@bendyline/gilde 0.1.54 → 0.1.56

package/data/craftbook-templates/pe/perf-optimization/versions/2.0.2/test.json

@@ -0,0 +1,235 @@
+{
+  "schemaVersion": 1,
+  "title": "Measured near-linear fix for a quadratic hot path",
+  "objective": "The craftbook drives a measured optimization of a seeded O(n^2) duplicate finder: baseline numbers recorded with their method, one bottleneck fixed at the real site, the same measurement re-run to prove the gain, and an enforced review — verified mechanically via a deterministic instrumented op-count budget, reference-equal results, and a green-suite run.",
+  "tags": [
+    "code",
+    "performance",
+    "tactical-fleet"
+  ],
+  "prompt": "Use the Targeted Performance Fix craftbook for this: support says importing a 200-row sheet crawls, and profiling points at findDuplicates - a 200-item list burns about 40,000 comparisons. The brief is in source/perf-brief.md. Get findDuplicates near-linear without changing its results.",
+  "setup": {
+    "projectName": "Sheet Importer",
+    "about": "A tiny sheet-import module with an instrumented duplicate finder. Tests run with `npm run test` (node --test).",
+    "files": [
+      {
+        "path": "package.json",
+        "content": "{\n  \"name\": \"sheet-importer\",\n  \"private\": true,\n  \"version\": \"1.0.0\",\n  \"type\": \"module\",\n  \"scripts\": {\n    \"test\": \"node --test\"\n  }\n}\n"
+      },
+      {
+        "path": "src/instrument.js",
+        "content": "let comparisons = 0;\n\nexport function countComparison() {\n  comparisons += 1;\n}\n\nexport function comparisonCount() {\n  return comparisons;\n}\n\nexport function resetComparisons() {\n  comparisons = 0;\n}\n"
+      },
+      {
+        "path": "src/find-duplicates.js",
+        "content": "import { countComparison } from './instrument.js';\n\nexport function findDuplicates(items) {\n  const duplicates = [];\n  for (let i = 0; i < items.length; i += 1) {\n    let count = 0;\n    for (let j = 0; j < items.length; j += 1) {\n      countComparison();\n      if (items[j] === items[i]) count += 1;\n    }\n    if (count > 1 && !duplicates.includes(items[i])) duplicates.push(items[i]);\n  }\n  return duplicates;\n}\n"
+      },
+      {
+        "path": "tests/duplicates.test.mjs",
+        "content": "import assert from 'node:assert/strict';\nimport { test } from 'node:test';\nimport { findDuplicates } from '../src/find-duplicates.js';\n\ntest('reports each duplicate once, in first-appearance order', () => {\n  assert.deepEqual(findDuplicates(['a', 'b', 'a', 'c', 'b']), ['a', 'b']);\n});\n\ntest('returns empty for unique lists', () => {\n  assert.deepEqual(findDuplicates(['x', 'y', 'z']), []);\n});\n\ntest('order pins to first appearance, not second occurrence', () => {\n  assert.deepEqual(findDuplicates(['a', 'b', 'b', 'a']), ['a', 'b']);\n});\n"
+      },
+      {
+        "path": "source/perf-brief.md",
