goalbuddy 0.3.5 → 0.3.6

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). 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 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 an actual clickable Markdown link, for example `[Open GoalBuddy board](http://goalbuddy.localhost:41737/<slug>/)`. Do not put the board URL only in a code block, quote, HTML comment, or prose that the UI cannot click.
 
 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.
 
@@ -203,15 +203,31 @@ Planning, Scout findings, Judge decisions, and a queued Worker task are not term
 For execution goals, the default run is continuous:
 
 ```text
-Discover enough evidence, choose a safe implementation slice, implement it, verify it, audit it, then immediately choose and execute the next safe slice until the full original outcome is complete.
+Discover enough evidence, choose the largest reversible local work package, implement it, verify it, review only at risk or phase boundaries, then immediately choose and execute the next work package until the full original outcome is complete.
 ```
 
 If the first `/goal` run reaches a Judge decision that names a safe Worker task with `allowed_files`, `verify`, and `stop_if`, the PM should activate that Worker and continue in the same run unless a stop condition applies.
 
-After a verified Worker slice and audit, do not mark the thread goal complete merely because that slice passed. A slice audit is a checkpoint. For broad automation or product goals, continue by reopening or advancing the board to the next safe Worker task until the full owner outcome is complete.
+After a verified Worker package, do not mark the thread goal complete merely because that package passed. For broad automation or product goals, continue by reopening or advancing the board to the next safe Worker package until the full owner outcome is complete.
 
 Missing owner input, credentials, production access, destructive-operation permission, or policy decisions are blockers for specific tasks, not stopping conditions for the whole goal. When a slice hits one of those blockers, mark that exact task blocked with a receipt, create a safe follow-up or workaround task, and keep doing local, non-destructive work that advances the full outcome.
 
+## Slice Sizing Policy
+
+A good task is the largest safe useful slice.
+
+Small is not the goal. Useful is the goal.
+
+Safe does not mean small. Safe means bounded, explicit, verified, and reversible.
+
+A good Worker task usually produces a working screen, a working API path, a working data pipeline step, a working backend vertical slice, a real bug fix, or a milestone review. A bad Worker task is one more tiny helper, projection function, contract file, read-only proof, or doc note unless that tiny task is truly blocking progress.
+
+Judge picks the largest safe useful next slice. Worker completes the whole assigned slice. Judge reviews the whole slice.
+
+After two tiny tasks in a row, PM or Judge should reorient the board. If a demo milestone is complete, the next task should move toward the next real milestone.
+
+Tiny tasks are allowed when the failure is isolated, the risk is high, the scope is unknown, or the tiny task unlocks a larger slice. Tiny tasks are bad when they keep happening, do not change behavior, only add wrappers/contracts/proof files, or avoid the real milestone.
+
 ## When To Use
 
 Use this skill for goals that are broad, multi-hour, ambiguous, high-risk, already planned, already stale, already red, or likely to need Scout/Judge/Worker delegation.
@@ -267,7 +283,7 @@ What counts as enough for the current tranche?
 Avoid forever goals. A broad goal should define an execution tranche, for example:
 
 ```text
-Discover the highest-leverage local improvements, complete successive safe verified implementation slices, audit each slice against the original user outcome, and keep advancing until the full outcome is complete.
+Discover the highest-leverage local improvements, complete successive safe verified work packages, review only at risk or phase boundaries, and keep advancing until the full outcome is complete.
 ```
 
 ## Board
@@ -390,8 +406,9 @@ Judge receipt:
 ```yaml
 receipt:
   result: done
-  decision: "Do router coverage first; defer auth flake because it is not reproducible locally."
-  next_allowed_task: T004
+  decision: "approved"
+  full_outcome_complete: false
+  rationale: "Router coverage is verified; continue with the next PM-selected work package."
   blocked_tasks:
     - T005
 ```
@@ -440,7 +457,7 @@ Blocked tasks do not necessarily block the goal. The PM should keep doing safe l
 
 - create a Scout task to improve evidence;
 - create a Judge task to resolve ambiguity;
-- create a Worker task for a smaller safe slice;
+- create a Worker task for the largest reversible local work package that can proceed;
 - write or update a note for handoff;
 - update receipts and verification freshness.
 
