@bendyline/gilde 0.1.26 → 0.1.28

package/data/craftbook-templates/ho/holiday-card-run/versions/1.0.1/test.json

@@ -0,0 +1,128 @@
+{
+  "schemaVersion": 1,
+  "title": "Holiday Card Run — roster sweep to print-ready card and address sheet",
+  "objective": "Measure whether the holiday-card-run craftbook sweeps a seeded address roster, produces a print-ready card and address sheet, and reports the stale and missing addresses instead of quietly dropping households.",
+  "tags": [
+    "html-page"
+  ],
+  "prompt": "time for the holliday cards — can you do the card and the address sheet from the list? a few adresses might be stale. warm message, nothing over the top",
+  "setup": {
+    "projectName": "Bracken Lane Card Run",
+    "about": "Correspondence desk for the Miller-Osei household's annual card run. The address roster lives at workspace/correspondents.json; the run's print files go under workspace/cards.",
+    "missionObjectives": "Get the December run print-ready with a clean address list. Everything is grounded in the roster — no live services, no real credentials.",
+    "files": [
+      {
+        "path": "correspondents.json",
+        "content": "{\n  \"household\": \"the Miller-Oseis\",\n  \"cardList\": [\n    { \"family\": \"Barrett\", \"cardLabel\": \"The Barrett Family\", \"address\": \"14 Cedar Loop, Halstead, MN 55301\" },\n    { \"family\": \"Okonkwo\", \"cardLabel\": \"The Okonkwo Family\", \"address\": \"902 Birchwood Ave, Halstead, MN 55301\" },\n    { \"family\": \"Reyes\", \"cardLabel\": \"The Reyes Family\", \"address\": \"77 Quarry Rd, Duluth, MN 55803\" },\n    { \"family\": \"Lindqvist\", \"cardLabel\": \"The Lindqvist Family\", \"address\": \"5 Aspen Ct, Halstead, MN 55301\", \"note\": \"moved last spring — address unconfirmed\" },\n    { \"family\": \"Achterberg\", \"cardLabel\": \"The Achterberg Family\", \"address\": \"310 Mill Pond Ln, Roseau, MN 56751\" },\n    { \"family\": \"Nguyen\", \"cardLabel\": \"The Nguyen Family\", \"address\": null },\n    { \"family\": \"Castellano\", \"cardLabel\": \"The Castellano Family\", \"address\": \"48 Harbor View Dr, Bayfield, WI 54814\" },\n    { \"family\": \"Whitfield\", \"cardLabel\": \"The Whitfield Family\", \"address\": \"\" },\n    { \"family\": \"Dube\", \"cardLabel\": \"The Dube Family\", \"address\": \"221 Larkspur St, Halstead, MN 55301\" },\n    { \"family\": \"Petrov\", \"cardLabel\": \"The Petrov Family\", \"address\": \"1600 Winter Hill Rd, Grand Marais, MN 55604\" }\n  ]\n}\n"
+      }
+    ],
+    "worker": {
+      "name": "Sanne",
+      "role": "Designer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "cards/card.html is a print-styled card with the settled message; cards/addresses.html covers the roster with the gaps marked; report.md names the stale and missing addresses.",
+    "deliverables": [
+      {
+        "path": "cards/card.html",
+        "kind": "html-page",
+        "minBytes": 1200,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 650,
+            "file": "cards/card.html"
+          },
+          {
+            "kind": "contains",
+            "file": "cards/card.html",
+            "pattern": "@page|@media\\s+print",
+            "flags": "i",
+            "label": "print CSS"
+          }
+        ]
+      },
+      {
+        "path": "cards/addresses.html",
+        "kind": "html-page",
+        "minBytes": 1000,
+        "checks": [
+          {
+            "kind": "valuesSubsetOf",
+            "file": "cards/addresses.html",
+            "sourceFiles": [
+              "correspondents.json"
+            ],
+            "pattern": "The\\s+([A-Z][A-Za-z-]+)\\s+Family",
+            "minMatches": 8,
+            "label": "address blocks use the roster's own labels"
+          },
+          {
+            "kind": "contains",
+            "file": "cards/addresses.html",
+            "pattern": "\\d+\\s*(?:households?|addresses|recipients?|cards)",
+            "flags": "i",
+            "label": "run count stated on the sheet"
+          }
+        ]
+      },
+      {
+        "path": "report.md",
+        "kind": "markdown-report",
+        "minBytes": 600,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "missing|stale|unconfirmed",
+            "flags": "i",
+            "label": "address gaps surfaced"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Nguyen|Whitfield|Lindqvist",
+            "flags": "i",
+            "label": "flagged households named"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "cards/card.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "print readiness",
+        "description": "The card and sheet carry real print styling — page setup, margins, breaks — not a screen layout with a print label."