+        "content": "# Performance brief\n\nSupport reports that importing a 200-row sheet crawls. Profiling points at `findDuplicates` in src/find-duplicates.js: for a 200-item list it performs about 40,000 instrumented comparisons (200 x 200 full rescans). The counter lives in src/instrument.js - `comparisonCount()` reads it, `resetComparisons()` clears it.\n\nTarget: get `findDuplicates` near-linear - well under 2,000 instrumented comparisons for a 200-item list - WITHOUT changing its results. Each duplicated value is reported once, in order of FIRST appearance.\n\nRules:\n\n- src/instrument.js is measurement infrastructure; leave it exactly as it is.\n- Keep the measurement honest: keep calling `countComparison()` for every equality comparison the new implementation still performs. Deleting instrumentation instead of deleting work is measurement theater.\n- Measure with a repeatable command: a small script that builds a 200-item list, calls `findDuplicates`, and prints `comparisonCount()`.\n"
+      },
+      {
+        "path": "tests/verify-perf.mjs",
+        "content": "import assert from 'node:assert/strict';\nimport { execFileSync } from 'node:child_process';\nimport { findDuplicates } from '../src/find-duplicates.js';\nimport { comparisonCount, resetComparisons } from '../src/instrument.js';\n\n// Independent reference: each duplicated value once, first-appearance order.\nfunction referenceDuplicates(items) {\n  const counts = new Map();\n  for (const item of items) counts.set(item, (counts.get(item) ?? 0) + 1);\n  const out = [];\n  const added = new Set();\n  for (const item of items) {\n    if ((counts.get(item) ?? 0) > 1 && !added.has(item)) {\n      added.add(item);\n      out.push(item);\n    }\n  }\n  return out;\n}\n\n// 1) Results identical to reference on small pinned cases.\nassert.deepEqual(findDuplicates(['a', 'b', 'a', 'c', 'b']), ['a', 'b']);\nassert.deepEqual(findDuplicates([]), []);\nassert.deepEqual(findDuplicates(['a', 'b', 'b', 'a']), ['a', 'b']);\n\n// 2) Deterministic 200-item workload: results equal reference AND the\n// instrumented op-count is under the stated budget (seeded code: 40000).\nconst items = [];\nfor (let i = 0; i < 200; i += 1) items.push('v' + ((i * 7) % 149));\nresetComparisons();\nconst result = findDuplicates(items);\nassert.deepEqual(result, referenceDuplicates(items), 'results changed - speed that changes answers is a bug');\nconsole.log('PERF_OPTIMIZATION_ORACLE results ok');\nconst ops = comparisonCount();\nassert.ok(\n  ops <= 2000,\n  'findDuplicates on 200 items performed ' + ops + ' instrumented comparisons - the budget is 2000 and the seeded code did 40000',\n);\nconsole.log('PERF_OPTIMIZATION_ORACLE ops ' + ops + ' within budget');\n\n// 3) The whole suite is green on the optimized tree (real run).\nfunction runSuite(cwd) {\n  try {\n    execFileSync(process.execPath, ['--test'], { cwd, stdio: 'pipe', timeout: 30000 });\n    return 0;\n  } catch (err) {\n    return typeof err.status === 'number' ? err.status : 1;\n  }\n}\nassert.equal(runSuite(process.cwd()), 0, 'the suite must be green on the optimized tree');\nconsole.log('PERF_OPTIMIZATION_ORACLE suite green');\nconsole.log('PERF_OPTIMIZATION_ORACLE done');\n",
+        "surface": "harness"
+      }
+    ],
+    "craftbookParams": {
+      "scope": "findDuplicates in src/find-duplicates.js does about 40,000 instrumented comparisons for a 200-item list; get it near-linear (well under 2,000 comparisons) without changing its results. See source/perf-brief.md."
