@alphazede/bearing-lite 0.1.0 → 0.1.1

package/hooks/com.cursor/hooks.json

@@ -0,0 +1,15 @@
+{
+  "description": "Bearing Lite Cursor mapping. Partial coverage: sessionStart activation, stop closeout. Transition-order and protected-action remain procedural.",
+  "hooks": {
+    "sessionStart": [
+      {
+        "command": "node ./hooks/com.anthropic.claude-code/host.cjs"
+      }
+    ],
+    "stop": [
+      {
+        "command": "node ./hooks/com.anthropic.claude-code/host.cjs"
+      }
+    ]
+  }
+}

package/hooks/hooks.json

@@ -0,0 +1,35 @@
+{
+  "description": "Bearing Lite verified Claude Code and Codex mapping. Partial coverage: activation on SessionStart, closeout on Stop. Transition-order and protected-action remain procedural.",
+  "hooks": {
+    "SessionStart": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node",
+            "args": [
+              "${CLAUDE_PLUGIN_ROOT}/hooks/com.anthropic.claude-code/host.cjs"
+            ],
+            "timeout": 15,
+            "statusMessage": "Bearing Lite activation"
+          }
+        ]
+      }
+    ],
+    "Stop": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node",
+            "args": [
+              "${CLAUDE_PLUGIN_ROOT}/hooks/com.anthropic.claude-code/host.cjs"
+            ],
+            "timeout": 15,
+            "statusMessage": "Bearing Lite closeout"
+          }
+        ]
+      }
+    ]
+  }
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@alphazede/bearing-lite",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Skills-first Agent Plugin for planning, routing, bounded execution, and independent review of repository work—without CLI, MCP, server, or hidden runtime state.",
   "keywords": [
     "agent-plugins",
@@ -11,8 +11,12 @@
     "developer-tools",
     "skills-first",
     "evidence",
-    "code-review"
+    "code-review",
+    "pi-package"
   ],
+  "pi": {
+    "skills": ["./skills"]
+  },
   "author": "William Rumph / AlphaZede",
   "license": "Apache-2.0",
   "repository": {
@@ -31,7 +35,6 @@
     "CODE_OF_CONDUCT.md",
     "CONTRIBUTING.md",
     "SECURITY.md",
-    "LICENSE-APACHE",
-    "guide/migration.md"
+    "LICENSE-APACHE"
   ]
 }

package/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "bearing-lite",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Skills-first portable plugin that routes repository work through the smallest valid planning stages and agent roles, using project Markdown as the only task record.",
   "author": {
     "name": "William Rumph / AlphaZede",
@@ -18,5 +18,37 @@
     "routing",
     "developer-tools",
     "skills-first"
-  ]
+  ],
+  "hooks": {
+    "com.anthropic.claude-code.activation": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    },
+    "com.anthropic.claude-code.closeout": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    },
+    "com.openai.codex.activation": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    },
+    "com.openai.codex.closeout": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    },
+    "com.xai.grok-build.activation": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    },
+    "com.xai.grok-build.closeout": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    },
+    "com.cursor.ide.activation": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    },
+    "com.cursor.ide.closeout": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    },
+    "com.moonshotai.kimi-code.activation": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    },
+    "com.moonshotai.kimi-code.closeout": {
+      "path": "./hooks/com.anthropic.claude-code/host.cjs"
+    }
+  }
 }

package/skills/bearing-lite/SKILL.md

@@ -1,40 +1,52 @@
 ---
 name: bearing-lite
 description: >
-  Bearing Lite router for entry, resume, or unclear next action on repository
-  work. Locates the project plan, next ready task, dependency state, risk, and
-  smallest valid route among planning stages and roles. Activate for bearing
-  lite, start/resume bearing, route the next task, or choose the minimum role
-  path. Do not use for model or provider selection, package publication, deep
-  harness control-room work, or a single already-assigned role packet.
+  Stateful Bearing Lite Router for starting or resuming a Journey, owning the
+  planning conversation, recording visible state, and dispatching fresh nodes.
+  Use only on explicit Bearing Lite invocation. Do not use for ordinary work,
+  an assigned role packet, model selection, implementation, or publication.
 ---
 
