axstack 0.20.13 → 0.20.14

package/README.md

@@ -107,11 +107,10 @@ model is unavailable. See [workflow and routing details](docs/workflows.md).
 ## Optional PR automation
 
 Manual review and watch work independently of scheduled automation.
-For recurring use, Axstack defines two native Orca manager lanes: one discovers
-eligible peer-review requests, and the other monitors your open PRs and handles
-authorized repair events.
+For recurring peer review, Axstack defines one optional native Orca review manager.
+Own-PR observation and authorized repair remain user-driven through `axstack-watch`.
 
-The lanes use staggered 15-minute schedules. Each pass uses a fresh finite
+The review manager uses a 15-minute schedule. Each pass uses a fresh finite
 session in an isolated workspace and admits eligible actionable PR events within
 measured host capacity. Waiting PRs remain tracked without consuming
 execution slots, so a large open-PR backlog does not require an idle agent per PR.
@@ -121,8 +120,7 @@ release capacity only after native descendant settlement. Uncertain execution
 teardown pauses the lane; settled evidence cleanup does not occupy a slot.
 
 Scheduling is opt-in and requires host-specific runtime validation before
-activation. Installing Axstack does not turn it on. Repairs are limited to
-explicitly allowed repositories; automation never merges for you.
+activation. Installing Axstack does not turn it on. The review automation never merges for you.
 See [PR-manager setup and safety](skills/axstack/references/automations.md).
 
 ## Documentation

package/docs/installation.md

@@ -228,14 +228,12 @@ not prove that a running harness reloaded them.
 
 The installed Axstack bundle does not own or copy Orca's guides. At an action
 boundary, the skill resolves one Orca executable and loads that binary's
-version-matched `orchestration` and `orca-cli` guides. Automation guidance is
-loaded only for the watch branch. Missing discovery is a setup gap, not a reason
+version-matched `orchestration` and `orca-cli` guides. Review automation guidance is loaded only for the scheduled review branch. Missing discovery is a setup gap, not a reason
 to fall back or invent commands.
 
-Native watch activation is currently held: provider selection exists, but
-model, effort, permission, and bounded-expiry support do not preserve the
-accepted contract. Installation creates no production schedule and adds no
-custom scheduler.
+Installation creates no production schedule and adds no custom scheduler.
+The optional review manager requires a separate native canary before activation;
+installed guidance does not prove live behavior.
 
 ## Historical migration
 

package/docs/workflows.md

@@ -140,12 +140,10 @@ session and evidence remain valid.
   never publishes; authorized submission binds the exact commit.
 - `axstack-watch` adopts an existing PR under observation-only, peer, or
   authorized-maintenance scope. A changed head or comment is an event, not
-  repair authority. Repairs return to the original author only for a
-  run-launched session and receive refreshed authored review before scoped
-  `gh stack` publication. `gh stack` publication does not apply to manager
-  repairs: the bounded PR job repairs in its per-PR child worktree, the local
-  SHA receives the actual-author-provenance review, and the exact candidate
-  lands by fast-forward `git push` after final readback.
+  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
+  and remote readback.
 - `axstack-audit` separates execution outcome, procedure, and measurement
   coverage with evidenced denominators; it proposes but never self-edits.
 - `axstack-cleanup` distinguishes settled-Dispatch release, exact unused-shell
@@ -187,15 +185,14 @@ authority. Delivery failure never clears the underlying hold.
 Healthy watch observations remain quiet. The optional `axstack-monitor` is a
 read-only observer for standalone watches and never sends.
 
-## Native watch automations
+## Optional native peer-review automation
 
-The accepted contract has exactly two logical native manager lanes: review at
-minutes `0,15,30,45` and watch at `7,22,37,52`. Each scheduled pass uses a
-fresh finite session in a new isolated workspace, scans complete
+The optional native review manager runs at minutes `0,15,30,45`. Each
+scheduled pass uses a fresh finite session in a new isolated workspace, scans complete
 discovery pages, and admits eligible actionable PR events within measured host
-capacity across both lanes. Waiting PRs stay covered and consume no slot after
-owned descendants settle. Each job uses one repository-parented worktree; managers never check out
-PR branches in their own workspaces.
+capacity. Waiting PRs stay covered and consume no slot after
+owned descendants settle. Each job uses one repository-parented worktree; the
+manager never checks out PR branches in its own workspace.
 