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "The quadratic rescan is gone, the instrumented op-count for 200 items is under budget, results are identical to the reference on a deterministic workload, the suite is green on a real run, and every fleet artifact exists with honest numbers and citations.",
+    "deliverables": [
+      {
+        "path": "{{task.dir}}/baseline.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/baseline.md",
+            "pattern": "^##\\s+Current behavior[\\s\\S]*^##\\s+Measurements[\\s\\S]*^##\\s+Guardrail",
+            "flags": "im",
+            "label": "baseline sections in order"
+          },
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/baseline.md",
+            "pattern": "^##\\s+Measurements[\\s\\S]*\\d",
+            "flags": "im",
+            "label": "baseline numbers recorded"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "{{task.dir}}/baseline.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/plan.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/plan.md",
+            "pattern": "^##\\s+Target[\\s\\S]*^##\\s+Stages[\\s\\S]*^##\\s+Acceptance criteria",
+            "flags": "im",
+            "label": "plan sections in order"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "{{task.dir}}/plan.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/change-notes.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 600,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/change-notes.md",
+            "pattern": "^##\\s+Stages executed[\\s\\S]*^##\\s+Files touched[\\s\\S]*^##\\s+Deviations from plan",
+            "flags": "im",
+            "label": "change-notes sections in order"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "{{task.dir}}/change-notes.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/verification.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/verification.md",
+            "pattern": "^##\\s+Before\\s*/\\s*after[\\s\\S]*^##\\s+Suite[\\s\\S]*^##\\s+Result",
+            "flags": "im",
+            "label": "verification sections in order"
+          },
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/verification.md",
+            "pattern": "^##\\s+Before\\s*/\\s*after[\\s\\S]*\\d",
+            "flags": "im",
+            "label": "both numbers quoted"
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/review.md",
+        "kind": "markdown-report",
+        "artifact": true,
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/review.md",
+            "pattern": "Verdict:\\s*(?:PASS|REVISE)",
+            "flags": "i",
+            "label": "explicit reviewer verdict"
+          }
+        ]
+      }
+    ],
+    "checks": [
+      {
+        "kind": "notContains",
+        "file": "src/find-duplicates.js",
+        "pattern": "for\\s*\\(let j = 0; j < items\\.length",
+        "label": "the seeded inner full-list rescan is gone"
+      },
+      {
+        "kind": "sourceParses",
+        "file": "src/find-duplicates.js"
+      },
+      {
+        "kind": "nodeScriptPasses",
+        "script": "tests/verify-perf.mjs",
+        "timeoutMs": 60000,
+        "requiredOutput": [
+          {
+            "pattern": "PERF_OPTIMIZATION_ORACLE results ok",
+            "label": "results identical to the reference"
+          },
+          {
+            "pattern": "PERF_OPTIMIZATION_ORACLE ops \\d+ within budget",
+            "label": "instrumented op-count under the stated budget"
+          },
+          {
+            "pattern": "PERF_OPTIMIZATION_ORACLE suite green",
+            "label": "suite green on the optimized tree"
+          }
+        ]
+      }
+    ],
+    "taskNotes": {
+      "minBytes": 120,
+      "checks": [
+        {
+          "kind": "contains",
+          "file": "task-notes.md",
+          "pattern": "\\bDONE\\b[\\s\\S]*(npm\\s+run\\s+test|node\\s+--test)",
+          "flags": "i",
+          "label": "DONE note names the real test command"
+        }
+      ]
+    },
+    "taskGraph": {
+      "requireCraftbookTask": true,
+      "requireTerminalStep": true
+    },
+    "unchangedFixtures": [
+      "source/perf-brief.md",
+      "package.json",
+      "src/instrument.js"
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "{{task.dir}}/verification.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "Measurement honesty",
+        "description": "Baseline numbers were gathered by a stated, repeatable method before the change, and verification re-ran the identical method and quoted both figures side by side - no adjectives standing in for numbers, no swapped workload."
+      },
+      {
+        "name": "Bottleneck focus",
+        "description": "One bottleneck was named with its mechanism and fixed at the real site by that mechanism - not a synthetic proxy, a weakened measurement, or scattered micro-tweaks."