@@ -471,9 +488,11 @@ After a task completes, immediately write its receipt and select the next active
 
 - a final audit proves the full original owner outcome is complete.
 
-Do not stop at "ready for implementation" when a safe Worker task exists. Activate the Worker, execute it, verify it, and then run the audit task.
+Do not stop at "ready for implementation" when a safe Worker task exists. Activate the Worker, execute it, verify it, and keep going.
 
-Do not stop after one verified implementation slice when the broader owner outcome still has safe local follow-up slices. Treat a slice audit as permission to advance the board, not as permission to finish, unless the audit explicitly proves the full original outcome is complete.
+Do not stop after one verified work package when the broader owner outcome still has safe local follow-up work. Advance the board to the next work package unless a risk boundary or final audit is due.
+
+Do not create a Judge task after every Worker by default. Use Judge only for phase boundaries, high-risk changes, unclear scope, rejected verification, or final completion. Repeated same-shape work belongs in one Worker package.
 
 Do not stop because the current slice needs owner input, credentials, production access, destructive operations, or policy decisions. Mark that slice blocked, spawn or activate the smallest safe local task that can proceed around the blocker, and continue.
 
@@ -507,8 +526,8 @@ Non-`installed` states are warnings, not false failures, because the main `/goal
 | Agent | Thinking level | Write access | Use for |
 |---|---:|---:|---|
 | 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 |
+| Worker | medium | yes, bounded | one coherent bounded useful slice |
+| Judge | high | no | phase/risk/final review, ambiguity, scope, completion skepticism |
 
 A task's `assignee` determines the agent. The task card is the order. The receipt is the return format.
 
@@ -540,7 +559,9 @@ Treat `reasoning_hint` as PM guidance. It does not override task scope, write pe
 
 ## 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 prompt docs/goals/<slug>` to render a compact prompt for the active task. The prompt includes only task-specific material, safe agent metadata, continuation warnings, and the expected receipt shape. It should not include broad chat history or dump the whole state file.
+
+When dispatching Codex subagents from a GoalBuddy prompt, the `required_spawn_agent_type` is mandatory. Use that exact `spawn_agent` `agent_type` (`goal_scout`, `goal_worker`, or `goal_judge`). Do not substitute generic `scout`, `worker`, or `judge` agents; if the required GoalBuddy agent is unavailable, stop spawning and continue as PM fallback or run `npx goalbuddy agents`/`npx goalbuddy install`. After one `wait_agent` timeout with no visible allowed-file changes, stop waiting, record the timeout, and recover deterministically instead of waiting forever.
 
 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.
 
@@ -552,7 +573,7 @@ Completion is a Judge or PM audit task. The goal is done only when a final done
 
 For execution goals, completion also requires implementation evidence. A final audit cannot call the goal done if the only completed work is planning, discovery, or task selection.
 
-For continuous execution goals, the final audit receipt must include `full_outcome_complete: true`. If the receipt only proves that the current slice or tranche is complete, keep the goal active and queue or activate the next safe Worker/Judge/PM task.
+For continuous execution goals, the final audit receipt must include `full_outcome_complete: true`. If the receipt only proves that the current work package or tranche is complete, keep the goal active and queue or activate the next safe Worker/PM task. Add a Judge only when the next decision is a phase, risk, ambiguity, rejected verification, or final completion review.
 
