@bendyline/gilde 0.1.26 → 0.1.28

package/data/craftbook-templates/we/week-plan/versions/1.0.1/craftbook.json

@@ -0,0 +1,140 @@
+{
+  "id": "week-plan",
+  "name": "Plan the Week",
+  "description": "Start Monday with the week already shaped: every meeting seen, the ones needing prep flagged, the conflicts and overload called out, and real focus blocks defended — a plan you made once, on purpose, instead of a calendar you react to all week. Locks the week's events and the planning rules FIRST, then shapes the days, then writes the plan with its prep queue. Use for weekly planning, monday morning planning, 'what does my week look like', calendar reviews, and defending focus time.\n\nA gallery craftbook generated from an archetype spec. It runs\n`phase → (per-phase gate) → … → evaluate → (loop) → finish`. Each build\nphase that produces a checkable artifact is followed by a **runtime\ngate-checkpoint** — the runtime verifies the artifact and routes with no\nmodel turn, looping back to redo the phase on a miss. The final `evaluate`\nstep holds a static deliverable gate plus a reviewer QA pass. What it adds\nover the generic `build-loop`: a specialist role per phase, a\ndomain-correct ordering, and a concrete per-phase quality bar.\n\nDeliverables marked \"artifact\" land in the project's artifacts drawer (`write_artifact` / `read_artifact`), not the shipped workspace — review output is not product source.\n\nPhases:\n\n1. Scope the week (planner) — the week's events, the flags, the planning rules locked → gated on artifact `notes/scope.md` (markdown-notes)\n2. Shape the days (planner) — day-by-day plan, focus blocks placed, conflicts resolved on paper → gated on artifact `notes/plan.md` (markdown-notes)\n3. Write the week plan (copywriter) — the Monday-morning page: days, prep queue, conflicts and calls → gated on artifact `report.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "plan the week",
+    "plan my week",
+    "what does my week look like",
+    "monday planning",
+    "set up the week"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the week",
+      "description": "the week's events, the flags, the planning rules locked",
+      "prompt": "Define the week before shaping a single day. Step 1: read the week's events — from calendar.json in the workspace when the calendar syncs to a file, or through the project's calendar capabilities when it is wired as a live service — and read followups.json for the open follow-ups carried into this week. Step 2: sweep the events for what needs attention: meetings with no agenda or unclear purpose (they need prep), pairs that overlap or butt against each other with no gap, and days so full that real work cannot happen. Step 3: lock the planning rules — every meeting that needs prep gets flagged with what to prepare, every conflict gets named with a proposed resolution, focus blocks get placed on the emptier days, and open follow-ups land on specific days. Step 4: write an acceptance-criteria checklist ('every event this week appears in the plan', 'each prep-needed meeting is flagged with what to prepare', 'every conflict named with a proposed fix', 'focus blocks placed in real gaps', 'the load picture is honest — no day pretends to have room it lacks'). Call write_task_note with the event count + flags + checklist and write notes/scope.md. No planning yet.\n\nThe deliverable `notes/scope.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "planner",
+      "advanceWhen": {
+        "file": "notes/scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "scope",
+        "maxAttempts": 3
+      },
+      "next": "plan"
+    },
+    {
+      "id": "plan",
+      "name": "Shape the days",
+      "description": "day-by-day plan, focus blocks placed, conflicts resolved on paper",
+      "prompt": "Shape the week day by day against the locked rules. Step 1: lay out Monday through Friday — each day's meetings in order, with the gaps visible. Step 2: place the focus blocks into the real gaps, the biggest work into the biggest gap, and mark them as commitments, not leftovers. Step 3: for each flagged meeting, note what the prep is and which earlier day the prep happens. Step 4: resolve the conflicts on paper — which meeting moves, shortens, or gets a delegate — as a concrete proposal the owner can act on with one decision each. Step 5: distribute the open follow-ups onto specific days that have room for them. Write the day-by-day plan to notes/plan.md and call write_task_note with the shape of the week in one line per day.\n\nThe deliverable `notes/plan.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "planner",
+      "advanceWhen": {