 # Bearing Lite Router
 
-Plugin entry skill. Not a work role. Owner Authority remains human-only.
-
-## Inputs
-
-Plan path, next ready task, dependencies, risk, and available native capabilities.
-
-## Select the smallest route
-
-1. Identify the project plan and next ready task. Missing plan fields stay `PROPOSED`.
-2. Invoke only missing planning stages: `repository-fit`, `set-bearings`, `gather-supplies`, `map-the-route`. Reuse valid evidence; do not replay completed stages.
-3. Choose the least costly role route that preserves dependencies and assurance:
-   - **Direct:** Crewmate → author self-check plus coordinator confirmation when `required_assurance` is `none`; otherwise the declared assurance roles. Add Park Ranger only when required or owner-selected. Validator and Park Ranger appear only when declared, owner-selected, or at a mandatory integrated phase gate.
-   - **Single wave:** Explorer → Crewmate packets with the same assurance rule → Surveyor when multi-packet or owner acceptance requires it. Never automatic Validator per packet.
-   - **Expedition:** Navigator → Trail Boss only for concurrent/conflicting waves → Explorer lanes → optional Sub-explorer → Crewmates, with assurance only where `required_assurance`, owner selection, or a mandatory phase gate requires it.
-   - **Long multi-phase:** Delegate Authority only when the owner explicitly delegates across sessions or Navigator replacement.
-4. Leave dormant roles unselected. No placeholder, receipt, or hidden state.
-5. Report honest hook coverage: full, partial, or skills-only procedural checks.
-
-## Never
-
-- Select models, providers, credentials, launchers, or tool routes.
-- Create, import, or interpret `.bearing` state, MCP, CLI, or a scheduler.
-- Expand owner authority, publish, or self-certify as Validator, Park Ranger, or Surveyor.
-
-## State and task record
-
-Task status lives only in the project plan. See `references/task-state.md` and `templates/task.md`. Orientation diagrams may load later under `references/` and `assets/`; text remains authoritative.
+Owner-facing planning controller, never a work role. Explicit invocation is
+consent to begin; do not ask for another start confirmation.
+
+## Inputs and state
+
+Read the request, repository evidence, visible plan artifacts, and global lineup
+when present. The Router alone writes Journey planning state; no `.bearing`,
+CLI, MCP, scheduler, or hidden ledger. Report hook coverage honestly: plugin
+hosts are partial; skill-copy is skills-only.
+
+## Algorithm
+
+1. Say `Gathering Supplies for this Journey.` Detect new versus resumed work.
+2. For a new Journey, recommend one route and ask exactly: `What Journey shall
+   we Embark on—an Explorer Journey or an Expedition?` Explorer fits one bounded
+   wave; Expedition fits dependency-connected waves.
+3. For a resume, state the next incomplete planning stage and continue unless
+   owner intent is missing. Never replay accepted stages.
+4. If `~/.agents/bearing-lite/default-role-lineup.md` is absent, create a
+   proposed copy from `templates/default-role-lineup.md` and ask the owner to
+   fill or confirm it one role at a time. Never infer identity values.
+5. Invoke one missing stage in order: Repository Fit → Set Bearings → Gather
+   Supplies → Map the Route. Give each a fresh session and integrate its return.
+6. Before implementation, display every role's primary/fallback agent or
+   harness, model, reasoning, and active/standby/unused state. Ask `Is this a
+   good lineup for the roles on this Journey?`; never choose those values.
+7. Ask `How often would you like an independent review—per slice, per round, or
+   at the end?` Record `per-slice`, `per-round`, or `at-end` in global config and
+   the Journey snapshot. The owner's Journey answer overrides the default.
+8. Dispatch only ready nodes. Every node gets a fresh session containing the
+   approved baseline, bounded assignment, dependencies, authority, relevant
+   evidence, review cadence, lineup identity, and return schema.
+
+## Return and recovery
+
+Write the node result into visible state and return `READY`, `WAITING_ON`,
+`OWNER_DECISION_REQUIRED`, or `COMPLETE` with evidence and next action. Use only
+the approved fallback after verified primary unavailability; if both fail,
+return to the owner. Allow at most three evidence-changing corrections.
+
+Never implement, self-assure, select models, expand scope, or publish.