 Queued or active Worker tasks block `goal.status: done`. If a Worker is no longer required, mark it blocked with a receipt explaining why, remove it during PM board maintenance, or replace it with the actual required Worker task before completion.
 

package/plugins/goalbuddy/skills/goalbuddy/agents/README.md

@@ -13,7 +13,7 @@ This directory contains skill metadata and bundled agent definitions for Codex a
 | Agent | Codex file | Claude Code file | Reasoning effort | Write scope |
 |---|---|---|---:|---|
 | Scout | `goal_scout.toml` | `goal-scout.md` | medium | read-only |
-| Worker | `goal_worker.toml` | `goal-worker.md` | low | workspace-write |
+| Worker | `goal_worker.toml` | `goal-worker.md` | medium | workspace-write |
 | Judge | `goal_judge.toml` | `goal-judge.md` | high | read-only |
 
 ## Recommended Codex Config

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

@@ -13,11 +13,16 @@ 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 Worker package must include objective, allowed_files, verify commands, and stop_if, and should cover the largest reversible local work package at that boundary.
+- Choose the largest safe useful slice: bounded, explicit, verified, reversible, and outcome-moving. Safety does not mean tiny.
+- Judge a whole useful slice, not one helper at a time.
+- Detect micro-slice loops. Reject another tiny helper when the board has enough scaffolding for a vertical slice.
+- Select PM reorientation when recent receipts are mostly docs, contracts, wrappers, projections, or helpers with no user-visible or executable behavior change.
+- Prefer milestone reviews over helper reviews.
 - 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 generate routine next tasks, choose the active task, or mutate state. The PM owns continuation after your review.
 
 Return exactly one parseable JSON receipt object:
 
@@ -26,11 +31,10 @@ Return exactly one parseable JSON receipt object:
     "result": "done | blocked",
     "task_id": "<T###>",
     "board_path": "<path to state.yaml>",
-    "decision": "approve_next | reject_next | approve_subgoal | reject_subgoal | not_complete | complete",
+    "decision": "approved | rejected | 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": [],

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

@@ -1,13 +1,13 @@
 name = "goal_worker"
-description = "GoalBuddy Worker. Bounded writer for exactly one active Worker task. Edits only allowed_files, runs verify, returns receipt."
-model_reasoning_effort = "low"
+description = "GoalBuddy Worker. Bounded writer for one coherent reversible Worker work package. Edits only allowed_files, runs verify, returns receipt."
+model_reasoning_effort = "medium"
 sandbox_mode = "workspace-write"
 nickname_candidates = ["Worker", "Patch", "Fixer"]
 
 developer_instructions = """
 You are Worker for GoalBuddy.
 
-Default effort: low. Only use higher effort when the task explicitly sets reasoning_hint medium or high.
+Default effort: medium for implementation tasks. Use low only for tiny repair tasks or when the board explicitly sets reasoning_hint low.
 
 Hard contract:
 - Execute exactly one Worker task on exactly one board.
@@ -18,7 +18,11 @@ Hard contract:
 - 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.
+- Do not request a Judge just because the package is done. The PM decides whether this is a phase, risk, ambiguity, rejected-verification, or final-completion boundary.
+- Keep the diff coherent, bounded, and reversible. Do not shrink the assigned work below the largest safe useful slice.
+- Complete the whole assigned slice. Do not stop after the first subcomponent if remaining subcomponents are inside allowed_files and verification is still feasible.
+- If the task asks for a vertical slice, complete the vertical slice.
+- Do not under-implement to avoid verification.
 
 Parallel safety:
 - Do not assume parallel Worker safety.
@@ -37,7 +41,6 @@ Return exactly one parseable JSON receipt object:
     "commands": [],
     "summary": "<=120 words>",
     "remaining_blockers": [],
-    "needs_judge": false,
     "verification_attempts": 1,
     "stopped_because": null
   }

package/plugins/goalbuddy/skills/goalbuddy/extend/local-goal-board/scripts/lib/goal-board.mjs

