@alphazede/bearing-lite 0.1.10 → 0.1.11

package/skills/navigator/SKILL.md

@@ -1,59 +1,36 @@
 ---
 name: navigator
 description: >
-  Sequence dependency-connected Expedition waves, resolve cross-wave conflicts,
-  and own integration boundaries. Use for Navigator, Expedition, or multi-wave
-  execution control. Do not use for one packet/wave, product implementation,
-  planning-state ownership, model selection, publication, or assurance.
+  Compatibility diagnostic for plans that still name Navigator. Use when an
+  existing plan assigns Navigator or asks to sequence expedition waves as
+  navigator. Do not use for new Journeys, packet work, planning, assurance,
+  or publication.
 ---
 
 # Navigator
 
-Highest execution authority below Router; performs the least hands-on execution.
+Compatibility only. Router now owns cross-wave sequencing and conflict
+resolution.
 
 ## Inputs and match
 
-- **Inputs:** approved artifacts, wave graph, dependencies, repository scope,
-  authority, lineup from the recorded Journey snapshot, review cadence,
-  acceptance, and return schema.
-- **Match:** an Expedition has multiple dependency-connected waves or phases,
-  including simultaneous waves that share interfaces or conflict.
-- **Non-match:** one Explorer wave or Crewmate packet is sufficient.
+- **Inputs:** a plan that still assigns `Navigator`, plus the recorded Journey
+  snapshot.
+- **Match:** an existing plan names Navigator as an assigned role.
+- **Non-match:** new Journeys, Explorer waves, Crewmate packets, or assurance.
 
 ## Algorithm
 
-1. Start fresh and reread the approved specification, design, SEIT,
-   implementation, and review baseline. Verify snapshot lineup and cadence.
-   Read dispatch identities only from the recorded Journey snapshot, never
-   from the current global defaults file. Revalidate the visible checkout
-   lease against the approved Journey, repository, checkout/worktree, branch,
-   candidate revision, generation, and active state before the first write,
-   dispatch, integration, or cross-wave transition. Released, stale-generation,
-   forged, or branch/HEAD-drifted leases fail closed. Authorized same-Journey
-   candidate progress whose parent is the current leased revision refreshes
-   candidate_revision on the same generation. The same valid lease
-   continues without duplicate dispatch.
-2. Sequence fresh Explorer sessions. For simultaneous waves with
-   shared-interface or dependency conflicts, resolve ordering and integration
-   here; never add a nested multi-wave controller.
-3. Integrate typed wave returns and correct only sequencing/coverage gaps inside
-   approved authority; never perform implementation.
-4. Dispatch independent assurance once at the confirmed `per-slice`,
-   `per-round`, or final integrated boundary. Honor `max_assurance_rounds` of 1
-   from visible `assurance_rounds`. If the review is repairable, spend at most
-   one remaining `attempts` repair, run deterministic coordinator verification,
-   and close the gate without another review. A failed repair or scope change
-   returns `OWNER_DECISION_REQUIRED` with candidate and count. After Journey
-   `COMPLETE`, deployment checks do not reopen assurance.
-5. Return to the Router after the bounded Expedition outcome; do not silently
-   continue into another Journey or protected action.
+1. Do not sequence waves, reread the artifact set, dispatch Explorers, or
+   run assurance. Read identities only from the recorded Journey snapshot,
+   never from the current global defaults file.
+2. Return `REROUTED` to the Router with a diagnostic that Navigator is not a
+   normal role; treat the assignment as unused and continue under Router.
+3. Preserve the checkout lease. Do not write planning state.
 
 ## Return and recovery
 
-Return `READY`, `REROUTED`, `WAITING_ON`, or `OWNER_DECISION_REQUIRED` with
-plan ref, role, subject, dependencies, scope, authority, evidence, blocker, next
-action, and receiver. Attempts 1–3 require new evidence or strategy; a material
-design, intent, scope, security, destructive, remote, or publication change
-returns to Owner Authority.
+Return `REROUTED` with verdict, candidate_ref, changed_paths, tests, findings,
+and blocker. Findings name the compatibility path.
 
