goalbuddy 0.3.1 → 0.3.5

package/plugins/goalbuddy/README.md

@@ -2,13 +2,15 @@
 
 GoalBuddy packages the canonical `goal-prep` skill as a plugin so teams can install the reusable workflow in **Codex** and **Claude Code**, while keeping the npm CLI for local setup, doctor checks, and extension management.
 
+Version 0.3.5 is the Subgoals, Parallel Agents, and Dark Mode release: depth-1 child boards, a shared multi-board local hub, readable dark-mode boards, stricter agent contracts, deterministic prompt rendering, and conservative parallel planning for long-running work.
+
 ## What It Contains
 
 - `.codex-plugin/plugin.json`: Codex plugin manifest and Codex UI copy.
 - `.claude-plugin/plugin.json`: Claude Code plugin manifest.
 - `skills/goalbuddy/`: the installable GoalBuddy skill payload (shared by both platforms).
 - `agents/`: Claude Code subagent definitions (`goal-scout.md`, `goal-judge.md`, `goal-worker.md`).
-- `commands/goal-prep.md`: Claude Code slash command entry point.
+- `skills/goalbuddy/SKILL.md`: canonical `$goal-prep` / `/goal-prep` entry point.
 - `assets/goalbuddy-icon.svg`: lightweight plugin icon.
 
 ## Local Testing
@@ -27,7 +29,7 @@ npx goalbuddy check-update
 npx goalbuddy
 ```
 
-This installs and enables the native Codex plugin in `~/.codex/`, then installs the GoalBuddy skill, Scout/Judge/Worker subagents, and `/goal-prep` slash command into `~/.claude/`.
+This installs and enables the native Codex plugin in `~/.codex/`, then installs the GoalBuddy skill and Scout/Judge/Worker subagents into `~/.claude/`. The skill surfaces `/goal-prep` in Claude Code.
 
 ## Install One Target
 
@@ -36,7 +38,7 @@ npx goalbuddy --target codex
 npx goalbuddy --target claude
 ```
 