@@ -110,7 +110,7 @@ export function normalizeTask(task, index) {
   }
 
   const id = cleanText(task.id);
-  const status = cleanText(task.status);
+  const status = normalizeTaskStatus(task.status);
   if (!id) throw new GoalBoardError(`Task ${index + 1} is missing id.`);
   if (!VALID_STATUSES.has(status)) {
     throw new GoalBoardError(`Task ${id} has unsupported status "${status}".`);
@@ -332,14 +332,222 @@ function cleanText(value) {
   return String(value ?? "").trim();
 }
 
+function normalizeTaskStatus(value) {
+  const status = cleanText(value);
+  if (status === "complete" || status === "completed") return "done";
+  return status;
+}
+
 export function parseGoalStateText(text) {
-  const lines = tokenizeYaml(text);
-  if (!lines.length) throw new GoalBoardError("Goal state is empty.");
-  const [value, nextIndex] = parseBlock(lines, 0, lines[0].indent);
-  if (nextIndex < lines.length) {
-    throw new GoalBoardError(`Could not parse line ${lines[nextIndex].number}.`);
+  try {
+    const lines = tokenizeYaml(text);
+    if (!lines.length) throw new GoalBoardError("Goal state is empty.");
+    const [value, nextIndex] = parseBlock(lines, 0, lines[0].indent);
+    if (nextIndex < lines.length) {
+      throw new GoalBoardError(`Could not parse line ${lines[nextIndex].number}.`);
+    }
+    return value;
+  } catch (error) {
+    if (error instanceof GoalBoardError && canRecoverBoardSubset(error)) {
+      return parseGoalBoardSubset(text);
+    }
+    throw error;
   }
-  return value;
+}
+
+function canRecoverBoardSubset(error) {
+  return /Could not parse line|Expected key\/value pair|Expected mapping|Block scalar YAML/.test(error.message);
+}
+
+function parseGoalBoardSubset(text) {
+  const tasks = parseTaskSubsets(text);
+  if (!tasks.length) throw new GoalBoardError("Missing non-empty tasks list.");
+  return {
+    version: parseYamlScalar(findTopLevelScalar(text, "version") || "2"),
+    goal: {
+      title: parseYamlScalar(findNestedScalar(text, "goal", "title") || "Untitled goal"),
+      slug: parseYamlScalar(findNestedScalar(text, "goal", "slug") || "untitled-goal"),
+      kind: parseYamlScalar(findNestedScalar(text, "goal", "kind") || "open_ended"),
+      tranche: parseYamlScalar(findNestedScalar(text, "goal", "tranche") || ""),
+      status: parseYamlScalar(findNestedScalar(text, "goal", "status") || "active"),
+    },
+    active_task: parseYamlScalar(findTopLevelScalar(text, "active_task") || ""),
+    tasks,
+  };
+}
+
+function parseTaskSubsets(text) {
+  const tasksText = findTopLevelSection(text, "tasks");
+  if (!tasksText) return [];
+  const taskBlocks = [];
+  let current = [];
+  for (const line of tasksText.split("\n")) {
+    if (/^  - id:/.test(line)) {
+      if (current.length) taskBlocks.push(current.join("\n"));
+      current = [line];
+    } else if (current.length) {
+      current.push(line);
+    }
+  }
+  if (current.length) taskBlocks.push(current.join("\n"));
+  return taskBlocks.map((block) => ({
+    id: parseYamlScalar(findTaskScalar(block, "id") || ""),
+    type: parseYamlScalar(findTaskScalar(block, "type") || "pm"),
+    assignee: parseYamlScalar(findTaskScalar(block, "assignee") || ""),
+    status: parseYamlScalar(findTaskScalar(block, "status") || "queued"),
+    title: parseYamlScalar(findTaskScalar(block, "title") || ""),
+    objective: parseYamlScalar(findTaskScalar(block, "objective") || ""),
+    inputs: findTaskList(block, "inputs"),
+    constraints: findTaskList(block, "constraints"),
+    expected_output: findTaskList(block, "expected_output"),
+    allowed_files: findTaskList(block, "allowed_files"),
+    verify: findTaskList(block, "verify"),
+    stop_if: findTaskList(block, "stop_if"),
+    subgoal: findTaskSubgoal(block),
+    receipt: findTaskReceipt(block),
+  }));
+}
+
+function findTopLevelScalar(text, key) {
+  return findScalar(text, new RegExp(`^${escapeRegExp(key)}:\\s*(.*?)\\s*$`, "m"));
+}
+
+function findNestedScalar(text, section, key) {
+  return findScalar(findTopLevelSection(text, section), new RegExp(`^  ${escapeRegExp(key)}:\\s*(.*?)\\s*$`, "m"));
+}
+
+function findTaskScalar(text, key) {
+  if (key === "id") return findScalar(text, /^  - id:\s*(.*?)\s*$/m);
+  return findScalar(text, new RegExp(`^    ${escapeRegExp(key)}:\\s*(.*?)\\s*$`, "m"));
+}
+
+function findScalar(text, pattern) {
+  const match = String(text || "").match(pattern);
+  return match ? match[1] : "";
+}
+
+function findTopLevelSection(text, key) {