 Never implement, self-assure, select models, or mutate remotes.

package/skills/park-ranger/SKILL.md

@@ -2,9 +2,10 @@
 name: park-ranger
 description: >
   Independently review one exact stable candidate for introduced actionable
-  defects in a fresh session at the selected review boundary. Use for Park
-  Ranger, code review, or defect adjudication. Do not use for implementation,
-  automatic review, evidence scoring, user acceptance, or author self-review.
+  defects in a fresh session at the end. Use for Park Ranger, code review, or
+  defect adjudication. Do not use for implementation, automatic review,
+  evidence scoring, user acceptance, author self-review, or slice/round
+  boundaries.
 ---
 
 # Park Ranger
@@ -14,18 +15,20 @@ Independent defect assurance, outside the mutation-authority ladder.
 ## Inputs and match
 
 - **Inputs:** approved baseline, exact candidate ref and diff, author identity,
-  relevant evidence, cadence boundary, review focus, and return schema.
-- **Match:** Park Ranger is declared and the selected `per-slice`, `per-round`,
-  or `at-end` boundary has a stable candidate.
-- **Non-match:** boundary is not reached, candidate is unstable/unchanged, or
+  relevant evidence, at-end boundary, review focus, and compact return schema.
+- **Match:** Park Ranger is declared and the final integrated candidate is
+  stable at-end.
+- **Non-match:** slice or round boundary, candidate is unstable/unchanged, or
   Validator/Surveyor work is requested.
 
 ## Algorithm
 
-1. Start fresh; reject author identity, candidate discontinuity, or missing
-   review boundary.
+1. Start a fresh session; reject author identity, author ancestry, candidate
+   discontinuity, or any boundary other than at-end.
 2. Review only introduced correctness, security, performance, and meaningful
-   maintainability defects plus applicable plan drift.
+   maintainability defects plus applicable plan drift. When the candidate
+   implements a published standard, compare the change against the cited text
+   rather than neighbouring agreement.
 3. Prove reachability and affected code, assign P0–P3, and cite precise changed
    locations. Avoid speculation and nits.
 4. Return a patch verdict and repair targets. Never implement a finding.
@@ -33,7 +36,7 @@ Independent defect assurance, outside the mutation-authority ladder.
 ## Return and recovery
 
 Return `BLOCK`, `REPAIR_REQUIRED`, `ACCEPT_WITH_FINDINGS`, or `ACCEPT` with
-candidate ref, findings, evidence, verdict, blocker, next action, and receiver.
+verdict, candidate_ref, changed_paths, tests, findings, and blocker.
 `ACCEPT`, `ACCEPT_WITH_FINDINGS`, and `BLOCK` are terminal. `REPAIR_REQUIRED`
 permits bounded correction. `ACCEPT_WITH_FINDINGS` accepts residual findings;
 do not follow it with another repair. Coordinators enforce

package/skills/surveyor/SKILL.md

@@ -2,9 +2,9 @@
 name: surveyor
 description: >
   Independently compare one stable integrated candidate with the approved
-  user-facing outcome in a fresh session at the selected acceptance boundary.
-  Use for Surveyor or outcome acceptance. Do not use for implementation,
-  evidence scoring, defect review, automatic review, or publication approval.
+  user-facing outcome in a fresh session at the end. Use for Surveyor or
+  outcome acceptance. Do not use for implementation, evidence scoring, defect
+  review, automatic review, publication approval, or slice/round boundaries.
 ---
 
 # Surveyor
@@ -14,17 +14,18 @@ Independent outcome assurance, outside the mutation-authority ladder.
 ## Inputs and match
 
 - **Inputs:** approved specification/review baseline, exact integrated candidate,
-  author identities, user-facing evidence, cadence boundary, prior required
-  assurance, and return schema.
-- **Match:** Surveyor is declared and a selected review boundary has an integrated
-  candidate suitable for user-facing comparison.
-- **Non-match:** unfinished packet, unstable candidate, Validator sufficiency,
-  Park Ranger defect review, or owner-only release decision.
+  author identities, user-facing evidence, at-end boundary, prior required
+  assurance, and compact return schema.
+- **Match:** Surveyor is declared and the final integrated candidate is ready
+  for user-facing comparison at-end.
+- **Non-match:** unfinished packet, slice or round boundary, unstable candidate,
+  Validator sufficiency, Park Ranger defect review, or owner-only release
+  decision.
 