+      },
+      {
+        "name": "address hygiene",
+        "description": "Stale and missing addresses are flagged by name; no household quietly dropped from the run."
+      },
+      {
+        "name": "message warmth",
+        "description": "The card message is warm and works for every household on the list."
+      },
+      {
+        "name": "run completeness",
+        "description": "Card, address sheet, and summary together make the run finishable in one sitting."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "print-ready output",
+    "address hygiene",
+    "no dropped households"
+  ]
+}

package/data/craftbook-templates/ho/hotfix-flow/versions/1.0.1/craftbook.json

@@ -0,0 +1,182 @@
+{
+  "id": "hotfix-flow",
+  "name": "Hotfix Flow",
+  "description": "Drive an expedited production hotfix from red to green: reproduce the live defect with a failing test, apply the smallest safe fix that makes it pass without scope-creeping into a refactor, and verify the fix plus a clean regression check before it ships out-of-band. The ordering is the whole discipline — reproduce FIRST (a failing test that captures the bug is the contract the fix must satisfy), then fix minimally, then verify the new test passes and nothing else broke. Use this for urgent production bugs, expedited patch releases, and out-of-band fixes where speed matters but a regression would be worse than the original bug.\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. Reproduce with a failing test (developer) — capture the live defect as a failing, deterministic test → gated on artifact `notes/reproduce.md` (markdown-notes)\n2. Apply the minimal fix (developer) — smallest safe change that turns the failing test green → gated on `hotfix.ts` (code-with-tests)\n3. Verify and regression-check (reviewer) — confirm green plus no regressions before shipping → gated on artifact `notes/verify.md` (markdown-notes)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "reproduce",
+  "triggers": [
+    "hotfix this bug",
+    "urgent production fix",
+    "expedited patch",
+    "fix the live defect",
+    "out-of-band fix"
+  ],
+  "steps": [
+    {
+      "id": "reproduce",
+      "name": "Reproduce with a failing test",
+      "description": "capture the live defect as a failing, deterministic test",
+      "prompt": "1. Read the bug report / incident and state the exact observed behavior vs the expected behavior in one line each. 2. Identify the smallest input or scenario that triggers the defect. 3. Write a NEW automated test that exercises that scenario and asserts the EXPECTED (correct) behavior — so it fails RED against current code for the right reason (it reproduces THIS bug, not some unrelated assertion). 4. Run the test and confirm it fails, capturing the failure output as proof of reproduction. 5. Do NOT fix anything yet and do NOT alter unrelated code. 6. Good looks like: one focused, deterministic failing test that pins the defect, plus the captured red output. Write an acceptance-criteria checklist ('a new test reproduces the bug and fails red', 'the test asserts correct behavior not the buggy behavior', 'the test is deterministic and minimal', 'the fix will be the smallest change that turns it green', 'full suite must stay green after the fix') plus the observed/expected behavior and the test location to the notes file via write_task_note AND to notes/reproduce.md.\n\nThe deliverable `notes/reproduce.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": "developer",
+      "advanceWhen": {
+        "file": "notes/reproduce.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/reproduce.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/reproduce.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "reproduce",
+        "maxAttempts": 3
+      },
+      "next": "fix"
+    },
+    {
+      "id": "fix",
+      "name": "Apply the minimal fix",
+      "description": "smallest safe change that turns the failing test green",
+      "prompt": "1. Open notes/reproduce.md and make the SMALLEST change that turns the reproducing test green — fix the root cause, not the symptom, but resist refactoring, renaming, or unrelated cleanup (this is a hotfix, not a rewrite). 2. Keep the diff tight and reviewable; touch only what the fix requires. 3. Run the reproducing test and confirm it now passes GREEN; capture the output. 4. If the fix needs a follow-up (a deeper refactor, tech-debt), note it as a separate item rather than doing it now. 5. Implement the fix and the reproducing test together in the deliverable file so the change is self-verifying. 6. Good looks like: a minimal diff that makes the new test pass for the right reason, with no scope creep. Write the fix plus the reproducing test (the source/test module that now passes) to hotfix.ts.\n\nBefore working, open the artifact input `notes/reproduce.md` with `read_artifact`; do not look for it in the workspace.",