 Every pass reconciles saved, GitHub, and native Orca state across all same-lane
 workspaces before admission. A
@@ -203,9 +200,10 @@ confirmed same-lane manager makes the new duplicate do no work or shared-record
 write and close only itself. Normal teardown settles descendants, saves durable
 continuity and decisions outside disposable workspaces, then retires its own
 verified isolated pass workspace as the final action. It never bulk-closes a
-shared manager workspace or a PR-job worktree, or cleans preserved candidates,
+shared manager workspace or a PR-job worktree, or cleans preserved
 evidence, user sessions, unknown liveness, `user_takeover`, or ambiguous
-publication state. Manual review/watch remains outside this scheduled lifecycle.
+publication state. Manual review and user-driven `axstack-watch` remain outside
+this scheduled lifecycle.
 
 One natively ordered successor may recover an exact positively completed
 predecessor whose terminal survived, but only after matching its automation,
@@ -229,18 +227,17 @@ teardown pauses the lane; retained evidence or cleanup metadata does not consume
 a slot after positive full-tree settlement. Once settled, an unchanged held
 event remains deduplicated while unrelated eligible PRs continue.
 
-Requested reviews cover any accessible repository; automatic repairs retain
-their `defi-com/monorepo` and `defi-com/mobile` scope. Orca owns schedules,
+Requested peer reviews cover any accessible repository. Orca owns schedules,
 sessions, Tasks, and Dispatches. Axstack adds no custom scheduler, queue engine,
 cursor files, polling loop, or historical runtime fallback.
 
-## Automations
+## Review automation
 
-The review and watch managers use short packaged prompts that load the current
-relative contract and invoke `axstack-review` or `axstack-watch`. Bounded jobs
-publish ordinary exact-head review verdicts or reviewed fast-forward repairs;
-the human merges. Exceptional security, permanent-on-chain, or architectural
-decisions remain actionable in GitHub or a durable user-owned conversation
+The review manager uses one short packaged prompt that loads the current
+relative contract and invokes `axstack-review`. Bounded jobs publish ordinary
+exact-head review verdicts; the human merges. Manual adopted-PR maintenance
+uses `axstack-watch` with local-SHA review before authorized publication.
+Exceptional security, permanent-on-chain, or architectural decisions remain actionable in GitHub or a durable user-owned conversation
 after manager self-close, with an authorized deduplicated Telegram notification.
 The current operational contract is
 `skills/axstack/references/automations.md`.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.20.13",
+  "version": "0.20.14",
   "description": "Axstack installer and setup CLI: installs owned chat skills and role data, configures supported harness settings, and checks Orca capabilities.",
   "keywords": [
     "claude-code",

package/skills/axstack/references/automations.md

@@ -1,17 +1,12 @@
-# Native PR managers
+# Native peer-review manager
 
-Read this only for the two native Orca PR-manager automations. The historical
+Read this for the optional native Orca peer-review automation. The historical
 automation specs and plans describe retired designs and are not instructions.
 
 ## Topology and schedules
 
-There are exactly two logical manager lanes:
-
-- **Review manager:** runs at minutes `0,15,30,45` and invokes
-  [axstack-review](../../axstack-review/SKILL.md) for eligible peer reviews.
-- **Watch manager:** runs at minutes `7,22,37,52` and invokes
-  [axstack-watch](../../axstack-watch/SKILL.md) for eligible own-PR watch or
-  repair events.
+The review manager runs at minutes `0,15,30,45` and invokes
+[axstack-review](../../axstack-review/SKILL.md) for eligible peer reviews.
 
 Use a new isolated workspace for every scheduled pass, with one fresh finite
 manager session. Configure native repo-created worktree mode against the
@@ -21,8 +16,8 @@ launch; the manager must not move itself from a shared launch workspace.
 Keep lane continuity and evidence outside disposable manager workspaces at
 the configured durable absolute paths. A manager never checks out a PR branch
 in its pass workspace. Missed slots do not replay a backlog; the next ordinary pass
-discovers current state. The two short packaged prompts sit beside this file
-and discover these rules by relative link instead of copying them.
+discovers current state. The short packaged review prompt sits beside this file
+and discovers these rules by relative link instead of copying them.
 