+  const lines = String(text || "").replace(/\r\n/g, "\n").split("\n");
+  const start = lines.findIndex((line) => line.trim() === `${key}:`);
+  if (start === -1) return "";
+  const section = [];
+  for (let index = start + 1; index < lines.length; index += 1) {
+    const line = lines[index];
+    if (/^\S/.test(line)) break;
+    section.push(line);
+  }
+  return section.join("\n");
+}
+
+function findIndentedSection(text, key, indent) {
+  const lines = String(text || "").replace(/\r\n/g, "\n").split("\n");
+  const prefix = " ".repeat(indent);
+  const start = lines.findIndex((line) => line.trim() === `${key}:` && line.startsWith(prefix));
+  if (start === -1) return "";
+  const section = [];
+  for (let index = start + 1; index < lines.length; index += 1) {
+    const line = lines[index];
+    if (line.trim() && !line.startsWith(`${prefix}  `)) break;
+    section.push(line);
+  }
+  return section.join("\n");
+}
+
+function findTaskList(text, key) {
+  const inline = findTaskScalar(text, key);
+  if (inline) {
+    const parsed = parseYamlScalar(inline);
+    if (Array.isArray(parsed)) return parsed.map(cleanText).filter(Boolean);
+    return cleanText(parsed) ? [cleanText(parsed)] : [];
+  }
+  const section = findIndentedSection(text, key, 4);
+  return section
+    .split("\n")
+    .map((line) => line.match(/^      -\s*(.*?)\s*$/)?.[1] || "")
+    .map(parseYamlScalar)
+    .map(cleanText)
+    .filter(Boolean);
+}
+
+function findTaskSubgoal(text) {
+  const inline = findTaskScalar(text, "subgoal");
+  if (inline && parseYamlScalar(inline) === null) return null;
+  const section = findIndentedSection(text, "subgoal", 4);
+  if (!section) return null;
+  return {
+    status: parseYamlScalar(findScalar(section, /^      status:\s*(.*?)\s*$/m) || "active"),
+    path: parseYamlScalar(findScalar(section, /^      path:\s*(.*?)\s*$/m) || ""),
+    owner: parseYamlScalar(findScalar(section, /^      owner:\s*(.*?)\s*$/m) || ""),
+    created_from: parseYamlScalar(findScalar(section, /^      created_from:\s*(.*?)\s*$/m) || ""),
+    depth: parseYamlScalar(findScalar(section, /^      depth:\s*(.*?)\s*$/m) || "1"),
+    rollup_receipt: parseYamlScalar(findScalar(section, /^      rollup_receipt:\s*(.*?)\s*$/m) || "null"),
+  };
+}
+
+function findTaskReceipt(text) {
+  const inline = findTaskScalar(text, "receipt");
+  if (inline && parseYamlScalar(inline) === null) return null;
+  const section = findIndentedSection(text, "receipt", 4);
+  if (!section) return null;
+  return {
+    result: parseYamlScalar(findScalar(section, /^      result:\s*(.*?)\s*$/m) || ""),
+    summary: parseYamlScalar(findScalar(section, /^      summary:\s*(.*?)\s*$/m) || ""),
+    decision: parseYamlScalar(findScalar(section, /^      decision:\s*(.*?)\s*$/m) || ""),
+    note: parseYamlScalar(findScalar(section, /^      note:\s*(.*?)\s*$/m) || ""),
+    changed_files: findReceiptList(section, "changed_files"),
+    commands: findReceiptCommands(section),
+    evidence: [],
+  };
+}
+
+function findReceiptList(text, key) {
+  const section = findIndentedSection(text, key, 6);
+  return section
+    .split("\n")
+    .map((line) => line.match(/^        -\s*(.*?)\s*$/)?.[1] || "")
+    .map(parseYamlScalar)
+    .map(cleanText)
+    .filter(Boolean);
+}
+
+function findReceiptCommands(text) {
+  const section = findIndentedSection(text, "commands", 6);
+  const blocks = [];
+  let current = [];
+  for (const line of section.split("\n")) {
+    if (/^        - cmd:/.test(line)) {
+      if (current.length) blocks.push(current.join("\n"));
+      current = [line];
+    } else if (current.length) {
+      current.push(line);
+    }
+  }
+  if (current.length) blocks.push(current.join("\n"));
+  return blocks.map((block) => ({
+    cmd: parseYamlScalar(findScalar(block, /^        - cmd:\s*(.*?)\s*$/m) || ""),
+    status: parseYamlScalar(findScalar(block, /^          status:\s*(.*?)\s*$/m) || ""),
+    note: parseYamlScalar(findScalar(block, /^          note:\s*(.*?)\s*$/m) || ""),
+  }));
+}
+
+function parseYamlScalar(value) {
+  const text = stripComment(String(value ?? "")).trim();
+  if (!text) return "";
+  try {
+    return parseScalar(text);
+  } catch {
+    if (
+      (text.startsWith("\"") && text.endsWith("\"")) ||
+      (text.startsWith("'") && text.endsWith("'"))
+    ) {
+      return text.slice(1, -1);
+    }
+    return text;
+  }
+}
+
+function escapeRegExp(value) {
+  return String(value).replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
 }
 
