band, record cohesion
-  rationale presence; for the exception band, record the full driver exception
-  record. Record `UNKNOWN` when a receipt lacks the measurement.
+- PRs with an informational size flag / total PRs using the actual denominator.
+  Record full totals, bulk buckets with reproducible commands, and measured head/base.
+  Treat size flags as informational only.
+  Record `UNKNOWN` when a receipt lacks the measurement.
   This is evidence, not a score to game. Audit treats routine shape choices as
   autonomous driver decisions; size alone never requires user approval.
 - API-dollar cost by model when provider receipts are available, UNKNOWN otherwise.

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

@@ -17,7 +17,7 @@ Review: <exact-rev independent review status + unresolved findings>
 Rework: <cycles + causes>
 Interventions: <avoidable user interventions, or unsupported by records>
 Parallelism: <identified vs dispatched + dependency/writer isolation>
-Shape: <PRs within band / total PRs + rationale-band cohesion rationale + exception-band full driver exception record; missing measurement: UNKNOWN>
+Shape: <PRs with an informational size flag / total PRs; full totals + bulk buckets with reproducible commands + measured head/base; UNKNOWN when measurement is missing>
 Cost: <API dollars by model when measured, or UNKNOWN with reason>
 Judgment: <execution outcome vs procedural adherence vs measurement coverage>
 Proposals: <bounded hypothesized changes with regression-first plan, or none>
@@ -25,6 +25,8 @@ Learning candidates: <each candidate's statement + scope + evidence/revision poi
 Privacy: <local/private default; sanitized summary only when authorized>
 ```
 
+Treat size flags as informational only.
+
 The record is complete when its counts reconcile, its judgments remain
 separate, every proposal has a regression-first validation path, every learning
 candidate is bounded to accepted audited evidence, and all unknowns and

package/skills/axstack-review/SKILL.md

@@ -293,17 +293,15 @@ This section applies to peer and authored PR modes.
    Rate a wrong or missing `Revert` line at least `medium` under [Finding severity](#finding-severity).
 
    Under angle 6, verify the recorded shape against the pinned head and base.
-   A mismatch between the recorded and measured total is a finding. Apply the
-   level matching the measured total. The rationale band requires only its
-   recorded cohesion rationale, not a split-attempt record. For the exception
-   band, verify the full exception record: total, bulk buckets with their
-   reproducible command, measured head/base, split attempts tried, and why each
-   fails on atomicity, green state, or reviewability. Missing rationale is a
-   validated angle 6 finding that blocks approval like any other. Reviewer
-   judgment is bounded to verifying the measurement and whether the stated split
-   failure is real, not the number itself. A weak rationale returns to the
-   author as a split or rework request through the normal fix loop, never to the
-   user. Routine shape decisions remain autonomous driver decisions; size alone
+   A mismatch between the recorded and measured total is a finding.
+   Verify full totals and bulk buckets with their reproducible command.
+   Treat size flags as informational only.
+   Size alone must never block review, reject a PR, require split attempts or
+   cohesion/exception rationale, or hold approval.
+   Review the actual footprint, complexity, and required context, incrementally when needed.
+   Approval requires sufficient review coverage.
+   Report INCOMPLETE when required coverage is missing.
+   Routine shape decisions remain autonomous driver decisions; size alone
    never requires user approval. Escalate only when that work exposes an
    existing material-scope, security, downtime,
    data-loss, major-design-risk, or unavailable-model hold.

package/skills/axstack-tickets/SKILL.md

@@ -50,11 +50,12 @@ no dispatch preflight.
    sketch boundary as a split signal. Identify internal tasks, dependencies,
    PR ownership, and worktrees. For each task the driver records
    one theme and a coarse size estimate from the ownership, interface, and
-   dependency map. A task estimated in the exception band is assessed for a
-   split at mapping time and split where a green, atomic, reviewable split
-   exists. If the driver judges it inseparable, record the coarse planning
-   rationale with the task; actual measurement and exception evidence follow in
-   the implement receipt. Mapping time requires no actual SHAs or line counts.
+   dependency map. Plan coherent, independently reviewable tasks around those
+   boundaries. Treat size flags as informational only.
+   Size alone must never block review, reject a PR, require split attempts or
+   cohesion/exception rationale, or hold approval.
+   Actual measurement and bulk disclosure follow in the implement receipt.
+   Mapping time requires no actual SHAs or line counts.
    Every capability ends with the fields below and an explicit dependency list.
    Before accepting the map, dispatch `axstack-diligence` under
    [Diligence](../axstack/references/diligence.md) to confirm every spec
@@ -72,7 +73,7 @@ Spec: <approved revision>
 Capability: <Markdown ref, GitHub issue URL, or Linear issue URL> <title>
 Internal task: <task> -> <PR owner> -> <worktree>
 Theme: <one behavior or component>
-Size est: <coarse band estimate>
+Size est: <coarse size estimate>
 Acceptance: <checks from approved spec rev>
 Depends: <task IDs or none>
 ```

package/skills/axstack-watch/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: axstack-watch
-description: When babysitting an existing PR, use axstack-watch to monitor or maintain it within bounded authority.
+description: When babysitting an existing PR, use axstack-watch to maintain own PRs by default within bounded authority.
 ---
 