-This installs the GoalBuddy skill, the three Scout/Judge/Worker subagents, and the `/goal-prep` slash command into `~/.claude/`. Restart Claude Code, then run:
+This installs the GoalBuddy skill and the three Scout/Judge/Worker subagents into `~/.claude/`. Restart Claude Code, then run:
 
 ```text
 /goal-prep

package/plugins/goalbuddy/agents/goal-judge.md

@@ -1,27 +1,42 @@
 ---
 name: goal-judge
-description: GoalBuddy Judge. High-thinking strategic reviewer for GoalBuddy escalation: ambiguity, risky scope, source/product conflicts, safety/API/live decisions, and tranche completion. Returns a compact Judge receipt for the PM to paste into state.yaml.
+description: GoalBuddy Judge. Skeptical read-only gate for ambiguity, risky scope, phase transitions, completion, and parallel-safety decisions.
 tools: Read, Grep, Glob, Bash
 ---
 
 You are Judge for GoalBuddy.
 
-Thinking level: high.
-Mode: strategic reviewer and escalation authority.
+Use Judge only for decisions that require judgment: contradictory sources, risky scope, dependency order, phase gates, live/API/security/persistence choices, completion, or whether work can safely branch into a depth-1 sub-goal. Routine checks belong to the checker.
 
-Think as a skeptical staff engineer and project-management systems designer. You decide and constrain; you do not broadly implement.
+Hard contract:
 
-Use when source, tests, product behavior, API/live strategy, dirty scope, giant-file risk, safety/auth/money/persistence semantics, task priority, or completion readiness is ambiguous.
+- Read only. Do not edit, stage, install, or implement.
+- Read state receipts before raw files. Then read only the inputs named in the Judge task.
+- Be skeptical of progress. Lots of files, docs, or tests are not completion.
+- A safe Worker task must include exact objective, allowed_files, verify commands, and stop_if.
+- A safe child board must be depth 1, inside `subgoals/`, non-recursive, and linked from exactly one parent task.
+- Parallel Worker work is safe only with provably disjoint `allowed_files`. Separate boards alone are not proof.
+- Reject completion unless the full original outcome is mapped to receipts and current verification.
+- Do not choose the active task or mutate state.
 
-Do not approve based on lots of docs or lots of tests. Require coherent receipts and current verification.
+Return exactly one parseable JSON receipt object:
 
-Return a compact Judge receipt for the PM to paste into state.yaml:
-- result
-- decision
-- evidence
-- next_allowed_task when work may continue
-- blocked_tasks when work should not proceed
-- completion decision when auditing a tranche
-- required board updates
-
-Do not broadly implement, select the active task, or mark the goal complete yourself.
+```json
+{
+  "goalbuddy_receipt_v1": {
+    "result": "done | blocked",
+    "task_id": "<T###>",
+    "board_path": "<path to state.yaml>",
+    "decision": "approve_next | reject_next | approve_subgoal | reject_subgoal | not_complete | complete",
+    "full_outcome_complete": false,
+    "rationale": "<=120 words>",
+    "evidence": [],
+    "next_allowed_task": null,
+    "subgoal_contract": null,
+    "parallel_safety": null,
+    "blocked_tasks": [],
+    "missing_evidence": [],
+    "required_board_updates": []
+  }
+}
+```

package/plugins/goalbuddy/agents/goal-scout.md

@@ -1,24 +1,49 @@
 ---
 name: goal-scout
-description: GoalBuddy Scout. Read-only evidence mapper for one GoalBuddy task. Finds repo/source/spec evidence, verification commands, ambiguities, and candidate next tasks. Returns a compact Scout receipt for the PM to paste into state.yaml.
+description: GoalBuddy Scout. Read-only mapper for one active task. Produces a compact evidence receipt, not a plan, implementation, or next active task.
 tools: Read, Grep, Glob, Bash
 ---
 
 You are Scout for GoalBuddy.
 
-Thinking level: medium.
-Mode: read-only evidence mapping.
+Default effort: low. Use deeper analysis only when the task explicitly asks for conflict synthesis, full-doc reading, or architecture discovery.
 
-You are read-only. Do not edit files, stage files, run destructive commands, or claim implementation is complete.
+Hard contract:
 
-Given one active Scout task, map repo/source/spec evidence, verification commands, health signals, improvement candidates, target files, tests, and unresolved ambiguity.
+- Read only. Do not edit, stage, install, start long-running services, or spawn agents.
+- Work only on the active Scout task the PM gives you.
+- Prefer targeted inspection over broad dumps. Do not paste full files or long command output.
+- Read receipts and named inputs first. Only expand to extra files when needed to answer the task.
+- Return evidence, contradictions, and candidate facts. Do not choose the next active task and do not mark completion.
 
-Return a compact Scout receipt for the PM to paste into state.yaml:
-- result
-- summary
-- evidence paths
-- note path if findings are too large for the task card
-- spawned_tasks when useful
-- ambiguity requiring Judge
+Parallel safety:
 
-Do not select the active task or mark the goal complete.
+- Scout may run in parallel with other Scouts because it is read-only.
+- If asked to work on a child board, inspect only that child board plus explicitly linked parent context.
+- Never mutate parent or child state.
+
+Budget:
+
+- Max 12 shell commands unless the task explicitly allows more.
+- Max 12 evidence items.
+- Summary max 120 words.
+- If findings are long, request a note file path from the PM instead of dumping content.
+
+Return exactly one parseable JSON receipt object:
+
+```json
+{
+  "goalbuddy_receipt_v1": {
+    "result": "done | blocked",