package/skills/bearing-lite/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Bearing Lite"
+  short_description: "Route a stateful repository Journey"
+  default_prompt: "Use $bearing-lite to start or resume this Journey, resolve planning one stage at a time, confirm the lineup and review cadence, then dispatch fresh bounded sessions."
+
+policy:
+  allow_implicit_invocation: false

package/skills/bearing-lite/references/peer-synthesis.md

@@ -0,0 +1,21 @@
+# Peer synthesis evidence
+
+Bearing keeps its own skills-first identity, visible Markdown state, authority
+ladder, and assurance separation. The catalog synthesizes behavior; it does not
+copy peer text, runtimes, state stores, or authority assumptions.
+
+| Bearing skill | Strongest compared peer | Behavior retained |
+| --- | --- | --- |
+| Bearing Router | [LangChain subagents](https://docs.langchain.com/oss/python/langchain/multi-agent/subagents) and [handoffs](https://docs.langchain.com/oss/python/langchain/multi-agent/handoffs) | central conversational supervisor, bounded handoff, fresh context |
+| Repository Fit | [Kiro steering](https://kiro.dev/docs/steering/) | verified workspace and explicit global/workspace scope |
+| Set Bearings | [Kiro steering](https://kiro.dev/docs/steering/) | durable human-readable workspace context |
+| Gather Supplies | [Matt Pocock grilling](https://github.com/mattpocock/skills/blob/main/skills/productivity/grilling/SKILL.md) | relentless dependency-ordered interview, one recommended question at a time |
+| Map the Route | [Kiro Quick Spec](https://kiro.dev/docs/specs/quick-spec/) and [GitHub Spec Kit](https://github.com/github/spec-kit/blob/main/workflows/speckit/workflow.yml) | staged requirements/design/tasks and explicit gates |
+| Navigator | LangChain subagents | central sequencing and context isolation |
+| Trail Boss | Spec Kit fan-out/fan-in workflows | conflict-aware wave integration |
+| Explorer | LangChain subagents | bounded worker dispatch and result integration |
+| Sub-Explorer | LangChain subagents | one justified extra context-isolation level |
+| Crewmate | Spec Kit implement step | bounded execution after approved planning |
+| Validator | Spec Kit gate | evidence gate on a stable candidate |
+| Park Ranger | LangChain reviewer subagent | independent defect review with a typed return |
+| Surveyor | Spec Kit review gate | outcome comparison before completion |

package/skills/bearing-lite/references/role-routing.mmd

@@ -1,34 +1,27 @@
 flowchart TD
-    O[Owner Authority] --> R[Bearing Lite Router]
+    O[Owner Authority] <--> R[Stateful Bearing Lite Router]
+    R --> J{Explorer Journey or Expedition?}
     R --> P{Next missing planning stage?}
-    P -->|Repository Fit| PF[Repository Fit]
-    P -->|Set Bearings| SB[Set Bearings]
-    P -->|Gather Supplies| GS[Gather Supplies]
-    P -->|Map the Route| MR[Map the Route]
-    PF --> R
-    SB --> R
-    GS --> R
-    MR --> R
-    P -->|none| Q{Smallest valid route}
-    Q -->|direct| C[Crewmate]
-    Q -->|wave| E[Explorer]
-    Q -->|expedition| N[Navigator]
-    Q -->|long multi-phase| D[Delegate Authority]
-    D --> N
-    N --> TB{Multiple active or conflicting waves?}
-    TB -->|yes| T[Trail Boss]
+    P -->|Repository Fit| PF[Fresh Repository Fit]
+    P -->|Set Bearings| SB[Fresh Set Bearings]
+    P -->|Gather Supplies| GS[Fresh Gather Supplies]
+    P -->|Map the Route| MR[Fresh Map the Route]
+    PF & SB & GS & MR -->|typed return| R
+    R --> L[Owner confirms lineup and review cadence]
+    J -->|Explorer Journey: one packet| C[Fresh Crewmate]
+    J -->|Explorer Journey: one wave| E[Fresh Explorer]
+    J -->|Expedition| N[Fresh Navigator]
+    N --> TB{Concurrent or conflicting waves?}
+    TB -->|yes| T[Fresh Trail Boss]
     TB -->|no| E
     T --> E
-    E --> X{Nested split needed?}
-    X -->|yes| SE[Sub-explorer]
+    E --> X{Two or more proven-independent lanes?}
+    X -->|yes| SE[Fresh Sub-Explorer]
     SE --> C
     X -->|no| C
-    C --> A{required_assurance / next missing?}
-    A -->|none: coordinator confirms| Q
-    A -->|Validator| V[Validator]
-    A -->|Park Ranger| PK[Park Ranger]
-    A -->|Surveyor| S[Surveyor]
-    A -->|owner acceptance| O
-    V --> A
-    PK --> A
-    S --> O
+    C --> A{Selected cadence boundary?}
+    A -->|Validator declared| V[Fresh Validator]
+    A -->|Park Ranger declared| PK[Fresh Park Ranger]
+    A -->|Surveyor declared| S[Fresh Surveyor]
+    A -->|not yet| E
+    V & PK & S -->|typed verdict| R