 Provision one explicit absolute continuity path per automation ID in the
 scheduled prompt. Follow [Run record](run-record.md) for its contents; the
@@ -136,32 +131,26 @@ only when its body ends with
 or a retained legacy receipt proves that provenance; otherwise never replace
 it automatically.
 
-The watch manager covers every open non-draft PR authored by self. It may
-repair only `defi-com/monorepo` and `defi-com/mobile`; PRs elsewhere remain
-observed but read-only. Preserve deploy-on-push exclusions, lowest-first stack
-dependencies, and existing ownership boundaries. Peer code is always
-read-only.
-
 Coverage is not execution. Waiting for CI, a reviewer, a user decision, or a
 merge occupies no execution slot after owned work and descendants settle.
-Watch membership never reserves a slot and no job stays active merely until a
+Review waiting state never reserves a slot and no job stays active merely until a
 PR merges or closes. Thirty open PRs, including ten settled waiting PRs, are
 all scanned; those ten occupy zero slots.
 
 ## Admission and fairness
 
-The review manager and watch manager admit all eligible actionable PR events
+The review manager admits all eligible actionable PR events
 that measured host capacity can support across ticks. Before each admission,
-inspect available memory, CPU load, and active worker trees across both lanes;
+inspect available memory, CPU load, and active worker trees across the host;
 account for the whole proposed worker tree, dependencies, spending limits, and
 exclusive ownership. Report unavailable metrics as unknown; use the remaining
 host evidence rather than treating a missing metric alone as a blocker. Defer
 an event when observed pressure or uncertain headroom cannot support its whole
 tree, record the reason, and remeasure on the next pass. Do not use a fixed
-PR-job count or reserve capacity for either lane.
+PR-job count or reserve a fixed slot.
 
-A slot covers one bounded PR event and remains occupied while its author,
-reviewers, or other owned descendants are active or unsettled. Leaf workers do
+A slot covers one bounded PR event and remains occupied while its reviewers
+or other owned descendants are active or unsettled. Leaf workers do
 not create recursive teams. Settlement of the PR job and every descendant
 frees the slot even while the PR stays open.
 
@@ -180,7 +169,7 @@ writer for the same PR. Reuse an existing valid per-PR worktree, owner, and
 unchanged receipts before creating anything. Otherwise create one separate
 Orca worktree per PR job, parented to that repository's primary worktree, and
 pin the observed head and base. The bounded PR coordinator loads the
-appropriate skill, launches only the reviewers or author that skill owns,
+review skill, launches only the reviewers that skill owns,
 handles the current actionable event, returns exact receipts, then settles.
 Settlement returns continuity to the manager rather than retaining an idle PR
 coordinator. Reviewers retain the isolation required by `axstack-review`.
@@ -194,12 +183,12 @@ containment is uncertain.
 
 An unchanged exact head and unchanged 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, check identity and
-result, or other current GitHub event receipt. Dedupe from current GitHub state,
+identity includes the applicable review ID and body digest, request identity, or other current GitHub event
+receipt. Dedupe from current GitHub state,
 native Orca Task and Dispatch 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, candidate,
-publication receipt, hold, and next action. GitHub remains authoritative for
+head, base, event identity, mode, owner and worker receipts, verdict,
+submission receipt, hold, and next action. GitHub remains authoritative for
 open state, revisions, reviews, checks, and merge state.
 
 ## Held job settlement
@@ -236,10 +225,10 @@ lane before another pass can admit work rather than accumulating active passes
 or claiming capacity from an uncertain process tree.
 
 When the current event is handled, settle and release owned native resources.
-Preserve dirty worktrees, unpushed candidates, unarchived review evidence, pending
+Preserve dirty worktrees, unarchived review evidence, pending
 external results, and user-owned work until durability and ownership are
 proven. Unknown liveness, `user_takeover`, and ambiguous publication likewise
-forbid cleanup. Here a pending external result means an unconfirmed publication
+forbid cleanup. Here a pending external result means an unconfirmed review submission
 or send outcome, not pending CI. Waiting state belongs in GitHub and the compact
 record, never in an idle model, per-PR timer, or polling loop.
 Follow the [private evidence archive](evidence-archive.md) when evidence is the
@@ -251,7 +240,7 @@ read back the archive and compact receipt, then follow
 the reviewer checkout before merge. This does not release active jobs or manager
 pass workspaces.
 