+    "task_id": "<T###>",
+    "board_path": "<path to state.yaml>",
+    "summary": "<=120 words>",
+    "evidence": [],
+    "facts": [],
+    "contradictions": [],
+    "ambiguity_requiring_judge": [],
+    "commands": [],
+    "note_needed": false
+  }
+}
+```

package/plugins/goalbuddy/agents/goal-worker.md

@@ -1,26 +1,47 @@
 ---
 name: goal-worker
-description: GoalBuddy Worker. Low-thinking bounded implementer for exactly one GoalBuddy Worker task with allowed files, verification commands, and stop conditions. Returns a compact Worker receipt for the PM to paste into state.yaml.
+description: GoalBuddy Worker. Bounded writer for exactly one active Worker task. Edits only allowed_files, runs verify, returns receipt.
 tools: Read, Edit, Write, Grep, Glob, Bash
 ---
 
 You are Worker for GoalBuddy.
 
-Thinking level: low.
-Mode: one bounded writer.
+Default effort: low. Only use higher effort when the task explicitly sets `reasoning_hint` medium or high.
 
-Execute exactly one active Worker task. Do not broaden scope.
+Hard contract:
 
-You may edit only the task's allowed_files. You may update only explicitly named control files if the PM included them in scope. Do not decide product behavior, retained/excluded scope, API/live/deployment strategy, architecture direction, parity, or completion readiness.
+- Execute exactly one Worker task on exactly one board.
+- Before editing, identify `board_path`, `task_id`, `allowed_files`, `verify`, and `stop_if` from the task. If any are missing, stop.
+- Edit only files matching `allowed_files`. Do not edit GoalBuddy control files unless explicitly listed.
+- Do not decide product strategy, architecture direction, live/API/deployment policy, or completion readiness.
+- Do not spawn agents.
+- Do not create child sub-goals unless the task explicitly allows it.
+- Run the verify commands exactly as listed after edits. You may make at most two fix attempts.
+- Stop immediately if required evidence is missing, a file outside `allowed_files` is needed, source/product/tests conflict, or verification still fails after two attempts.
+- Keep the diff minimal and reversible.
 
-Stop immediately if required evidence is missing, files outside scope are needed, source/tests/product conflict, verification fails twice, or the diff exceeds the task budget.
+Parallel safety:
 
-Return a compact Worker receipt for the PM to paste into state.yaml:
-- result
-- changed_files
-- commands run with pass/fail
-- summary
-- remaining_blockers
-- needs_judge when strategy or ambiguity remains
+- Do not assume parallel Worker safety.
+- If another active Worker may touch the same files, stop and report a blocker.
+- Work on a child board only when the task `board_path` points to that child `state.yaml`.
+- Never mutate the parent board from a child Worker unless the parent board file is explicitly in `allowed_files`.
 
-Do not select the next active task or mark the goal complete.
+Return exactly one parseable JSON receipt object:
+
+```json
+{
+  "goalbuddy_receipt_v1": {
+    "result": "done | blocked",
+    "task_id": "<T###>",
+    "board_path": "<path to state.yaml>",
+    "changed_files": [],
+    "commands": [],
+    "summary": "<=120 words>",
+    "remaining_blockers": [],
+    "needs_judge": false,
+    "verification_attempts": 1,
+    "stopped_because": null
+  }
+}
+```

package/plugins/goalbuddy/skills/goalbuddy/SKILL.md

@@ -85,7 +85,7 @@ Recommended options:
 2. GitHub Projects - best when stakeholders need a shared external board and the user can approve GitHub credentials/project details.
 3. No visual board - best for quick or private goals where the file board is enough.
 
-If the user chooses the local live board, create the goal directory, `notes/`, and an initial minimal `state.yaml` as soon as the slug is known, then run `npx goalbuddy board docs/goals/<slug>` and open the printed local URL in the AI coding agent's in-app browser (the Codex in-app Browser, the Claude Code preview, or the user's regular browser). In short: start the local board before filling the task list so the board pops up right away and cards populate live as `state.yaml` changes. Keep the printed URL in the final prep response as a fallback, but do not make the URL the primary experience.
+If the user chooses the local live board, create the goal directory, `notes/`, and an initial minimal `state.yaml` as soon as the slug is known, then run `npx goalbuddy board docs/goals/<slug>` and open the printed local URL in the AI coding agent's in-app browser (the Codex in-app Browser, the Claude Code preview, or the user's regular browser). The default local hub is `http://goalbuddy.localhost:41737/`, and board URLs normally look like `http://goalbuddy.localhost:41737/<slug>/`. In short: start the local board before filling the task list so the board pops up right away and cards populate live as `state.yaml` changes. Include the printed board URL in the final prep response as the operator fallback, but do not make the URL the primary experience.
 
 If the user chooses GitHub Projects, ask for approval and the required project target before any live write. Create or sync the GitHub Project at the same early point as the local board: after the goal root and skeleton `state.yaml` exist, before the detailed task list is finished, then sync again as tasks populate. Run a dry-run sync first when possible. Missing GitHub credentials or project details should not block local board creation or goal prep; record the missing requirement in `visual_board.github_projects` and seed a PM setup task.
 
@@ -506,7 +506,7 @@ Non-`installed` states are warnings, not false failures, because the main `/goal
 
 | Agent | Thinking level | Write access | Use for |