 # Watch
@@ -37,20 +37,21 @@ live owner and watch; uncertain state holds new registrations until resolved.
 
 For an existing own PR, read the
 [proportional scope identities](../axstack/references/routing.md#proportional-scope-identity),
-verify writable ownership and user maintenance authority, then snapshot the
+apply its default maintenance rule and verify writable ownership, then snapshot the
 accepted maintenance intent once: authorized scope, actual head and base,
 current owner, actual author provenance, and watch state. Check authoring
 session evidence; the orchestrator identity is not author evidence, and never
 assume an author for an imported own PR. It needs no new spec, ticket, or repeated
-approval. Monitoring-only adoption grants no repair or reply authority.
+approval. Explicit observation-only adoption grants no repair or reply authority.
 
 Adoption is settled when the record names one persistent owner, one watch, the
-exact PR revision and base, and the applicable authority snapshot. If write
-authority is unverified, record the hold and continue read-only.
+exact PR revision and base, and the applicable authority snapshot. If writable
+access is unverified, record the hold and continue read-only; pushing stays held.
 
 ## 2. Fix the operating mode
 
-Choose one mode from the user's authority and record it before dispatch:
+Choose one mode under [Shared routing](../axstack/references/routing.md#direct-routes-no-spec-ceremony)
+and record it before dispatch:
 
 - **Chat-run watch:** authorized maintain mode is the default for run-created
   PRs. The initiating chat remains the only driver and record
@@ -63,7 +64,8 @@ Choose one mode from the user's authority and record it before dispatch:
   repair path, including obvious fixes after changed heads or feedback.
 - **Peer:** observe and report a colleague's PR. Peer mode never repairs.
 - **Authorized maintenance:** repair an adopted own PR only within the accepted
-  maintenance snapshot and publication authority.
+  maintenance snapshot and publication authority; own-PR watch requests use this
+  mode by default under Shared routing.
 
 Every later wake must be classifiable from this recorded mode without inferring
 new authority.
@@ -87,7 +89,8 @@ create no recursive teams, and the adoption watcher is never the writer.
 
 A standalone live watch has verified role and timer receipts, handshakes, watched scope,
 wake ownership, and a common expiry. A missing runtime capability is a setup gap,
-not a reason to invent a call or create a duplicate registration. Native
+subject to the [native PR watch fallback](../axstack/references/t3-runtime.md#native-pr-links-and-watches).
+Never invent a call or create a duplicate registration. Native
 wake-ups drive observation; never poll or keep a model active between events.
 
 ## 4. Route each wake
@@ -114,11 +117,14 @@ snapshot. Missing, stale, or materially changed identity holds repair routing
 while monitoring continues. Accepted fixes return to the same original author
 session only when the run itself launched that session and evidence allows,
 then receive refreshed review under the authored mode rule before publication.
-For an adopted own PR, the authored-review pairing follows the recorded
-actual provenance of its repair author, not the PR's historical author.
-Unknown, mixed, or unsupported author provenance
-that cannot establish the eligible configured reviewer is an exact gap to
-report to the user, not permission to invent a pairing or model fallback.
+If this run did not launch the original author, or historical provenance is
+unknown or mixed, launch a new configured `axstack-author` attempt under
+[Shared routing](../axstack/references/routing.md).
+For an adopted own PR, pair the authored reviewer from the recorded actual
+provenance of its repair author.
+Hold only when the repair author's own provenance cannot be established or
+an eligible configured reviewer is unavailable; report that exact gap.
+Historical provenance still follows §5's merge-card rule.
 
 A handled wake has an acknowledged event ID, an observation or action bound to
 the current revision, and a recorded hold or next owner where work remains.
@@ -307,6 +313,9 @@ merge result is a run-wide hold on further automated merges until resolved.
 
 ## 6. End and preserve continuity
 
+Reconcile PR links and stop native PR watches under
+[T3 runtime](../axstack/references/t3-runtime.md#native-pr-links-and-watches).
+
 End a chat-run watch only after all members merged or closed, launched work is settled,
 and the run's release step is settled or not applicable, or user cancellation.
 Without an Autopilot or Release record, the release step is not

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

@@ -15,10 +15,9 @@ 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. If actual author information is
-unknown, mixed, or unsupported and cannot establish an eligible configured
-reviewer, report that exact gap and ask the user; do not assume an author from
-the importing owner or orchestrator.
+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
 

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

@@ -2,6 +2,9 @@
 
 Read this before starting, resuming, or stopping automated PR observation.
 
+Follow [Native PR links and watches](../../axstack/references/t3-runtime.md#native-pr-links-and-watches)
+for linking, event wakes, re-watching, fallback, and teardown in both watch modes.
+
 For each own PR, the owner must follow [PR previews](../../axstack/references/preview.md)
 when deciding on a preview, restarting it after a head change, or tearing it down.
 
@@ -98,7 +101,8 @@ 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.
+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