-## Review and repair authority
+## Review authority
 
 Peer review follows `axstack-review` peer mode: two isolated configured
 reviewers inspect the exact head and base. Complete review may publish the
@@ -269,21 +258,8 @@ private or local artifacts. Write the local HTML copy under the established
 `review-PR-<num>.html` reserved for `defi-com/monorepo`. Never publish a
 `COMMENT` review. An ambiguous submission is looked up before retry.
 
-An own PR becomes actionable for repair only when a failing check has a base
-check-run with the same name and producing app identity observed passing (or a
-legacy status has the same context), or when a new current-head
-`CHANGES_REQUESTED` review has both an unhandled review ID and an unhandled body
-digest. Missing, pending, or same-name/different-app base evidence holds repair.
-A new head or generic event grants no repair authority by itself.
-
-Authorized own-PR repair follows `axstack-watch`: produce the smallest repair
-in the per-PR worktree, obtain the actual-author-provenance reviewer pairing,
-and publish only a reviewed fast-forward repair push after exact-current
-candidate, head, base, event, allowlist, deploy, and remote readback receipts.
-Reconcile an ambiguous review or push result before any retry.
-
 No manager, coordinator, or worker may merge, close, force-push, rebase,
-restack, broaden scope, or use `gh stack` mutation. Human merge remains the
+restack, broaden scope, or mutate a PR branch. Human merge remains the
 boundary.
 
 ## Exceptional decisions and notifications
@@ -314,7 +290,7 @@ self-close. Waiting PRs still occupy zero slots once their owned trees settle.
 
 Cleanup of PR-job setup shells stays scoped to positively identified owned unused
 setup shells: use the native exact-terminal close operation for each only.
-Preserve dirty worktrees, unpushed candidates, unarchived review evidence, user-owned
+Preserve dirty worktrees, unarchived review evidence, user-owned
 terminals, unknown liveness, `user_takeover`, and ambiguous publication state.
 Never classify all dirt as evidence. If explicitly classified evidence is the
 last retention reason, apply and verify the [private evidence archive](evidence-archive.md),

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

@@ -29,17 +29,3 @@ 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.
-
-## Automation repair exception
-
-For a manager PR repair under
-[Native PR managers](automations.md), the candidate is a local immutable
-commit SHA in the per-PR child worktree, not a published remote ref. The
-reviewer confirms that exact local SHA with `git rev-parse` in the worktree
-instead of remote equality, and inspects a detached checkout of it with the
-pinned base. The remote ref is expected to still be the pre-repair head; record
-it as the expected-old remote SHA rather than requiring it to equal the
-candidate. Remote equality is re-checked at the publication readback of the
-watch skill's repair-publication reference immediately before the fast-forward
-push. Ordinary workflows keep the remote confirmation above; the
-exception never applies outside a manager PR job.

package/skills/axstack/references/lifecycle.md

@@ -17,8 +17,8 @@ binding state and receipts to exact revisions.
   `axstack-reviewer-secondary` sessions with identical brief and isolated first
   pass; authored = one eligible configured reviewer from actual author
   provenance. Owner and author never review.
-- Automation review/watch managers and optional monitor: see
-  [Watch health](#watch-health).
+- Automation review manager and optional standalone monitor: see
+  [Review automation health](#review-automation-health).
 - Auditor (`axstack-auditor`): report-only; never edits, merges, activates, or
   audits itself.
 
@@ -99,21 +99,21 @@ On `consumer_fenced`, reconcile the active coordinator rather than borrowing an
 identity. Respect settlement protection including `user_takeover`.
 
 No execution heartbeat or substitute scheduler is created by Axstack. Native
-watch automation follows [Watch health](#watch-health).
+review automation follows [Review automation health](#review-automation-health).
 Tracking grants no merge, release, model-substitution, or scope authority.
 