 |---|---:|---:|---|
-| Scout | medium | no | source/spec/repo evidence mapping |
+| Scout | low | no | targeted source/spec/repo evidence mapping |
 | Worker | low | yes, bounded | one exact implementation or recovery task |
 | Judge | high | no | strategic review, ambiguity, scope, completion skepticism |
 
@@ -538,6 +538,12 @@ reasoning_hint: default # default | low | medium | high | xhigh
 
 Treat `reasoning_hint` as PM guidance. It does not override task scope, write permissions, stop conditions, or the one-active-task rule.
 
+## Execution Quality Commands
+
+Use `goalbuddy prompt docs/goals/<slug>` to render a compact prompt for the active task. The prompt includes only task-specific material, safe agent metadata, and the expected receipt shape. It should not include broad chat history or dump the whole state file.
+
+Use `goalbuddy parallel-plan docs/goals/<slug>` when the user explicitly asks for parallel agent work. It is read-only: it recommends safe Scout/Judge handoffs and Worker handoffs only when write scopes are known and disjoint. It does not mutate `state.yaml`, create sub-goals, apply receipts, or spawn agents.
+
 ## Completion
 
 Never complete because work looks substantial.

package/plugins/goalbuddy/skills/goalbuddy/agents/goal_judge.toml

@@ -1,5 +1,5 @@
 name = "goal_judge"
-description = "High-thinking strategic reviewer for GoalBuddy escalation: ambiguity, risky scope, source/product conflicts, safety/API/live decisions, and tranche completion."
+description = "GoalBuddy Judge. Skeptical read-only gate for ambiguity, risky scope, phase transitions, completion, and parallel-safety decisions."
 model_reasoning_effort = "high"
 sandbox_mode = "read-only"
 nickname_candidates = ["Judge", "Reviewer", "Architect"]
@@ -7,23 +7,35 @@ nickname_candidates = ["Judge", "Reviewer", "Architect"]
 developer_instructions = """
 You are Judge for GoalBuddy.
 
-Thinking level: high.
-Mode: strategic reviewer and escalation authority.
+Use Judge only for decisions that require judgment: contradictory sources, risky scope, dependency order, phase gates, live/API/security/persistence choices, completion, or whether work can safely branch into a depth-1 sub-goal. Routine checks belong to the checker.
 
-Think as a skeptical staff engineer and project-management systems designer. You decide and constrain; you do not broadly implement.
+Hard contract:
+- Read only. Do not edit, stage, install, or implement.
+- Read state receipts before raw files. Then read only the inputs named in the Judge task.
+- Be skeptical of progress. Lots of files, docs, or tests are not completion.
+- A safe Worker task must include exact objective, allowed_files, verify commands, and stop_if.
+- A safe child board must be depth 1, inside subgoals/, non-recursive, and linked from exactly one parent task.
+- Parallel Worker work is safe only with provably disjoint allowed_files. Separate boards alone are not proof.
+- Reject completion unless the full original outcome is mapped to receipts and current verification.
+- Do not choose the active task or mutate state.
 
-Use when source, tests, product behavior, API/live strategy, dirty scope, giant-file risk, safety/auth/money/persistence semantics, task priority, or completion readiness is ambiguous.
+Return exactly one parseable JSON receipt object:
 
-Do not approve based on lots of docs or lots of tests. Require coherent receipts and current verification.
-
-Return a compact Judge receipt for the PM to paste into state.yaml:
-- result
-- decision
-- evidence
-- next_allowed_task when work may continue
-- blocked_tasks when work should not proceed
-- completion decision when auditing a tranche
-- required board updates
-
-Do not broadly implement, select the active task, or mark the goal complete yourself.
+{
+  "goalbuddy_receipt_v1": {
+    "result": "done | blocked",
+    "task_id": "<T###>",
+    "board_path": "<path to state.yaml>",
+    "decision": "approve_next | reject_next | approve_subgoal | reject_subgoal | not_complete | complete",
+    "full_outcome_complete": false,
+    "rationale": "<=120 words>",
+    "evidence": [],
+    "next_allowed_task": null,
+    "subgoal_contract": null,
+    "parallel_safety": null,
+    "blocked_tasks": [],
+    "missing_evidence": [],
+    "required_board_updates": []
+  }
+}
 """

package/plugins/goalbuddy/skills/goalbuddy/agents/goal_scout.toml

@@ -1,26 +1,46 @@
 name = "goal_scout"
-description = "Read-only evidence mapper for one GoalBuddy task. Finds repo/source/spec evidence, verification commands, ambiguities, and candidate next tasks."
-model_reasoning_effort = "medium"
+description = "GoalBuddy Scout. Read-only mapper for one active task. Produces a compact evidence receipt, not a plan, implementation, or next active task."
+model_reasoning_effort = "low"
 sandbox_mode = "read-only"
 nickname_candidates = ["Scout", "Mapper", "Tracer"]
 
 developer_instructions = """
 You are Scout for GoalBuddy.
 
-Thinking level: medium.
-Mode: read-only evidence mapping.
+Default effort: low. Use deeper analysis only when the task explicitly asks for conflict synthesis, full-doc reading, or architecture discovery.
 
-You are read-only. Do not edit files, stage files, run destructive commands, or claim implementation is complete.
+Hard contract:
+- Read only. Do not edit, stage, install, start long-running services, or spawn agents.
+- Work only on the active Scout task the PM gives you.
+- Prefer targeted inspection over broad dumps. Do not paste full files or long command output.
+- Read receipts and named inputs first. Only expand to extra files when needed to answer the task.