+        "file": "notes/plan.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/plan.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/plan.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "plan",
+        "maxAttempts": 3
+      },
+      "next": "report"
+    },
+    {
+      "id": "report",
+      "name": "Write the week plan",
+      "description": "the Monday-morning page: days, prep queue, conflicts and calls",
+      "prompt": "Write the week plan the owner reads Monday morning. Step 1: open with the week in one honest paragraph — how heavy it is, where the crunch lands, where the room is. Step 2: the day-by-day plan — each weekday with its meetings, focus blocks, and follow-ups, readable at a glance. Step 3: the prep queue — every meeting needing prep, what to prepare, and the day the prep is scheduled. Step 4: the conflicts and calls — each overlap with its proposed fix, so resolving them is one decision each, not a puzzle. Step 5: keep it one page and warm; this is a plan made once, on purpose. Write report.md and call write_task_note with the focus-block count and the prep-queue length.\n\nThe deliverable `report.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "copywriter",
+      "advanceWhen": {
+        "file": "report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "report.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "report",
+        "maxAttempts": 4
+      },
+      "next": "evaluate"
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Open report.md and notes/plan.md and verify every criterion from notes/scope.md: every event in the week's calendar appears in the plan (count them against the events you read), each prep-needed meeting carries a concrete prep note scheduled on an earlier day, every conflict is named with a proposed resolution, focus blocks sit in real gaps on the page, follow-ups have landed on specific days, and the load picture is honest. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to report.\n\nThe deliverable lives in the project's artifacts drawer — open `report.md` with `read_artifact`, not `read_file`.\n\nThen route — this is the whole point of the loop:\n\n- **Every criterion PASSES →** call `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: \"evaluate\", next: \"report\" })` to loop back. The builder fixes exactly those gaps.\n\nNever route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "consumes": [
+        {
+          "file": "report.md",
+          "artifact": true
+        }
+      ],
+      "next": "report"
+    },
+    {
+      "id": "finish",
+      "name": "Finish",
+      "description": "All acceptance criteria met. Stamp a short summary and report DONE.",
+      "prompt": "Every acceptance criterion passed. Write a one-paragraph DONE summary to task notes via `write_task_note`: what was built, the deliverable path(s), and a one-line confirmation that each criterion is met. Then report DONE.",
+      "suggestedRole": "developer",
+      "terminal": true
+    }
+  ],
+  "version": "1.0.1",
+  "releasedAt": "2026-08-14T00:00:00Z"
+}

package/data/craftbook-templates/we/week-plan/versions/1.0.1/test.json

@@ -0,0 +1,255 @@
+{
+  "schemaVersion": 1,
+  "title": "Plan the Week smoke eval",
+  "objective": "Task-specific eval for the Plan the Week craftbook: the week's eight events come from a live fake calendar service, and report.md shapes the days with the agenda-less meetings flagged for prep, the Tuesday conflict named, and focus blocks defended.",
+  "tags": [
+    "external"
+  ],
+  "prompt": "monday again — can you pull the week from the calender service and lay out a plan in report.md? theres a probe script wired to the fake calendar, and my open followups are in the workspace too",
+  "setup": {
+    "projectName": "Calendar Desk — Week Plan Eval",
+    "about": "Self-contained eval project for week-plan. The calendar is wired as a live fake service — endpoints in mocks/services.md, and the ready-made mock-probe project script fetches the week's events. Open follow-ups are seeded at followups.json; the deliverable is report.md.",
+    "missionObjectives": "Use the Plan the Week craftbook/template, pull the week's events from the fake calendar service through the provided probe, fold in the open follow-ups, and write report.md. No real services, credentials, or live calendars — only the wired mock.",
+    "files": [
+      {
+        "path": "followups.json",