 ## Deadline (one rule for every owned timer)
 
 The default 24-hour deadline covers standalone task-owned timers. Stop them at
-deadline and preserve remaining work; there is no watch deadline for
-automations. A PR is merge-ready only with the applicable review receipt(s) at
+deadline and preserve remaining work; the review automation has no task-owned
+deadline. A PR is merge-ready only with the applicable review receipt(s) at
 its exact head; green CI or tests alone never make it merge-ready. Merge-ready
 differs from merged; human merges.
 
-## Watch health
+## Review automation health
 
-Native review and watch lanes use fresh finite sessions in isolated per-pass
-workspaces on staggered 15-minute schedules. Each admits eligible actionable PR
+The native review manager uses fresh finite sessions in isolated per-pass
+workspaces on a 15-minute schedule. It admits eligible actionable PR
 events within measured host capacity; waiting PRs remain covered without
 reserving slots. Bounded PR jobs own their
 events, use per-PR worktrees, and settle after descendants settle. Build no

package/skills/axstack/references/simplify-diff.md

@@ -0,0 +1,51 @@
+# Simplify the diff
+
+Load this reference only after the relevant checks are green and the candidate
+contains code diffs or agent instructions. It does not apply to
+general human-facing or marketing prose.
+
+## Preserve behavior first
+
+Simplify only when the same checked behavior and accepted scope remain intact.
+Read the changed lines with their callers and local conventions; do not optimize
+an isolated snippet while making the surrounding system harder to understand.
+Re-run the check that established green after an applied simplification.
+
+Look for complexity introduced or retained by the diff:
+
+- speculative abstractions without a current second use;
+- redundant narration that repeats what names or structure already say;
+- unjustified defensive branches, fallback logic, or casts;
+- needless wrappers or indirection;
+- deep nesting that a guard clause or smaller direct operation can flatten; and
+- convention mismatch where the repository already has a simpler pattern.
+
+Prefer the smallest behavior-preserving change. Do not expand into nearby
+cleanup, redesign stable interfaces, or trade explicit behavior for brevity.
+
+## Keep necessary safeguards
+
+Never remove complexity merely because it looks verbose. Preserve:
+
+- trust-boundary validation and failure handling;
+- accessibility text and interaction semantics;
+- meaningful why-comments that capture a non-obvious constraint;
+- explicit uncertainty instead of turning an unknown into a claim; and
+- authority instructions, approval boundaries, and mutation limits.
+
+When evidence cannot show that a change preserves behavior, retain it and name
+the uncertainty. A justified `not-applicable` result is valid; there is no
+deletion quota and no quality score.
+
+## Receipt
+
+Record one line for the exact candidate:
+
+```text
+Simplification: <applied | not-applicable> — evidence: <diff locations and checks>; retained complexity: <necessary complexity and why>
+```
+
+For `applied`, name the simplified locations and the green check rerun. For
+`not-applicable`, name what was inspected and why no behavior-preserving
+simplification was justified. The receipt is review evidence, not proof of live
+model effectiveness and not an automatic gate.

package/skills/axstack-audit/SKILL.md

@@ -79,6 +79,10 @@ counts with denominators plus the evidence behind the count:
   evidence path is absent, or `UNKNOWN` with the reason when its records are
   unavailable.
 - Independent exact-revision review status and unresolved findings.
+- Simplification applicability determinations evidenced / total candidate diffs,
+  and complete simplification receipts / total candidates, broken down as
+  `applied`, `not-applicable`, or `UNKNOWN` with the reason. This measures
+  applicability and completeness; it is not a quality score.
 - 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.

package/skills/axstack-implement/SKILL.md

@@ -121,6 +121,15 @@ green evidence. For structure-preserving work, make only the accepted
 structural edits and keep the unchanged baseline and equivalence evidence
 green.
 