+      "suggestedRole": "developer",
+      "consumes": [
+        {
+          "file": "notes/reproduce.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "hotfix.ts",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "hotfix.ts",
+            "bytes": 300
+          },
+          {
+            "kind": "sniff",
+            "file": "hotfix.ts",
+            "sniff": "nonempty"
+          },
+          {
+            "kind": "esmImports",
+            "file": "hotfix.ts"
+          },
+          {
+            "kind": "sourceParses",
+            "file": "hotfix.ts"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "hotfix.ts",
+              "pattern": "\\b(test|describe|it|assert|expect)\\b",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "fix",
+        "maxAttempts": 3
+      },
+      "next": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify and regression-check",
+      "description": "confirm green plus no regressions before shipping",
+      "prompt": "1. Run the reproducing test and confirm it now passes GREEN. 2. Run the FULL relevant test suite and confirm nothing else broke — a hotfix that fixes one bug and regresses another is a failure. 3. Review the diff for scope creep: confirm the change is minimal and addresses the root cause described in notes/reproduce.md, not a symptom patch. 4. Sanity-check edge cases adjacent to the fix that a single test might miss. 5. Write a PASS/FAIL per acceptance criterion from reproduce.md, with the test output as evidence and any regression or over-reach called out. 6. Any failure routes back to the fix phase. Write findings to notes/verify.md.\n\nBefore working, open the artifact input `notes/reproduce.md` with `read_artifact`; do not look for it in the workspace.\n\nThe deliverable `notes/verify.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": "reviewer",
+      "consumes": [
+        {
+          "file": "notes/reproduce.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "notes/verify.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "hotfix.ts",
+            "bytes": 300
+          },
+          {
+            "kind": "sniff",
+            "file": "hotfix.ts",
+            "sniff": "nonempty"
+          },
+          {
+            "kind": "esmImports",
+            "file": "hotfix.ts"
+          },
+          {
+            "kind": "sourceParses",
+            "file": "hotfix.ts"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "hotfix.ts",
+              "pattern": "\\b(test|describe|it|assert|expect)\\b",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "verify",
+        "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 hotfix.ts and verify it against the criteria in notes/reproduce.md, PASS/FAIL each. Confirm: (a) it contains a test that reproduces the reported bug by asserting the correct behavior; (b) that test passes GREEN against the fix; (c) the fix is minimal and targets the root cause with no unrelated refactor/scope-creep; (d) the change does not regress adjacent behavior (the broader suite stays green); (e) the test is deterministic. Run/trace the test to gather evidence. Any FAIL routes back to the fix phase.\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: \"fix\" })` 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": "hotfix.ts"
+        }
+      ],
+      "next": "fix"
+    },
+    {
+      "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/ho/hotfix-flow/versions/1.0.1/test.json

@@ -0,0 +1,92 @@
+{
+  "schemaVersion": 1,
+  "title": "Hotfix Flow smoke eval",
+  "objective": "Self-contained smoke eval for the Hotfix Flow craftbook using the code generic harness.",
+  "tags": [
+    "code"
+  ],
+  "prompt": "We need a small Node helper for this — the requirments are in source/requirements.md. Put it in src/solution.mjs.",
+  "setup": {
+    "projectName": "Hotfix Flow Eval",
+    "about": "Self-contained eval project for hotfix-flow. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/src/solution.mjs.",
+    "missionObjectives": "Use the Hotfix Flow craftbook/template, read the seeded local fixtures, and write src/solution.mjs without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Hotfix Flow 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: hotfix-flow - Hotfix Flow.\n"