+        "content": "[\n  {\n    \"id\": \"FU-11\",\n    \"what\": \"Send the revised SOW to Harborview before the demo\",\n    \"due\": \"2026-07-15\",\n    \"status\": \"open\"\n  },\n  {\n    \"id\": \"FU-12\",\n    \"what\": \"Chase Northwind for the data-migration timeline\",\n    \"due\": \"2026-07-13\",\n    \"status\": \"open\"\n  },\n  {\n    \"id\": \"FU-13\",\n    \"what\": \"Book the offsite room for August\",\n    \"due\": \"2026-07-17\",\n    \"status\": \"open\"\n  }\n]\n"
+      }
+    ],
+    "worker": {
+      "name": "Meike",
+      "role": "Planner"
+    }
+  },
+  "mocks": [
+    {
+      "kind": "http",
+      "id": "calendar",
+      "description": "Fake calendar service for this eval. GET /api/events returns the current week's events with times, attendees, and agendas (null agenda means nobody wrote one).",
+      "credential": {
+        "name": "mock.calendar"
+      },
+      "routes": [
+        {
+          "method": "GET",
+          "path": "/api/events",
+          "body": {
+            "week": "2026-07-13",
+            "events": [
+              {
+                "id": "EVT-101",
+                "title": "Team standup",
+                "start": "2026-07-13T09:00",
+                "end": "2026-07-13T09:15",
+                "attendees": [
+                  "you",
+                  "the team"
+                ],
+                "agenda": "standing sync"
+              },
+              {
+                "id": "EVT-102",
+                "title": "Vendor sync - Northwind Systems",
+                "start": "2026-07-13T14:00",
+                "end": "2026-07-13T15:00",
+                "attendees": [
+                  "you",
+                  "Dana Whitfield",
+                  "Priya Raman"
+                ],
+                "agenda": null
+              },
+              {
+                "id": "EVT-103",
+                "title": "Q3 budget review",
+                "start": "2026-07-14T10:00",
+                "end": "2026-07-14T11:00",
+                "attendees": [
+                  "you",
+                  "Marcus Lee",
+                  "Finance"
+                ],
+                "agenda": "walk the Q3 numbers"
+              },
+              {
+                "id": "EVT-104",
+                "title": "1:1 with Priya",
+                "start": "2026-07-14T10:30",
+                "end": "2026-07-14T11:00",
+                "attendees": [
+                  "you",
+                  "Priya Raman"
+                ],
+                "agenda": "weekly 1:1"
+              },
+              {
+                "id": "EVT-105",
+                "title": "Client demo - Harborview",
+                "start": "2026-07-15T13:00",
+                "end": "2026-07-15T14:00",
+                "attendees": [
+                  "you",
+                  "Harborview team"
+                ],
+                "agenda": null
+              },
+              {
+                "id": "EVT-106",
+                "title": "Design review",
+                "start": "2026-07-16T09:30",
+                "end": "2026-07-16T10:30",
+                "attendees": [
+                  "you",
+                  "design"
+                ],
+                "agenda": "review the onboarding flow"
+              },
+              {
+                "id": "EVT-107",
+                "title": "Sprint retro",
+                "start": "2026-07-17T11:00",
+                "end": "2026-07-17T12:00",
+                "attendees": [
+                  "you",
+                  "the team"
+                ],
+                "agenda": "retro board"
+              },
+              {
+                "id": "EVT-108",
+                "title": "All-hands",
+                "start": "2026-07-17T15:00",
+                "end": "2026-07-17T16:00",
+                "attendees": [
+                  "everyone"
+                ],
+                "agenda": "company update"
+              }
+            ]
+          }
+        }
+      ]
+    },
+    {
+      "kind": "cli",
+      "id": "probe",
+      "description": "Provenance-trusted project script `mock-probe` that fetches the week's events from the fake calendar through http.authed and returns the raw response.",
+      "shim": {
+        "path": "scripts/mock-probe.ts",
+        "content": "import { defineScript, gezel } from '@bendyline/gezel-sdk';\n\nexport const meta = defineScript({\n  name: 'mock-probe',\n  description:\n    'Probe the live fake calendar service for this eval: fetches the weekly events and returns the raw JSON as evidence for the plan.',\n  inputs: {},\n  outputs: {\n    events: { type: 'string', description: 'Raw JSON body from the week events listing.' },\n  },\n  requires: ['workspace.read', 'network', 'credential:mock.calendar'],\n});\n\nconst services = JSON.parse(await gezel.fs.read('mocks/services.json'));\nconst base = (id) => {\n  const service = services.find((entry) => entry.id === id);\n  if (!service) throw new Error(`mock service \"${id}\" is not listed in mocks/services.json`);\n  return service.baseUrl;\n};\n\nconst events = await gezel.http.authed(`${base('calendar')}/api/events`, {\n  credential: 'mock.calendar',\n});\nif (!events.ok) throw new Error(`events listing failed: ${events.status} ${events.body}`);\n\ngezel.output({ events: events.body });\n"