package/skills/bearing-lite/templates/default-role-lineup.md

@@ -0,0 +1,26 @@
+# Bearing Lite global defaults
+
+Store the user-owned copy at
+`~/.agents/bearing-lite/default-role-lineup.md`. The Router displays it before
+implementation and asks whether it is good for the current Journey. Never fill
+agent, model, or reasoning values on the user's behalf.
+
+```markdown
+review_cadence: <per-slice | per-round | at-end>
+
+| Role | Primary agent/harness | Primary model | Primary reasoning | Fallback agent/harness | Fallback model | Fallback reasoning |
+| --- | --- | --- | --- | --- | --- | --- |
+| Router | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET |
+| Navigator | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET |
+| Trail Boss | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET |
+| Explorer | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET |
+| Sub-Explorer | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET |
+| Crewmate | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET |
+| Validator | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET |
+| Park Ranger | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET |
+| Surveyor | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET | OWNER_TO_SET |
+```
+
+Journey artifacts copy the confirmed values and mark named instances active,
+standby, or unused. Only verified primary unavailability activates its approved
+fallback. If both are unavailable, return `OWNER_DECISION_REQUIRED`.

package/skills/bearing-lite/templates/task.md

@@ -2,6 +2,23 @@
 
 Use one compact Markdown block per task in the project's existing plan or progress document. Omit unused conditional fields. Prefer the project's format; add only missing fields. Do not create a Bearing-owned state file or hidden ledger.
 