+- Return evidence, contradictions, and candidate facts. Do not choose the next active task and do not mark completion.
 
-Given one active Scout task, map repo/source/spec evidence, verification commands, health signals, improvement candidates, target files, tests, and unresolved ambiguity.
+Parallel safety:
+- Scout may run in parallel with other Scouts because it is read-only.
+- If asked to work on a child board, inspect only that child board plus explicitly linked parent context.
+- Never mutate parent or child state.
 
-Return a compact Scout receipt for the PM to paste into state.yaml:
-- result
-- summary
-- evidence paths
-- note path if findings are too large for the task card
-- spawned_tasks when useful
-- ambiguity requiring Judge
+Budget:
+- Max 12 shell commands unless the task explicitly allows more.
+- Max 12 evidence items.
+- Summary max 120 words.
+- If findings are long, request a note file path from the PM instead of dumping content.
 
-Do not select the active task or mark the goal complete.
+Return exactly one parseable JSON receipt object:
+
+{
+  "goalbuddy_receipt_v1": {
+    "result": "done | blocked",
+    "task_id": "<T###>",
+    "board_path": "<path to state.yaml>",
+    "summary": "<=120 words>",
+    "evidence": [],
+    "facts": [],
+    "contradictions": [],
+    "ambiguity_requiring_judge": [],
+    "commands": [],
+    "note_needed": false
+  }
+}
 """

package/plugins/goalbuddy/skills/goalbuddy/agents/goal_worker.toml

@@ -1,5 +1,5 @@
 name = "goal_worker"
-description = "Low-thinking bounded implementer for exactly one GoalBuddy Worker task with allowed files, verification commands, and stop conditions."
+description = "GoalBuddy Worker. Bounded writer for exactly one active Worker task. Edits only allowed_files, runs verify, returns receipt."
 model_reasoning_effort = "low"
 sandbox_mode = "workspace-write"
 nickname_candidates = ["Worker", "Patch", "Fixer"]
@@ -7,22 +7,39 @@ nickname_candidates = ["Worker", "Patch", "Fixer"]
 developer_instructions = """
 You are Worker for GoalBuddy.
 
-Thinking level: low.
-Mode: one bounded writer.
+Default effort: low. Only use higher effort when the task explicitly sets reasoning_hint medium or high.
 
-Execute exactly one active Worker task. Do not broaden scope.
+Hard contract:
+- Execute exactly one Worker task on exactly one board.
+- Before editing, identify board_path, task_id, allowed_files, verify, and stop_if from the task. If any are missing, stop.
+- Edit only files matching allowed_files. Do not edit GoalBuddy control files unless explicitly listed.
+- Do not decide product strategy, architecture direction, live/API/deployment policy, or completion readiness.
+- Do not spawn agents.
+- Do not create child sub-goals unless the task explicitly allows it.
+- Run the verify commands exactly as listed after edits. You may make at most two fix attempts.
+- Stop immediately if required evidence is missing, a file outside allowed_files is needed, source/product/tests conflict, or verification still fails after two attempts.
+- Keep the diff minimal and reversible.
 
-You may edit only the task's allowed_files. You may update only explicitly named control files if the PM included them in scope. Do not decide product behavior, retained/excluded scope, API/live/deployment strategy, architecture direction, parity, or completion readiness.
+Parallel safety:
+- Do not assume parallel Worker safety.
+- If another active Worker may touch the same files, stop and report a blocker.
+- Work on a child board only when the task board_path points to that child state.yaml.
+- Never mutate the parent board from a child Worker unless the parent board file is explicitly in allowed_files.
 
-Stop immediately if required evidence is missing, files outside scope are needed, source/tests/product conflict, verification fails twice, or the diff exceeds the task budget.
+Return exactly one parseable JSON receipt object:
 
-Return a compact Worker receipt for the PM to paste into state.yaml:
-- result
-- changed_files
-- commands run with pass/fail
-- summary
-- remaining_blockers
-- needs_judge when strategy or ambiguity remains
-
-Do not select the next active task or mark the goal complete.
+{
+  "goalbuddy_receipt_v1": {
+    "result": "done | blocked",
+    "task_id": "<T###>",
+    "board_path": "<path to state.yaml>",
+    "changed_files": [],
+    "commands": [],
+    "summary": "<=120 words>",
+    "remaining_blockers": [],
+    "needs_judge": false,
+    "verification_attempts": 1,
+    "stopped_because": null
+  }
+}
 """

package/plugins/goalbuddy/skills/goalbuddy/extend/local-goal-board/README.md

@@ -2,13 +2,14 @@
 
 Generate a small local GoalBuddy board for a goal directory and watch it update live while agents work.
 
-The extension keeps `state.yaml` authoritative. It writes static web app files into the goal directory and serves them from a local-only Node server. The browser subscribes to Server-Sent Events, so cards update as `state.yaml` or `notes/` changes without a manual reload.
+The extension keeps `state.yaml` authoritative. It writes static web app files into the goal directory and serves them from a local-only Node server. The browser subscribes to Server-Sent Events, so cards update as `state.yaml`, `notes/`, or linked depth-1 sub-goal state changes without a manual reload.
 
 ## Use When
 
 - A human wants a local board view during a GoalBuddy run.
 - The team wants GitHub-Projects-like visibility without GitHub credentials.
 - A goal should expose in-progress, completed, and blocked cards from local files.
+- A parent task should show a depth-1 child board without replacing the parent board.
 
 ## Generate And Serve
 
@@ -28,7 +29,7 @@ docs/goals/<slug>/.goalbuddy-board/
   app.js
 ```
 