 function tokenizeYaml(text) {
@@ -1326,6 +1534,25 @@ h1 {
   font-size: 14px;
 }
 
+.board-error {
+  grid-column: 1 / -1;
+  padding: 18px;
+  border: 1px solid var(--red-border);
+  border-radius: 8px;
+  background: var(--red-bg);
+  color: var(--text);
+}
+
+.board-error h2 {
+  margin: 0 0 8px;
+  font-size: 16px;
+}
+
+.board-error p {
+  margin: 0;
+  color: var(--muted);
+}
+
 @media (prefers-reduced-motion: reduce) {
   .github-stars,
   .settings-button,
@@ -1825,6 +2052,11 @@ function renderBoard(board) {
   document.getElementById("goal-active").textContent = board.goal.activeTask || "None";
   document.getElementById("goal-updated").textContent = new Date(board.generatedAt).toLocaleTimeString();
 
+  if (board.error) {
+    boardEl.replaceChildren(renderBoardError(board.error));
+    return;
+  }
+
   const delay = movingTaskIds.size ? 260 : 0;
   window.setTimeout(() => {
     boardEl.replaceChildren(...board.columns.map(renderColumn));
@@ -1832,6 +2064,15 @@ function renderBoard(board) {
   }, delay);
 }
 
+function renderBoardError(message) {
+  const node = el("section", "board-error");
+  node.append(
+    el("h2", "", "GoalBuddy could not parse this board"),
+    el("p", "", message),
+  );
+  return node;
+}
+
 function renderBoardSwitcher(boards) {
   boardSwitcherEl.closest(".board-switcher").classList.toggle("is-empty", boards.length <= 1);
   const currentPath = normalizePath(window.location.pathname);

package/plugins/goalbuddy/skills/goalbuddy/extend/local-goal-board/test/local-goal-board.test.mjs