+      },
+      {
+        "path": "source/requirements.md",
+        "content": "# Runner Requirements\n\nBuild a dependency-free Node ESM helper for Boreal Desk support operations. Export at least one function. Include a tiny self-test section using node:assert or an equivalent assertion helper. Use fixture values for 18 -> 6 hour response time and 14.2 -> 8.9 refund leakage.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "src/solution.mjs is a local ESM module with basic self-test scaffolding.",
+    "deliverables": [
+      {
+        "path": "src/solution.mjs",
+        "kind": "code-with-tests",
+        "minBytes": 1500,
+        "checks": [
+          {
+            "kind": "esmImports",
+            "file": "src/solution.mjs"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "export\\s+(function|const|class)|export\\s*\\{",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "assert|test|describe|it|expect",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "18|6|14\\.2|8\\.9|Boreal",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "src/solution.mjs",
+      "kind": "typescript"
+    },
+    "axes": [
+      {
+        "name": "correctness",
+        "description": "The module does what the requirements ask, with sensible edge handling."
+      },
+      {
+        "name": "verification",
+        "description": "Self-tests exercise real behavior, not trivial truths."
+      },
+      {
+        "name": "clarity",
+        "description": "Exports, naming, and structure make the module usable without reading every line."
+      },
+      {
+        "name": "robustness",
+        "description": "Invalid input and boundary cases fail loudly rather than silently."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "runnable ESM",
+    "test scaffolding",
+    "local fixtures"
+  ]
+}

package/data/craftbook-templates/ht/html-arcade-game/versions/1.2.1/craftbook.json

@@ -0,0 +1,218 @@
+{
+  "id": "html-arcade-game",
+  "name": "HTML Arcade Game",
+  "description": "Build a playable single-file HTML/canvas arcade game (shooter, runner, dodger, etc.). Splits design into game-mechanics and visual look, builds, then evaluates against a playability bar and loops until it is actually fun and bug-free.\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. Game design (game-designer) — mechanics, controls, win/lose, difficulty → gated on artifact `design/game-design.md` (markdown-notes)\n2. Visual design (visual-designer) — palette, shapes/sprites, layout, juice → gated on artifact `design/visual-design.md` (markdown-notes)\n3. Build (developer) — implement the game in one index.html → gated on `index.html` (html-game)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "game-design",
+  "triggers": [
+    "arcade game",
+    "space shooter",
+    "html game",
+    "build a game"
+  ],
+  "steps": [
+    {
+      "id": "game-design",
+      "name": "Game design",
+      "description": "mechanics, controls, win/lose, difficulty",
+      "prompt": "Design the GAME, not the code. Decide: core mechanic (what the player does), controls (keys/mouse/touch), win and lose conditions, scoring, restart behavior, and the difficulty curve. Then write an **acceptance-criteria checklist** (4-8 concrete, checkable items, e.g. \"arrow keys move the ship\", \"colliding with an enemy ends the game\", \"score increments on hit\", \"restart resets the score\", \"game is playable for >30s without a JS error\"). Save the complete mechanics + checklist to artifact `design/game-design.md` with `write_artifact`, and summarize the path in task notes. No code, no visuals yet.",
+      "suggestedRole": "game-designer",
+      "advanceWhen": {
+        "file": "design/game-design.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "design/game-design.md",
+            "bytes": 600,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "design/game-design.md",
+            "sniff": "nonempty",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "design/game-design.md",
+            "pattern": "acceptance|criteria|checklist",
+            "flags": "i",
+            "label": "acceptance criteria",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "design/game-design.md",
+            "pattern": "control|input|keyboard|mouse|touch",
+            "flags": "i",
+            "label": "control scheme",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "design/game-design.md",
+            "pattern": "win|lose|game over|victory|defeat",