+      },
+      {
+        "name": "Correctness under speed",
+        "description": "Results stayed identical on the same inputs, the suite stayed green between stages with real receipts, and residual risk or unverified claims are labeled honestly."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "numbers with their method",
+    "same-method re-measurement",
+    "enforced review loop"
+  ]
+}

package/data/craftbook-templates/pe/pest-diagnosis/versions/1.0.3/test.json

@@ -27,6 +27,9 @@
     "worker": {
       "name": "Wim",
       "role": "Gardener"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
     }
   },
   "mocks": [],
@@ -42,51 +45,59 @@
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
-            "flags": "i"
+            "flags": "i",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "likely|probable|possible|suspect",
             "flags": "i",
-            "label": "candidates stated as likelihoods, not verdicts"
+            "label": "candidates stated as likelihoods, not verdicts",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "caterpillar",
             "flags": "i",
-            "label": "engages the caterpillar evidence from the kale photo note"
+            "label": "engages the caterpillar evidence from the kale photo note",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "treat",
             "flags": "i",
-            "label": "treatment ladder present"
+            "label": "treatment ladder present",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "monitor|watch|check",
             "flags": "i",
-            "label": "monitoring plan present"
+            "label": "monitoring plan present",
+            "artifact": true
           },
           {
             "kind": "notContains",
             "file": "tasks/eval/report.md",
             "pattern": "(definitely|guaranteed|certainly) (is|will cure)",
             "flags": "i",
-            "label": "diagnosis stays hedged, never absolute"
+            "label": "diagnosis stays hedged, never absolute",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "extension|professional|nursery|expert",
             "flags": "i",
-            "label": "escalation path named"
+            "label": "escalation path named",
+            "artifact": true
           }
-        ]
+        ],
+        "artifact": true
       }
     ]
   },

package/data/craftbook-templates/pl/plan/versions/1.0.2/craftbook.json

@@ -0,0 +1,222 @@
+{
+  "id": "plan",
+  "name": "Plan",
+  "description": "Author a PLAN for a piece of work as a reviewable **draft task** — the gezel equivalent of `/plan` in other tools.\n\nUnlike a normal craftbook, this one's deliverable is not a workspace file: it's a high-quality *draft task* (a plan) that the user reviews and then activates to run. Invoke it via the `start_plan` tool, which creates the draft and an authoring task that walks this craftbook. The authoring gates inspect the draft being built (via the authoring task's `craftbookParams.draftRef`), so a weak model can't skip the parts that make a plan good.\n\nSteps:\n\n1. **Frame the goal** (planner) — write a strong \"about\" on the draft and set 3–8 concrete **outcomes** (what should be created or updated at success). Gated by `checkPlanFramed`.\n2. **Design the build steps** (planner) — add ordered build steps to the draft, each given a concrete static deliverable + enforced gate via `set_step_deliverable`. Gated by `checkStepsHaveDeliverables`.\n3. **Add the verification step** (planner) — append a terminal step (via `add_verification_step`) that confirms every outcome with evidence before the task can close. Gated by `checkVerificationStep`.\n4. **Review the plan** (planner) — sanity-check the whole graph. Gated by `checkPlanReady`, which returns one list of any remaining gaps.\n5. **Hand off to the user** (planner, terminal) — summarize the plan and tell the user to review and **activate** it.\n\nWhen activated (draft → active), the produced task runs its build steps — each looping back on a missed deliverable — and its terminal step verifies the outcomes were kept.\n",
+  "entryStepId": "frame",
+  "triggers": [
+    "plan this",
+    "make a plan",
+    "plan for",
+    "/plan"
+  ],
+  "steps": [
+    {
+      "id": "frame",
+      "name": "Frame the goal",
+      "description": "Write a strong 'about' and set the outcomes on the draft plan.",
+      "prompt": "You are drafting a PLAN. The plan is a separate **draft task** — its ref is in your task's `craftbookParams.draftRef` (shown in your task description / entry note). Everything you author here targets that draft using the exact draft ref.\n\n**Do two things:**\n\n1. **Write a strong \"about\".** Call `update_task({ ref: \"<draftRef>\", description })` with a clear job-to-be-done from the user's perspective — what success looks like, in 120+ characters.\n2. **Set the outcomes.** Call `set_outcomes({ task: \"<draftRef>\", outcomes: [ ... ] })` with 3–8 concrete, individually-verifiable statements of what should be **created or updated** at completion (e.g. \"An index.html with a playable snake game and a game-over/restart screen\", \"A README documenting how to run it\").\n\nWhen done, call `advance_task_step({ ref, stepId: \"frame\", next: \"outline\" })`. The gate rejects until the draft has a real about and at least 3 outcomes — fix what it names and advance again.",