+At this post-green refactor step, inspect the changed paths. When the candidate
+contains a code diff or agent-instruction changes, load and follow
+[Simplify the diff](../axstack/references/simplify-diff.md), then rerun affected
+green checks after any edit. Do not load it for general human-facing or
+marketing prose. Record the required evidence line whether simplification was
+applied or found not applicable in the `Simplification:` line of the
+[section 5 implementation receipt](#5-verify-and-return-the-candidate),
+including evidence and retained complexity.
+
 ## 5. Verify and return the candidate
 
 Run the acceptance checks and affected integration boundaries. Record commands,
@@ -138,6 +147,7 @@ Owner: <profile + session ID + worktree>
 Scope: <approved spec + capability | small-change intent | maintenance snapshot>
 Shape: <total> lines vs base <sha>; bulk: <buckets>; theme: <one line>
 TDD: <normal red/green | structure-preserving old-green/same-check-new-green evidence>
+Simplification: <applied | not-applicable> — evidence: <diff locations and checks>; retained complexity: <necessary complexity and why>
 Acceptance: <checks + observed results>
 Dependencies: <parent revisions or none>
 Unverified: <boundaries + reasons>

package/skills/axstack-review/SKILL.md

@@ -5,7 +5,7 @@ description: When a candidate PR needs final review, use axstack-review for conf
 
 # Review
 
-Manual invocation does not enter the scheduled manager lifecycle; never close the user’s chat or workspace.
+Manual review keeps the user’s chat and workspace open.
 
 Produce one evidence-bound verdict for an exact candidate revision using the
 review count and model routing required by its mode. Report within the
@@ -21,7 +21,7 @@ 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, and apply the shared
-[PR-shape policy](../axstack/references/pr-shape.md). For an owned candidate,
+[PR-shape policy](../axstack/references/pr-shape.md). 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
@@ -89,17 +89,17 @@ owns the event and settles after its skill-owned reviewers settle.
 
 ## Review the candidate
 
-1. **Pin the brief.** For an owned candidate, verify remote confirmation of the
-   candidate SHA before reviewer dispatch. For an automation repair, confirm
-   instead the local immutable candidate SHA with `git rev-parse` in the
-   per-PR child worktree and pin the remote pre-repair head as the
-   expected-old remote SHA; remote equality is re-checked at the publication
-   readback, per the automation repair exception of the
+1. **Pin the brief.** For an implementation candidate, verify remote confirmation
+   of the candidate SHA before reviewer dispatch under the
    [candidate-publication boundary](../axstack/references/candidate-publication.md).
-   Record the PR URL, exact candidate
-   SHA and current base, applicable intent or spec/ticket identity and
-   acceptance, exclusions, authority, actual author provenance for authored
-   mode, and all six angles.
+   For manual adopted-PR maintenance under
+   [Repair and publication](../axstack-watch/references/repair-publication.md),
+   confirm the exact local candidate SHA with `git rev-parse` in the owned
+   worktree, pin the remote pre-repair head and current base, and review code and
+   reply bodies before publication. Record the PR URL, exact candidate SHA,
+   current base, applicable intent or spec/ticket identity and acceptance,
+   exclusions, authority, actual author provenance for authored mode, and all
+   six angles.
 2. **Materialize the mode-required review.** Immediately before dispatch, read
    [Orca runtime](../axstack/references/orca-runtime.md), then apply exactly one
    branch below. For every reviewer, apply
@@ -174,6 +174,16 @@ owns the event and settles after its skill-owned reviewers settle.
    existing material-scope, security, downtime,
    data-loss, major-design-risk, or unavailable-model hold.
 
+   Also under angle 6, independently classify the pinned diff. When it contains
+   code or agent-instruction changes, load
+   [Simplify the diff](../axstack/references/simplify-diff.md) and independently
+   verify both the simplification receipt and the relevant diff; for excluded
+   prose, verify the receipt's `not-applicable` evidence without loading the
+   reference. A simplification finding names the concrete location, consequence,
+   and simpler behavior-preserving alternative. Preserve trust boundaries,
+   accessibility, meaningful why-comments, uncertainty, and authority; do not
+   turn this judgment into a deletion quota or score.
+
    Verify the applicable spec, ticket, or intent acceptance, executable
    evidence, exact candidate SHA, current base, and affected integration
    boundary, plus rendered interaction evidence for relevant UI work. A

package/skills/axstack-watch/SKILL.md

@@ -5,7 +5,7 @@ description: When babysitting an existing PR, use axstack-watch to monitor or ma
 
 # Watch
 
-Manual invocation does not enter the scheduled manager lifecycle; never close the user’s chat or workspace.
+Manual watch keeps the user’s chat and workspace open.
 