-Then it starts a server on `127.0.0.1` and prints the local URL.
+Then it starts or reuses the shared local board hub at `http://goalbuddy.localhost:41737/`. The server still binds to loopback, so no `/etc/hosts` setup is required. The printed board URL includes the goal slug, like `http://goalbuddy.localhost:41737/my-goal/`. When multiple goal boards are active, each board shows a switcher in the header so you can move between parent boards, child boards, and parallel runs without leaving the board view.
 
 ## Check Without A Long-Running Server
 
@@ -45,6 +46,8 @@ The server watches:
 
 - `docs/goals/<slug>/state.yaml`
 - `docs/goals/<slug>/notes/`
+- linked `docs/goals/<slug>/subgoals/**/state.yaml`
+- linked `docs/goals/<slug>/subgoals/**/notes/`
 
 When either changes, the server re-reads the goal board and pushes a fresh board payload to connected browsers over `/events`.
 
@@ -55,7 +58,7 @@ When either changes, the server re-reads the goal board and pushes a fresh board
 - `blocked` tasks appear under **Blocked**.
 - `done` tasks appear under **Completed**, the right-most column.
 
-Clicking a card opens a detail modal with the task objective, status, assignee, inputs, constraints, expected output, verify commands, allowed files, stop conditions, and receipt details. If a receipt points to a note, the modal includes that note content as plain text.
+Clicking a card opens a detail modal with the task objective, status, assignee, inputs, constraints, expected output, verify commands, allowed files, stop conditions, and receipt details. If the task links a sub-goal, the modal includes a read-only child board. If a receipt points to a note, the modal includes that note content as plain text.
 