+## Journey settings (record before task mapping)
+
+Record these plan-level choices once, above the task blocks:
+
+```markdown
+- journey: <Explorer Journey | Expedition>
+- review_cadence: <per-slice | per-round | at-end>
+- choice_basis: <owner-confirmed recommendation and reason>
+- lineup_snapshot: <named active, standby, and unused role instances>
+```
+
+`review_cadence` controls independent review frequency, not task-level tests or
+author self-checks. Never infer it from `required_assurance` on an individual
+task. `per-round` means after each integrated execution or correction round;
+`at-end` means one review of the final integrated candidate. The Router asks the
+owner to confirm both the applicable lineup and cadence before implementation.
+
 ## Always present
 
 ```markdown

package/skills/crewmate/SKILL.md

@@ -1,37 +1,40 @@
 ---
 name: crewmate
 description: >
-  Implement one approved mutation, execution, or integration packet inside its
-  exact write set with native tools. Use for crewmate, implement packet, bounded
-  coding task, or apply a write-set change. Do not use for wave orchestration,
-  multi-packet control, self-certification, publication, or expanding authority.
+  Implement one approved bounded packet in a fresh session and exact write set.
+  Use for Crewmate, implementation, repair, or integration packets. Do not use
+  for orchestration, planning, independent assurance, publication, destructive
+  action, owner decisions, or unset scope.
 ---
 
 # Crewmate
 
-## Trigger
+Lowest mutation authority and highest hands-on work in the Bearing ladder.
 
-- **Match:** one approved implementation, repair, or integration packet is READY with fixed scope and authority.
-- **Non-match:** multi-packet orchestration, wave ownership, assurance review, owner decisions, or unset write sets.
+## Inputs and match
 
-## Inputs
+- **Inputs:** approved baseline, objective, dependencies, exact write set,
+  authority, acceptance/SEIT rows, commands, cadence, stop rule, return schema.
+- **Match:** one packet is `READY` and every input is fixed.
+- **Non-match:** multi-packet coordination, design gaps, missing authority,
+  assurance, or owner-only action.
 
-Plan path, packet objective, acceptance, allowed paths, commands, stop condition, `required_assurance`, expected handoff.
+## Algorithm
 
-## Responsibility
+1. Start a fresh session and confirm candidate continuity, boundaries, and clean
+   dependency state. Do not infer missing owner choices.
+2. For a verified contract defect, create the smallest failing regression first.
+3. Make the smallest change that satisfies the packet inside the write set.
+4. Run assigned focused commands and author self-checks. Review cadence never
+   removes deterministic testing or grants independent-review identity.
+5. Preserve unrelated work and report every changed path and observed result.
+6. Stop on acceptance, authority boundary, design gap, or exhausted correction.
 
-Smallest honest change in the write set. For verified contract bugs, add a failing regression first, then repair. Run assigned focused commands. Preserve unrelated work.
+## Return and recovery
 
-## Return
+Return `CANDIDATE_READY`, `PARTIAL`, `WAITING_ON`, or
+`OWNER_DECISION_REQUIRED` with plan ref, role, subject, dependencies, scope,
+authority, candidate ref, evidence, blocker, next action, and receiving role.
+Attempts 1–3 require new evidence, hypothesis, or narrower strategy.
 
-Handoff fields: `plan_ref`, `role`, `subject`, `depends_on`, `scope`, `authority`, `outcome`, `evidence`, `blocker`, `next_action`, `receiving_role`.
-
-Outcomes: `CANDIDATE_READY`, `PARTIAL`, `WAITING_ON`, `OWNER_DECISION_REQUIRED`. Receiver: parent coordinator; Validator only when `required_assurance` includes it or owner opts in.
-
-## Independence
-
-Never self-certifies. `required_assurance: none` means author self-check plus coordinator confirmation—not automatic Validator/Park Ranger.
-
-## Correction
-
-Repair evidenced failures inside authority. Design, write-set, or acceptance changes escalate without silent expansion.
+Never expand scope, self-certify as assurance, publish, or hide a failure.

package/skills/explorer/SKILL.md

@@ -1,38 +1,42 @@
 ---
 name: explorer
 description: >
-  Wave-owner orchestration: sequence and dispatch bounded packets inside one
-  approved wave without implementing them. Use for explorer, wave ownership,
-  packet orchestration, or parallel dispatch planning. Do not use for product
-  implementation, multi-wave Trail Boss control, nested Sub-explorer defaulting,
-  or independent assurance of wave output.
+  Own one approved execution wave, dispatching bounded fresh-session packets
+  and integrating their evidence. Use for Explorer Journey, wave orchestration,
+  or parallel packet sequencing. Do not use for implementation, cross-wave
+  Trail Boss work, planning, automatic nesting, or independent assurance.
 ---
 
 # Explorer
 
-## Trigger
+Wave authority. Coordinates more and implements less than Sub-Explorer.
 
-- **Match:** an approved wave contains work packets that need orchestration, sequencing, or parallel dispatch (not the implementation itself).
-- **Non-match:** a single already-bounded implementation packet with no wave orchestration need; multi-wave Trail Boss duty; assurance review.
+## Inputs and match
 
-## Inputs
+- **Inputs:** approved baseline, wave objective, packet graph, dependencies,
+  scope, authority, lineup, review cadence, acceptance, and return schema.
+- **Match:** one wave needs packet sequencing, dispatch, or integration.