 Leave each adopted PR with one accountable owner, current readiness evidence,
 and user-facing updates that name its current milestone and next wake or
@@ -16,13 +16,6 @@ Its required edge loads [Shared lifecycle](../axstack/references/lifecycle.md),
 including the end-of-run audit hook. Reach other references only at the steps
 that name them.
 
-When the current session is a fresh watch-manager session, load
-[Native PR managers](../axstack/references/automations.md) and follow only its
-discovery, admission, recovery, and settlement branch. Do not adopt or repair a
-PR, materialize `axstack-owner`, or check out a PR branch in the manager
-workspace. Each admitted bounded PR coordinator re-enters this skill in its
-recorded mode.
-
 Preserve any explicitly named PR, repository, or peer scope. For broad
 discovery of the user's own PRs (such as “my” or “our” PRs), run
 `gh api user --jq .login` on the execution host, then select open PRs authored
@@ -30,10 +23,6 @@ by that login in the named or current repository. Never hardcode or guess the
 username; a missing or failed authenticated-login lookup is a concrete blocker.
 The authenticated human login selects PRs. Runtime session IDs coordinate work
 only and establish neither human identity nor write, reply, or merge authority.
-When the session is a bounded watch-manager PR job, also load
-[Native PR managers](../axstack/references/automations.md): the bounded PR
-coordinator owns that event and its allowlist bounds every mutation.
-
 ## 1. Adopt and reconcile
 
 Start from actual state. Reconcile the PR's remote head and base, ownership,
@@ -73,13 +62,9 @@ Read-only checks and updates to the already-owned local record need no runtime
 load. When the watch needs a new owner or automated observation, first read
 [Watch runtime](references/watch-runtime.md) and then
 [Orca runtime](../axstack/references/orca-runtime.md). Reconcile before creating
-anything. Each native watch-manager pass starts a fresh finite session in an
-isolated per-pass workspace on its staggered 15-minute schedule, covers
-every eligible own PR, and starts only bounded actionable-event jobs. Waiting PRs reserve no execution slots and
-there is no watch deadline for manager automation. `axstack-monitor` stays an
-optional read-only observer that never sends. One read-only PR observation
-needs neither. The bounded PR coordinator is the live owner for its event;
-materialize no `axstack-owner` and start no automation for a read-only check.
+anything. Task-owned observations use their recorded wakes and expiry.
+`axstack-monitor` stays an optional read-only observer that never sends. One read-only PR observation
+needs neither. Start no automation for a read-only check.
 
 For standalone adoption, materialize `axstack-owner` only when no live owner
 exists. Once it exists, the current chat is not a competing coordinator. Only
@@ -102,9 +87,7 @@ A healthy unchanged observation produces no user-facing message.
 
 Observation-only and peer wakes produce a read-only report and stop. For an
 authorized maintenance wake that may require a repair or public reply, read and
-follow [Repair and publication](references/repair-publication.md). A manager PR
-job repairs in its per-PR child worktree created through `orca-cli`;
-the manager workspace never checks out a PR branch.
+follow [Repair and publication](references/repair-publication.md).
 
 ### Feedback routing
 
@@ -115,11 +98,9 @@ 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 under the manager, the original authoring session is
-not a run-launched session: the repair author is the manager PR coordinator or
-a dispatched `axstack-author`, and the authored-review
-pairing follows the recorded actual provenance of that repair, not the PR's
-historical author. Unknown, mixed, or unsupported author provenance
+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.
 
@@ -128,9 +109,8 @@ the current revision, and a recorded hold or next owner where work remains.
 
 When a new actionable event is eligible under a recorded `Notification policy`,
 the owner may use the optional [axstack-relay](../axstack-relay/SKILL.md).
-The monitor never sends. The manager deduplicates authorized notifications;
-absent policy or failed relay uses the recorded durable GitHub or user-owned
-conversation and leaves every existing hold open.
+The monitor never sends. Deduplicate authorized notifications; absent policy
+or failed relay uses the current Orca conversation and leaves the existing hold open.
 
 ## 5. State readiness precisely
 
@@ -141,14 +121,9 @@ observed state distinct from merged, and the human merges by default.
 