+      "suggestedRole": "planner",
+      "gate": {
+        "at": "completion",
+        "scripts": [
+          {
+            "name": "checkPlanFramed",
+            "scope": "standard",
+            "inputs": {}
+          }
+        ],
+        "onReject": "frame",
+        "maxAttempts": 4
+      },
+      "next": "outline",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "none"
+      }
+    },
+    {
+      "id": "outline",
+      "name": "Design the build steps",
+      "description": "Add ordered build steps to the draft, each gated on a concrete static deliverable.",
+      "prompt": "Design the implementation as an ordered series of **build steps** on the draft (`craftbookParams.draftRef`). Each build step must produce a **concrete static file** with an enforced gate.\n\nThe draft starts with one placeholder step named **\"Implement\"**. First call `craftbook_read({ task: \"<draftRef>\" })` and note the actual id of that placeholder step. Then either:\n- repurpose that exact step with `craftbook_update_step({ task: \"<draftRef>\", stepId: \"<actualId>\", name, prompt, suggestedRole })`, then immediately call `set_step_deliverable({ task: \"<draftRef>\", stepId: \"<actualId>\", path, kind })`; or\n- remove that exact step with `craftbook_remove_step({ task: \"<draftRef>\", stepId: \"<actualId>\" })` after you have added the real build steps.\n\nFor each added step, in order:\n1. `craftbook_add_step({ task: \"<draftRef>\", name, prompt, suggestedRole })` — a concrete, instructive step (e.g. name \"Build the game\", role \"developer\", a prompt that says exactly what to make).\n2. Call `craftbook_read({ task: \"<draftRef>\" })` and use the actual id of the step you just added.\n3. `set_step_deliverable({ task: \"<draftRef>\", stepId: \"<actualId>\", path, kind })` — declare the named file it produces and auto-attach the gate. Pick `kind` to match the artifact: `html-page` / `html-game` / `markdown-report` / `code-with-tests` / `json` / etc.\n\nDo not invent step ids like `build` unless `craftbook_read` shows that exact id. Do not advance while any build step lacks `advanceWhen`/`gate`. Order the steps so each builds on the last. When every build step has a deliverable, call `advance_task_step({ ref, stepId: \"outline\", next: \"verify-step\" })`. The gate lists any step still missing a deliverable.",
+      "suggestedRole": "planner",
+      "gate": {
+        "at": "completion",
+        "scripts": [
+          {
+            "name": "checkStepsHaveDeliverables",
+            "scope": "standard",
+            "inputs": {}
+          }
+        ],
+        "onReject": "outline",
+        "maxAttempts": 4
+      },
+      "next": "verify-step",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "none"
+      }
+    },
+    {
+      "id": "verify-step",
+      "name": "Add the verification step",
+      "description": "Append a terminal verification step that checks the outcomes were kept.",
+      "prompt": "Add the final **verification step** to the draft (`craftbookParams.draftRef`): call `add_verification_step({ task: \"<draftRef>\" })`. This appends a terminal step — gated by `checkOutcomesMet` — that makes the executor confirm each outcome (with evidence) before the task can close. Pass a custom `prompt` only if you need domain-specific verification instructions.\n\nThen call `advance_task_step({ ref, stepId: \"verify-step\", next: \"review\" })`. The gate rejects until the draft has a terminal step that verifies the outcomes.",
+      "suggestedRole": "planner",
+      "gate": {
+        "at": "completion",
+        "scripts": [
+          {
+            "name": "checkVerificationStep",
+            "scope": "standard",
+            "inputs": {}
+          }
+        ],
+        "onReject": "verify-step",
+        "maxAttempts": 4
+      },
+      "next": "review",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "none"
+      }
+    },
+    {
+      "id": "review",
+      "name": "Review the plan",
+      "description": "Sanity-check the whole plan before handing it to the user.",
+      "prompt": "Final check before handing the plan to the user. `craftbook_read({ task: \"<draftRef>\" })` and sanity-check: the steps are ordered sensibly, each build step has a deliverable, and the last step verifies the outcomes. Fix anything off with the `craftbook_*` / `set_step_deliverable` tools on the draft.\n\nWhen the plan is solid, call `advance_task_step({ ref, stepId: \"review\", next: \"done\" })`. The gate returns a single list of anything still missing (thin about, fewer than 3 outcomes, ungated steps, or no verification step).",