 ## Algorithm
 
-1. Start fresh; verify candidate continuity, independence, completed prerequisite
-   assurance, and the cadence boundary.
+1. Start a fresh session; reject author ancestry; verify candidate continuity,
+   independence, completed prerequisite assurance, and the at-end boundary.
 2. Exercise or inspect every observable approved outcome, including failure and
    recovery behavior relevant to the Journey.
 3. Map each gap to an exact requirement and evidence location. Separate observed
@@ -33,8 +34,8 @@ Independent outcome assurance, outside the mutation-authority ladder.
 
 ## Return and recovery
 
-Return `ACCEPT`, `GAPS`, or `OWNER_DECISION_REQUIRED` with candidate ref,
-requirement coverage, evidence, gaps, blocker, next action, and receiver.
+Return `ACCEPT`, `GAPS`, or `OWNER_DECISION_REQUIRED` with verdict,
+candidate_ref, changed_paths, tests, findings, and blocker.
 A gap may receive one repair followed by coordinator verification; do not
 reassess the same Journey.
 

package/skills/validator/SKILL.md

@@ -2,9 +2,9 @@
 name: validator
 description: >
   Independently validate evidence sufficiency and optional rubric scoring for
-  one exact stable candidate in a fresh session at the selected review boundary.
-  Use for Validator or evidence validation. Do not use for implementation,
-  defect review, user acceptance, automatic reviews, or author self-checks.
+  one exact stable candidate in a fresh session at the end. Use for Validator
+  or evidence validation. Do not use for implementation, defect review, user
+  acceptance, automatic reviews, author self-checks, or slice/round boundaries.
 ---
 
 # Validator
@@ -14,26 +14,28 @@ Independent assurance responsibility, outside the mutation-authority ladder.
 ## Inputs and match
 
 - **Inputs:** approved baseline, exact candidate ref, author identity, scope,
-  evidence, acceptance, cadence boundary, optional rubric, and return schema.
-- **Match:** Validator is declared and the chosen `per-slice`, `per-round`, or
-  `at-end` boundary is reached.
-- **Non-match:** candidate is unstable, boundary is not reached, evidence alone
+  evidence, acceptance, at-end boundary, optional rubric, and compact return
+  schema.
+- **Match:** Validator is declared and the final integrated candidate is ready
+  at-end.
+- **Non-match:** candidate is unstable, slice or round boundary, evidence alone
   needs author self-check, or another assurance responsibility applies.
 
 ## Algorithm
 
-1. Start fresh and reject author identity, candidate discontinuity, or a missing
-   cadence boundary.
+1. Start a fresh session; reject author identity, author ancestry, candidate
+   discontinuity, or any boundary other than at-end.
 2. Check scope continuity, labeled evidence, required commands, positive and
-   negative cases, and acceptance support.
+   negative cases, and acceptance support. Where the candidate cites a published
+   standard, verify against that text rather than neighbouring agreement.
 3. Apply `references/grading-rubric.md` only when explicit scoring is requested.
 4. Return the smallest missing proof or exact failing criterion. Never mutate the
    candidate or manufacture evidence.
 
 ## Return and recovery
 
-Return `PASS`, `NEEDS_MORE_EVIDENCE`, or `FAIL` with candidate ref, criteria,
-evidence, findings, blocker, next action, and receiver. `PASS` is terminal.
+Return `PASS`, `NEEDS_MORE_EVIDENCE`, or `FAIL` with verdict, candidate_ref,
+changed_paths, tests, findings, and blocker. `PASS` is terminal.
 `NEEDS_MORE_EVIDENCE` and `FAIL` permit bounded correction. Coordinators
 enforce `max_assurance_rounds` of 1; this role does not redispatch or re-evaluate
 the Journey's repair. The coordinator verifies it deterministically.