 ## 6. End and preserve continuity
 
-A bounded manager PR job ends as soon as its current event and every owned
-descendant settle. It returns exact receipts and remaining state to the logical
-manager lane's durable continuity, releases proven resources, and never waits
-for merge or stops the manager's recurring schedule.
-
 End a standalone watch early when all required PRs merge, at cancellation, or
-at its shared default 24 h deadline. There is no watch deadline for manager
-automation. In every case, stop and verify all owned registrations.
+at its shared default 24 h deadline. In every case, stop all owned
+registrations and verify their receipts.
 
 At every end condition, leave the compact state below in the private run record
 and report it in the current chat, even when work remains. Expiry grants neither

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

@@ -8,9 +8,7 @@ and peer modes stop with a report before this branch.
 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. For an adopted own PR under the manager, the repair author is
-the manager PR coordinator or a dispatched `axstack-author`; record that
-repair's actual provenance before
+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
@@ -25,20 +23,22 @@ the importing owner or orchestrator.
 ## 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 per-PR child worktree and reviewed in
-authored mode at its local SHA; nothing is pushed for review. Both code and
+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. Under a manager PR job, a serious-risk escalation
-preserves the local candidate and exact context, records the hold in the
-compact 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.
+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.
 
 ## 3. Revalidate immediately before publication
 
@@ -51,15 +51,11 @@ readback.
 
 ## 4. Publish idempotently
 
-Use `gh stack` for the adopted PR only, preserving unrelated stack entries.
+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.
 
-Manager automation pushes fast-forward only: run the section 3 publication
-readback immediately before the push, then `git push` to the PR branch with no
-lease or force, and no `gh stack` sync or restack from a manager. A
-non-fast-forward remote is a recorded hold, never a rewrite.
-
 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.

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

@@ -10,32 +10,3 @@ current GitHub state, persists event IDs, wakes the owner only for a new
 actionable event, and never sends or mutates. Healthy observations update
 quietly. Reuse prior watch identity rather than registering a duplicate, and
 stop task-owned registrations at completion, cancellation, or expiry.
-
-## Native watch manager
-
-The separate native watch manager lane follows the
-[native PR-manager contract](../../axstack/references/automations.md). Each pass
-uses a new isolated workspace and fresh finite session at minutes `7,22,37,52`.
-Continuity survives outside disposable workspaces; admission reconciles the
-whole lane across workspaces. It scans every eligible own PR and
-admits bounded actionable-event jobs within measured host capacity. Waiting PRs
-stay covered without reserving slots. Each job uses its own repository-parented worktree and
-settles with all descendants; no model, per-PR timer, or polling loop waits for
-CI, review, a user decision, or merge.
-
-Load the version-matched Orca automation and orchestration guidance through the
-shared [runtime boundary](../../axstack/references/orca-runtime.md). Requested
-settings or source configuration are not runtime evidence. Preserve quiet
-unchanged behavior, exact-head event dedupe, ownership, complete discovery,
-and current authority.
-
-Before activation, canary fresh-session launch, an overlapping scheduled pass,
-session loss and recovery, nested dispatch depth for coordinator-launched leaves, and
-total process and memory behavior. Until observed, those remain unverified; do
-not replace them with a precheck, watchdog, custom scheduler, state engine, or
-legacy fallback.
-
-On recovery reconcile actual native workers, GitHub, and the compact run record
-before admitting work. Unknown state blocks only the affected PR. At every job
-end, settle owned workers, preserve unsafe or user-owned state, release proven
-resources, and leave exact resumable receipts.

package/skills/axstack/references/watch-manager-prompt.md

@@ -1,12 +0,0 @@
-# Watch manager prompt
-
-You are a fresh finite watch-manager session in its isolated per-pass Orca workspace. Enter
-through the installed `axstack-watch` skill; that skill loads its packaged
-`../axstack/references/automations.md` contract by relative reference. Discover
-every eligible own-PR event and invoke the skill through Orca for each admitted
-bounded PR job. Keep complete coverage and admit actionable events within
-measured host capacity, preserve exact ownership, candidates, holds, and receipts,
-settle completed trees, and stay quiet when nothing changed. Reconcile before
-admission, save durable continuity outside this workspace, then retire only this
-pass workspace as the final action under the contract's ownership guards.
-Reconcile the whole lane, not just this workspace. Never check out a PR branch here.