+      "suggestedRole": "planner",
+      "gate": {
+        "at": "completion",
+        "scripts": [
+          {
+            "name": "checkPlanReady",
+            "scope": "standard",
+            "inputs": {}
+          }
+        ],
+        "onReject": "review",
+        "maxAttempts": 4
+      },
+      "next": "done",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "none"
+      }
+    },
+    {
+      "id": "done",
+      "name": "Hand off to the user",
+      "description": "Summarize the plan and tell the user to review and activate it.",
+      "prompt": "The plan is ready. Summarize it for the user in your reply: mention the draft task **<draftRef>** by its ref (so it renders as a reviewable plan card), and recap the about, the outcomes, and the build steps. Tell the user they can **review and activate** the plan to run it — or ask you to tweak it first. Then report DONE.",
+      "suggestedRole": "planner",
+      "terminal": true,
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "none"
+      }
+    }
+  ],
+  "version": "1.0.2",
+  "releasedAt": "2026-09-04T13:46:25Z"
+}

package/data/craftbook-templates/pl/plan/versions/1.0.2/test.json

@@ -0,0 +1,91 @@
+{
+  "schemaVersion": 1,
+  "title": "Reviewable draft task plan",
+  "objective": "Measure whether the plan craftbook creates a real draft task with a substantial about, concrete outcomes, gated build steps, and a terminal verification step.",
+  "tags": [
+    "planning"
+  ],
+  "prompt": "In the `Plan Eval` project, author a reviewable draft plan for building a self-contained `index.html` bug triage board for a small support team. The eventual board should let users add bugs, assign severity, filter open/closed items, and show a summary. Use the plan flow/start_plan rather than building the board now: the output should be a draft task with strong outcomes, ordered gated build steps, and a final verification step for the user to review and activate. Important: every non-terminal build step on the draft, including the initial placeholder step if you keep or rename it, must get `set_step_deliverable({ task: \"<draftRef>\", stepId, path: \"index.html\", kind: \"html-page\" })` before you finish.",
+  "setup": {
+    "projectName": "Plan Eval",
+    "about": "Self-contained eval project for the plan craftbook. The deliverable is a reviewable draft task, not workspace files.",
+    "missionObjectives": "Author a high-quality draft task plan for a bug triage board, including outcomes, gated build steps, and verification before activation. A build step is not gated until set_step_deliverable is called on that exact step.",
+    "files": [],
+    "worker": {
+      "name": "Pieter",
+      "role": "Planner"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "A task sourced from the plan craftbook points to a draft task with outcomes, gated build steps, and terminal verification.",
+    "taskGraph": {
+      "checks": [
+        {
+          "kind": "contains",
+          "file": "task-graph.md",
+          "pattern": "index.html",
+          "flags": "i"
+        },
+        {
+          "kind": "contains",
+          "file": "task-graph.md",
+          "pattern": "bug|triage",
+          "flags": "i"
+        },
+        {
+          "kind": "contains",
+          "file": "task-graph.md",
+          "pattern": "severity",
+          "flags": "i"
+        },
+        {
+          "kind": "contains",
+          "file": "task-graph.md",
+          "pattern": "verify|outcome|evidence",
+          "flags": "i"
+        }
+      ],
+      "requireCraftbookTask": true,
+      "requireDraftRef": true,
+      "draft": {
+        "status": "draft",
+        "minDescriptionBytes": 120,
+        "minOutcomes": 3,
+        "minSteps": 3,
+        "requireTerminalVerification": true,
+        "requireGatedBuildSteps": true
+      }
+    }
+  },
+  "rubric": {
+    "artifact": {
+      "path": "task-graph.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "decomposition",
+        "description": "The draft breaks the goal into ordered steps a crew could actually execute."
+      },
+      {
+        "name": "outcomes",
+        "description": "Outcomes are concrete and checkable rather than restatements of the goal."
+      },
+      {
+        "name": "gating",
+        "description": "Build steps carry a deliverable so progress is verifiable, and verification comes last."
+      },
+      {
+        "name": "grounding",
+        "description": "The plan reflects the requested scope — no invented requirements, none dropped."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "task-native deliverable",
+    "outcomes",
+    "gated build steps",
+    "verification step"
+  ]
+}