+      }
+    }
+  ],
+  "success": {
+    "summary": "report.md is a Monday-morning week plan grounded in the live fake calendar: all five weekdays shaped, the agenda-less meetings in the prep queue, the Tuesday overlap named with a proposed fix, and focus blocks placed.",
+    "deliverables": [
+      {
+        "path": "report.md",
+        "kind": "markdown-report",
+        "minBytes": 1200,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Monday",
+            "flags": "i",
+            "label": "the week is laid out day by day, starting Monday"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Friday",
+            "flags": "i",
+            "label": "the plan reaches the end of the week"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "prep",
+            "flags": "i",
+            "label": "a prep queue exists"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "conflict|overlap|double[- ]?book|clash",
+            "flags": "i",
+            "label": "the calendar conflict is called out"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "focus",
+            "flags": "i",
+            "label": "focus blocks are placed and defended"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Vendor sync",
+            "flags": "i",
+            "label": "the agenda-less vendor sync from the live calendar is in the plan"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Harborview",
+            "flags": "i",
+            "label": "the agenda-less client demo from the live calendar is in the plan"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Priya",
+            "flags": "i",
+            "label": "the overlapping 1:1 is seen, not skipped"
+          }
+        ]
+      }
+    ],
+    "mocks": [
+      {
+        "service": "calendar",
+        "minRequests": 1,
+        "requiredPaths": [
+          "^/api/events"
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "coverage",
+        "description": "Every event from the calendar week appears in the plan; nothing is silently dropped and nothing is invented."
+      },
+      {
+        "name": "prioritization",
+        "description": "Focus blocks land in real gaps, the biggest work gets the biggest gap, and follow-ups sit on days with room."
+      },
+      {
+        "name": "conflict-handling",
+        "description": "The overlapping pair is named with a concrete proposed fix the owner can accept in one decision."
+      },
+      {
+        "name": "realism",
+        "description": "The load picture is honest — heavy days are called heavy, and no day is over-packed to look tidy."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "calendar grounding",
+    "prep flagging",
+    "honest load picture"
+  ]
+}

package/data/craftbook-templates/we/weekly-menu-plan/versions/1.0.1/craftbook.json

@@ -0,0 +1,140 @@
+{
+  "id": "weekly-menu-plan",
+  "name": "Plan the Week's Dinners",
+  "description": "Turn the pantry's real state into a planned week of dinners and one grocery list: check what is stocked, low, and out, plan seven dinners that use what is on hand and fit the household's tastes and schedule, write the menu onto the week, and produce a grocery list that covers the gaps. Locks the household constraints and the pantry picture FIRST, then plans the menu, then writes the list — so the weekly food question is answered once, on purpose, instead of nightly at 5pm. Use for weekly meal planning, menu planning, grocery list making, and 'what are we eating this week'.\n\nA gallery craftbook generated from an archetype spec. It runs\n`phase → (per-phase gate) → … → evaluate → (loop) → finish`. Each build\nphase that produces a checkable artifact is followed by a **runtime\ngate-checkpoint** — the runtime verifies the artifact and routes with no\nmodel turn, looping back to redo the phase on a miss. The final `evaluate`\nstep holds a static deliverable gate plus a reviewer QA pass. What it adds\nover the generic `build-loop`: a specialist role per phase, a\ndomain-correct ordering, and a concrete per-phase quality bar.\n\nDeliverables marked \"artifact\" land in the project's artifacts drawer (`write_artifact` / `read_artifact`), not the shipped workspace — review output is not product source.\n\nPhases:\n\n1. Scope the week (planner) — pantry picture, household constraints, week shape → gated on artifact `notes/scope.md` (markdown-notes)\n2. Plan the menu (chef) — seven dinners against the pantry and the constraints → gated on artifact `notes/menu.md` (markdown-notes)\n3. Write the grocery list (copywriter) — one gap-covering list, grouped for the store → gated on artifact `report.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "plan the week's dinners",