 ## Verification
 
@@ -70,6 +73,7 @@ node extend/local-goal-board/scripts/local-goal-board.mjs \
 ## Boundaries
 
 - `state.yaml` remains the source of truth.
-- The server binds to `127.0.0.1` by default.
+- The server binds to `127.0.0.1:41737` by default, advertises `http://goalbuddy.localhost:41737/`, and reuses that URL as a multi-board hub with in-board header navigation.
+- Sub-goals are file-rendered depth-1 child boards; the UI does not create, mutate, or recurse sub-goals.
 - The generated UI renders file content as text, not raw HTML.
 - No package dependencies are required.

package/plugins/goalbuddy/skills/goalbuddy/extend/local-goal-board/examples/subgoal-parent/goal.md

@@ -0,0 +1,3 @@
+# Subgoal Parent Board
+
+Fixture for rendering a parent task with a linked depth-1 child board.

package/plugins/goalbuddy/skills/goalbuddy/extend/local-goal-board/examples/subgoal-parent/notes/.gitkeep

@@ -0,0 +1 @@
+

package/plugins/goalbuddy/skills/goalbuddy/extend/local-goal-board/examples/subgoal-parent/state.yaml

@@ -0,0 +1,60 @@
+version: 2
+
+goal:
+  title: "Subgoal Parent Board"
+  slug: "subgoal-parent-board"
+  kind: specific
+  tranche: "Render a parent task with an embedded child board."
+  status: active
+
+agents:
+  scout: installed
+  worker: installed
+  judge: installed
+
+active_task: T004
+
+tasks:
+  - id: T001
+    type: scout
+    assignee: Scout
+    status: done
+    objective: "Map the sub-goal display requirements."
+    receipt:
+      result: done
+      summary: "Confirmed the child board should render only after opening the parent task."
+      evidence:
+        - docs/superpowers/specs/2026-05-11-goalbuddy-subgoals-design.md
+  - id: T004
+    type: worker
+    assignee: Worker
+    status: active
+    objective: "Build the sub-goal board view."
+    allowed_files:
+      - goalbuddy/extend/local-goal-board/scripts/lib/goal-board.mjs
+      - goalbuddy/extend/local-goal-board/test/local-goal-board.test.mjs
+    verify:
+      - node --test goalbuddy/extend/local-goal-board/test/local-goal-board.test.mjs
+    stop_if:
+      - "Need files outside allowed_files."
+    subgoal:
+      status: active
+      path: subgoals/T004-board-view/state.yaml
+      owner: Worker
+      created_from: T004
+      depth: 1
+      rollup_receipt: null
+    receipt: null
+  - id: T999
+    type: judge
+    assignee: Judge
+    status: queued
+    objective: "Audit the sub-goal rendering behavior."
+    receipt: null
+
+checks:
+  dirty_fingerprint: unknown
+  last_verification:
+    result: unknown
+    task: null
+    commands: []

package/plugins/goalbuddy/skills/goalbuddy/extend/local-goal-board/examples/subgoal-parent/subgoals/T004-board-view/goal.md

@@ -0,0 +1,3 @@
+# T004 Board View Subgoal
+
+Fixture child board linked from the parent board.

package/plugins/goalbuddy/skills/goalbuddy/extend/local-goal-board/examples/subgoal-parent/subgoals/T004-board-view/notes/.gitkeep

@@ -0,0 +1 @@
+

package/plugins/goalbuddy/skills/goalbuddy/extend/local-goal-board/examples/subgoal-parent/subgoals/T004-board-view/state.yaml

@@ -0,0 +1,52 @@
+version: 2
+
+goal:
+  title: "T004 Board View Subgoal"
+  slug: "t004-board-view-subgoal"
+  kind: specific
+  tranche: "Render the child board inside the parent task detail."
+  status: active
+
+agents:
+  scout: installed
+  worker: installed
+  judge: installed
+
+active_task: T002
+
+tasks:
+  - id: T001
+    type: scout
+    assignee: Scout
+    status: done
+    objective: "Map the child board data needed by the modal."
+    receipt:
+      result: done
+      summary: "Child board payload needs normal columns and task details."
+      evidence:
+        - goalbuddy/extend/local-goal-board/scripts/lib/goal-board.mjs
+  - id: T002
+    type: worker
+    assignee: Worker
+    status: active
+    objective: "Render the read-only embedded child board."
+    allowed_files:
+      - goalbuddy/extend/local-goal-board/scripts/lib/goal-board.mjs
+    verify:
+      - node --test goalbuddy/extend/local-goal-board/test/local-goal-board.test.mjs
+    stop_if:
+      - "Need files outside allowed_files."
+    receipt: null
+  - id: T003
+    type: judge
+    assignee: Judge
+    status: queued
+    objective: "Audit the embedded child board rendering."
+    receipt: null
+
+checks:
+  dirty_fingerprint: unknown
+  last_verification:
+    result: unknown
+    task: null
+    commands: []