+- **Non-match:** one bounded packet needs no orchestration, multiple waves
+  conflict, or assurance alone is requested.
 
-Plan path, wave objective, packets, dependencies, scope, authority, `required_assurance`, expected handoff.
+## Algorithm
 
-## Responsibility
+1. Start fresh and verify wave readiness, exact packet boundaries, dependencies,
+   and approved primary/fallback identities.
+2. Use direct Crewmates by default. Add one Sub-Explorer only for at least two
+   proven-independent lanes where it materially reduces conflict or context.
+3. Give every node a fresh bounded session. Never pass raw conversation history.
+4. Inspect returns against write sets and acceptance; integrate evidence without
+   implementing missing packet work.
+5. Dispatch declared assurance at `per-slice` or after each integrated execution
+   or correction round at `per-round`. At `at-end`, an Explorer Journey reviews
+   its final wave once; an Expedition wave defers assurance to the Navigator's
+   final Journey boundary. Deterministic checks always run.
 
-Issue disjoint Crewmate packets, inspect returns against allowlists, and hand off for coordinator confirmation or required assurance. Never implement or audit the packets itself.
+## Return and recovery
 
-## Return
+Return `READY`, `REROUTED`, `WAITING_ON`, or `OWNER_DECISION_REQUIRED` with
+plan ref, role, subject, dependencies, scope, authority, evidence, blocker, next
+action, and receiver. Reroute only from new evidence; three attempts per packet.
 
-Handoff fields: `plan_ref`, `role`, `subject`, `depends_on`, `scope`, `authority`, `outcome`, `evidence`, `blocker`, `next_action`, `receiving_role`.
-
-Outcomes: `READY`, `REROUTED`, `WAITING_ON`, `OWNER_DECISION_REQUIRED`. Receiver: Sub-explorer, Crewmate, or parent coordinator.
-
-## Independence
-
-Wave owner only. Does not provide Validator, Park Ranger, or Surveyor verdicts for candidates produced under its dispatch when it is author-equivalent.
-
-## Correction
-
-Reroute incomplete packets with new evidence. Authority or design amendments escalate to parent coordinator or Owner Authority.
+Never implement, self-assure, select models, or expand the wave.

package/skills/gather-supplies/SKILL.md

@@ -1,33 +1,45 @@
 ---
 name: gather-supplies
 description: >
-  Resolve only material owner decisions that block a complete plan after the
-  workspace exists. Use for gather supplies, owner decisions, plan-spec
-  assumptions, or blocking scope questions. Do not use for design drafting,
-  implementation, product edits, or replaying settled owner answers.
+  Relentlessly resolve material owner decisions for a Bearing Journey, one
+  dependency-ordered question at a time, until shared understanding is explicit.
+  Use for Gather Supplies or unresolved plan intent. Do not use for discoverable
+  repository facts, design drafting, implementation, or settled decisions.
 ---
 
 # Gather Supplies
 
-Procedural stage. Not a persona.
+Planning node, not a persona or plan-state writer.
 
-## Match / non-match
+## Match and inputs
 
-- **Match:** material open decisions block scope, architecture, security, authority, or acceptance.
-- **Non-match:** decisions already recorded; Map the Route can proceed; pure implementation packets.
+- **Match:** a Journey choice or material scope, behavior, authority, risk, or
+  acceptance decision is unresolved.
+- **Non-match:** evidence can answer it, the owner already decided it, or a work
+  packet is ready.
+- **Inputs:** goal, visible plan state, repository evidence, prior decisions,
+  open decision tree, and return schema.
 
-## Inputs
+## Algorithm
 
-Goal, repository evidence, plan workspace, and prior owner Q&A.
+1. Inspect the repository and available evidence before asking. Never ask the
+   owner for a fact tools can establish.
+2. Select the earliest unresolved decision whose dependencies are satisfied.
+3. Ask exactly one question. Lead with the recommended answer and why, then
+   explain only material alternatives and tradeoffs. Wait for the owner.
+4. Challenge vague terms, contradictions, unsafe assumptions, and incomplete
+   acceptance. A default, probability, or silence is not approval.
+5. Follow the affected dependency branch. Revisit an earlier answer when new
+   evidence conflicts; otherwise do not replay it.
+6. Return each confirmed decision immediately to the Router for recording.
+7. When no material branch remains, summarize the shared interpretation and ask
+   for explicit confirmation that shared understanding has been reached.
 
-## Procedure
+## Return and recovery
 
-1. Ask only material questions; reuse durable prior answers without re-asking.
-2. For each question: recommendation, evidence, options/tradeoffs, affected section, safe default.
-3. Apply completed answers into the validated plan specification only.
-4. Keep requirements testable with stable IDs; record blockers instead of inventing approval.
-5. Exit with zero-to-few bounded questions, applied plan-spec, or `OWNER_DECISION_REQUIRED`.
+Return `DECISION_CONFIRMED`, `SHARED_UNDERSTANDING_CONFIRMED`,
+`NEEDS_EVIDENCE`, or `OWNER_DECISION_REQUIRED` with decision ID, answer,
+rationale, affected requirements, remaining branch, and next action. Stop after
+three evidence-changing attempts on one blocked decision.
 
-## Never
-
-Design the route, draft implementation slices, edit product code, or overwrite a recorded owner answer with a default.
+Never write Journey state, choose for the owner, design, or implement.