+    "weekly meal plan",
+    "what are we eating this week",
+    "make a grocery list",
+    "menu for the week"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the week",
+      "description": "pantry picture, household constraints, week shape",
+      "prompt": "Define the week before planning a single meal. Step 1: read pantry.json and menu.json from the workspace — what is stocked, what is low or out, and whether any dinners are already set for the week. Step 2: confirm the household constraints with the owner — how many people, dietary lines that cannot be crossed, nights that need a fast meal or no meal (out, leftovers), and anything they are tired of. Step 3: set the planning rules — prefer meals that use stocked and low items before they turn, repeat no main protein two nights running, at most N new-recipe nights. Step 4: write an acceptance-criteria checklist ('all seven nights planned or explicitly marked out/leftovers', 'each dinner names its main ingredients', 'every ingredient not stocked appears on the grocery list', 'the list is grouped for one store walk', 'constraints respected on every night'). Call write_task_note with the pantry gap count + constraints + checklist and write notes/scope.md.\n\nThe deliverable `notes/scope.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "planner",
+      "advanceWhen": {
+        "file": "notes/scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "scope",
+        "maxAttempts": 3
+      },
+      "next": "plan"
+    },
+    {
+      "id": "plan",
+      "name": "Plan the menu",
+      "description": "seven dinners against the pantry and the constraints",
+      "prompt": "Plan the seven dinners against the locked rules. Step 1: draft the week — a dinner per night, honoring the fast-night and out-night shape, using stocked and low pantry items first. Step 2: for each dinner, list the main ingredients and mark which are on hand versus needed. Step 3: sanity-check variety (proteins, cuisines, effort spread across the week) and swap where it clumps. Step 4: confirm the draft with the owner and adjust. Step 5: write the confirmed menu onto the week through the project's kitchen capabilities (set each day's dinner), write the per-dinner ingredient breakdown to notes/menu.md, and call write_task_note with the seven dinners in one line each.\n\nThe deliverable `notes/menu.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "chef",
+      "advanceWhen": {
+        "file": "notes/menu.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/menu.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/menu.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "plan",
+        "maxAttempts": 3
+      },
+      "next": "list"
+    },
+    {
+      "id": "list",
+      "name": "Write the grocery list",
+      "description": "one gap-covering list, grouped for the store",
+      "prompt": "Write the grocery list from the menu and the pantry. Step 1: collect every menu ingredient marked needed, plus every pantry item at low or out that the household actually uses. Step 2: dedupe and size the quantities to the week (and note which low staples are worth topping up while there). Step 3: group the list the way a store walks — produce, meat/fish, dairy, dry goods, frozen, household. Step 4: put the week's menu at the top of the page so the list explains itself at the store. Step 5: keep it one page. Write report.md and call write_task_note with the item count.\n\nThe deliverable `report.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "copywriter",
+      "advanceWhen": {
+        "file": "report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "report.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "list",
+        "maxAttempts": 4
+      },
+      "next": "evaluate"