+            "flags": "i",
+            "label": "end-state rules",
+            "artifact": true
+          }
+        ],
+        "onReject": "game-design",
+        "maxAttempts": 3
+      },
+      "next": "visual-design"
+    },
+    {
+      "id": "visual-design",
+      "name": "Visual design",
+      "description": "palette, shapes/sprites, layout, juice",
+      "prompt": "Read artifact `design/game-design.md` with `read_artifact`, then decide how the game LOOKS. Pick a palette with exact color values, the canvas shapes or sprites for player/enemies/projectiles, the HUD layout (score, lives or timer), and at least one feedback effect (hit flash, screen shake, or particles). Keep it self-contained — canvas drawing or CSS, no external asset downloads. Save the concrete visual target to artifact `design/visual-design.md` with `write_artifact`, and summarize the path in task notes. Still no game code.",
+      "suggestedRole": "visual-designer",
+      "consumes": [
+        {
+          "file": "design/game-design.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "design/visual-design.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "design/visual-design.md",
+            "bytes": 450,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "design/visual-design.md",
+            "sniff": "nonempty",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "design/visual-design.md",
+            "pattern": "#[0-9a-f]{3,8}|rgb\\(|hsl\\(",
+            "flags": "i",
+            "label": "concrete palette",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "design/visual-design.md",
+            "pattern": "HUD|score|lives|timer",
+            "flags": "i",
+            "label": "HUD design",
+            "artifact": true
+          }
+        ],
+        "onReject": "visual-design",
+        "maxAttempts": 3
+      },
+      "next": "build"
+    },
+    {
+      "id": "build",
+      "name": "Build",
+      "description": "implement the game in one index.html",
+      "prompt": "Read artifacts `design/game-design.md` and `design/visual-design.md` with `read_artifact`. Implement the game in workspace `index.html` with `write_file` (inline CSS + JS) so it satisfies the acceptance criteria and matches the visual spec. Include a real game loop, real input handling, score/state, a visible win or lose state, and an in-page restart path. Keep it self-contained with no network assets. On a loop-back, fix only the gaps the reviewer named — do not regress criteria that already passed. `write_task_note` the workspace path and which criteria now pass.",
+      "suggestedRole": "developer",
+      "consumes": [
+        {
+          "file": "design/game-design.md",
+          "artifact": true
+        },
+        {
+          "file": "design/visual-design.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "index.html",
+        "minBytes": 1,
+        "sniff": "html-complete"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "index.html",
+            "bytes": 3200
+          },
+          {
+            "kind": "htmlLint",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "game\\s*-?\\s*over|you\\s+(?:win|won|lose|lost)|victory|defeat",
+            "flags": "i",
+            "label": "visible end state"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "restart|play\\s*again|new\\s*game|try\\s*again",
+            "flags": "i",
+            "label": "restart path"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkHtmlGame",
+            "scope": "standard",
+            "inputs": {
+              "file": "index.html"
+            }
+          },
+          {
+            "name": "checkJsParses",
+            "scope": "standard",
+            "inputs": {
+              "file": "index.html"
+            }
+          }
+        ],
+        "onReject": "build",
+        "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": "Read workspace `index.html` with `read_file` and actually exercise the game. If a browser/QA capability is available, load it, play it, test restart, and watch the console for errors; otherwise trace the game loop, input listeners, end-state transition, and reset path in source. Check every criterion from artifact `design/game-design.md` and write PASS/FAIL per criterion.\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: \"build\" })` 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": "index.html"
+        }
+      ],
+      "next": "build"
+    },
+    {
+      "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": "1.2.1",
+  "releasedAt": "2026-08-14T00:00:00Z"
+}