@@ -82,6 +82,62 @@ tasks:
   }
 });
 
+test("keeps board rendering when deep receipt YAML is malformed", () => {
+  const root = mkdtempSync(join(tmpdir(), "goalbuddy-board-subset-parser-"));
+  try {
+    const goalDir = join(root, "subset-parser");
+    mkdirSync(join(goalDir, "notes"), { recursive: true });
+    writeFileSync(join(goalDir, "state.yaml"), `version: 2
+goal:
+  title: "Subset parser"
+  slug: "subset-parser"
+  kind: specific
+  tranche: "Recover shallow board fields."
+  status: active
+active_task: T003
+checks:
+  last_verification:
+    status: pass
+    raw:
+      malformed nested checker output
+tasks:
+  - id: T001
+    type: worker
+    assignee: Worker
+    status: completed
+    objective: "Ship a completed worker slice."
+    receipt:
+      result: done
+      summary: "Worker finished."
+      raw:
+        malformed nested receipt output
+  - id: T002
+    type: judge
+    assignee: Judge
+    status: complete
+    objective: "Approve the result."
+    receipt: null
+  - id: T003
+    type: scout
+    assignee: Scout
+    status: active
+    objective: "Inspect what is left."
+    receipt: null
+`);
+
+    const payload = createBoardPayload(goalDir);
+    assert.equal(payload.goal.title, "Subset parser");
+    assert.equal(payload.goal.activeTask, "T003");
+    assert.equal(payload.counts.completed, 2);
+    assert.equal(payload.counts.inProgress, 1);
+    assert.equal(payload.tasks.find((task) => task.id === "T001").status, "done");
+    assert.equal(payload.tasks.find((task) => task.id === "T002").status, "done");
+    assert.equal(payload.tasks.find((task) => task.id === "T001").receipt.summary, "Worker finished.");
+  } finally {
+    rmSync(root, { recursive: true, force: true });
+  }
+});
+
 test("fails loudly when a linked subgoal state file is missing", () => {
   const root = mkdtempSync(join(tmpdir(), "goalbuddy-missing-subgoal-"));
   try {
@@ -194,6 +250,7 @@ test("writes a minimal GoalBuddy web app into the goal directory", () => {
   assert.match(css, /:root\[data-density="compact"\] \.task-card/);
   assert.match(css, /:root\[data-completed-visibility="collapse"\]/);
   assert.match(css, /\.subgoal-board/);
+  assert.match(css, /\.board-error/);
   assert.match(js, /new EventSource\("\.\/events"\)/);
   assert.match(js, /fetch\("\.\.\/api\/boards"/);
   assert.match(js, /fetch\("\.\.\/api\/settings"/);
@@ -206,6 +263,7 @@ test("writes a minimal GoalBuddy web app into the goal directory", () => {
   assert.match(js, /card\.animate/);
   assert.match(js, /highlightMovingCards/);
   assert.match(js, /renderSubgoal/);
+  assert.match(js, /renderBoardError/);
   assert.match(js, /boardOptionLabel/);
   assert.match(js, /duration: changedColumn \? 980 : 520/);
   assert.equal(logo.subarray(1, 4).toString("ascii"), "PNG");
@@ -333,7 +391,7 @@ test("advertises goalbuddy.localhost while binding to loopback", async () => {
 });
 
 test("runs when installed under a symlinked temp path", () => {
-  const root = mkdtempSync("/tmp/goalbuddy-local-board-direct-");
+  const root = mkdtempSync(join(tmpdir(), "goalbuddy-local-board-direct-"));
   try {
     cpSync("extend/local-goal-board/scripts", join(root, "scripts"), { recursive: true });
     cpSync("extend/local-goal-board/assets", join(root, "assets"), { recursive: true });