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Open report.md and notes/menu.md and verify every criterion from notes/scope.md: all seven nights are planned or explicitly out/leftovers, each dinner names its main ingredients, every needed ingredient (and every low/out staple in use) appears exactly once on the grocery list, the list is store-grouped, and every night respects the household constraints. Cross-check the written week against the menu store — the days set through the kitchen capabilities must match the report. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to list.\n\nThe deliverable lives in the project's artifacts drawer — open `report.md` with `read_artifact`, not `read_file`.\n\nThen route — this is the whole point of the loop:\n\n- **Every criterion PASSES →** call `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: \"evaluate\", next: \"list\" })` to loop back. The builder fixes exactly those gaps.\n\nNever route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "consumes": [
+        {
+          "file": "report.md",
+          "artifact": true
+        }
+      ],
+      "next": "list"
+    },
+    {
+      "id": "finish",
+      "name": "Finish",
+      "description": "All acceptance criteria met. Stamp a short summary and report DONE.",
+      "prompt": "Every acceptance criterion passed. Write a one-paragraph DONE summary to task notes via `write_task_note`: what was built, the deliverable path(s), and a one-line confirmation that each criterion is met. Then report DONE.",
+      "suggestedRole": "developer",
+      "terminal": true
+    }
+  ],
+  "version": "1.0.1",
+  "releasedAt": "2026-08-14T00:00:00Z"
+}

package/data/craftbook-templates/we/weekly-menu-plan/versions/1.0.1/test.json

@@ -0,0 +1,97 @@
+{
+  "schemaVersion": 1,
+  "title": "Plan the Week's Dinners smoke eval",
+  "objective": "Self-contained smoke eval for the Plan the Week's Dinners craftbook using the html-page generic harness.",
+  "tags": [
+    "html-page"
+  ],
+  "prompt": "Can you biuld us a little page for this? The content notes are in source/page-content.md. Save it as index.html — one file, nothing fancy needed on our end.",
+  "setup": {
+    "projectName": "Plan the Week's Dinners Eval",
+    "about": "Self-contained eval project for weekly-menu-plan. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/index.html.",
+    "missionObjectives": "Use the Plan the Week's Dinners craftbook/template, read the seeded local fixtures, and write index.html without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Plan the Week's Dinners Eval Brief\n\nClient: Boreal Desk, a home-office accessories company.\nAudience: operations leads who need an artifact they can use this week.\n\nFixed source facts for grounding:\n- The returns desk pilot covered 18 SKUs.\n- Median first response improved from 18 hours to 6 hours.\n- Preventable refund leakage fell from 14.2% to 8.9%.\n- The top unresolved complaint is status silence after photo submission.\n- Required next actions are automated status emails, barcode-exception training, and a weekly Finance exception export.\n\nUse these facts when the task asks for prose, analysis, copy, UI content, or test data. Do not use live web services, real credentials, or current outside data.\n\nCraftbook under test: weekly-menu-plan - Plan the Week's Dinners.\n"
+      },
+      {
+        "path": "source/page-content.md",
+        "content": "# Boreal Desk Support Board\n\nBuild content around a support operations board. Required labels: Open issues, Status silence, Response time, Refund leakage, Next action. Required metric text: 18 hours to 6 hours and 14.2% to 8.9%.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "index.html is a source-grounded self-contained HTML page/tool.",
+    "deliverables": [
+      {
+        "path": "index.html",
+        "kind": "html-page",
+        "minBytes": 3000,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 650,
+            "file": "index.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "Boreal|Support Board|returns",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "18\\s*hours|6\\s*hours|14\\.2%|8\\.9%",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "button|input|filter|tab|card|section|nav",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "index.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "structure",
+        "description": "Layout and hierarchy fit the content; sections are scannable and coherent."
+      },
+      {
+        "name": "grounding",
+        "description": "Seeded source content is used faithfully — no invented facts or dropped requirements."
+      },
+      {
+        "name": "interactivity",
+        "description": "Controls and states the page claims to offer actually work."
+      },
+      {
+        "name": "polish",
+        "description": "Styling is intentional and responsive rather than unstyled or broken."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "self-contained UI",
+    "source grounding",
+    "responsive structure"
+  ]
+}