@bendyline/gilde 0.1.51 → 0.1.53

package/data/craftbook-templates/co/comprehensive-codebase-review/versions/1.0.1/test.json

@@ -0,0 +1,160 @@
+{
+  "schemaVersion": 1,
+  "title": "Comprehensive Codebase Review multi-dimension eval",
+  "objective": "Measure whether the review verifies planted architecture, duplication, hygiene, and lightweight-security problems in real source, states its index coverage honestly, and delivers a consultant report with a grounded scorecard, systemic themes, and a machine-readable findings file.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "Use the Comprehensive Codebase Review craftbook to do a deep, consultant-level review of this codebase and its architecture. Write the report to tasks/eval/codebase-review.md. Do not change source.",
+  "setup": {
+    "projectName": "Comprehensive Review Eval",
+    "about": "A small web service with deliberate problems in several dimensions: duplicated parsing logic, a hardcoded token, debug prints, dead code, and a leaky module boundary.",
+    "missionObjectives": "Verify problems in source across architecture, duplication, hygiene, and security; grade each dimension; separate quick wins from strategic work.",
+    "files": [
+      {
+        "path": "src/routes/orders.ts",
+        "content": "import { db } from '../storage/db';\nexport async function postOrder(req, res) {\n  // TODO: validate\n  // TODO: auth\n  // TODO: rate limit\n  const items = String(req.body.items || '');\n  const parsed = items.split(',').map(s => { const [sku, qty] = s.split(':'); return { sku: sku.trim(), qty: Number(qty || 1) }; });\n  console.log('DEBUG order', parsed);\n  const rows = await db.query(\"INSERT INTO orders (items) VALUES ('\" + items + \"')\");\n  res.json({ ok: true, rows });\n}\n"
+      },
+      {
+        "path": "src/routes/quotes.ts",
+        "content": "export async function postQuote(req, res) {\n  const items = String(req.body.items || '');\n  const parsed = items.split(',').map(s => { const [sku, qty] = s.split(':'); return { sku: sku.trim(), qty: Number(qty || 1) }; });\n  res.json({ quote: parsed.length * 10 });\n}\n"
+      },
+      {
+        "path": "src/storage/db.ts",
+        "content": "import { postOrder } from '../routes/orders';\nexport const API_TOKEN = 'sk-live-9f2a71c04d8e';\nexport const db = { query: async (sql) => { return [{ sql }]; } };\nexport function legacyMigrate() { /* unused since v2 */ return null; }\n"
+      },
+      {
+        "path": "test/quotes.test.ts",
+        "content": "test('quotes', async () => {\n  expect(1 + 1).toBe(2);\n});\n"
+      },
+      {
+        "path": "README.md",
+        "content": "# Order service\nA tiny order and quote service.\n"
+      }
+    ],
+    "worker": {
+      "name": "Rae",
+      "role": "Reviewer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "tasks/eval/codebase-review.md verifies the planted problems with real file citations, grades at least five dimensions, clusters findings into root-cause themes, and ships a machine-readable findings JSON beside it.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/codebase-review.md",
+        "kind": "markdown-report",
+        "artifact": true,
+        "minBytes": 2500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/codebase-review.md",
+            "pattern": "##\\s+Executive summary[\\s\\S]*##\\s+Scorecard[\\s\\S]*##\\s+Systemic themes[\\s\\S]*##\\s+Findings[\\s\\S]*##\\s+Quick wins",
+            "flags": "i",
+            "label": "consultant report sections",
+            "artifact": true
+          },
+          {
+            "kind": "tableShape",
+            "file": "tasks/eval/codebase-review.md",
+            "requiredColumns": [
+              "Dimension",
+              "Grade"
+            ],
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/codebase-review.md",
+            "pattern": "src/routes/(orders|quotes)\\.ts",
+            "flags": "i",
+            "label": "duplication evidence cites a real route file",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/codebase-review.md",
+            "pattern": "API_TOKEN|hard-?coded (secret|token|credential)",
+            "flags": "i",
+            "label": "the planted hardcoded token is found",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/codebase-review.md",
+            "pattern": "console\\.log|debug (print|logging|output)",
+            "flags": "i",
+            "label": "the planted debug print is found",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/codebase-review.md",
+            "pattern": "root[\\s-]?cause",
+            "flags": "i",
+            "label": "themes analyze root cause",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/codebase-review.md",
+            "pattern": "Index coverage",
+            "flags": "i",
+            "label": "index coverage is stated",
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/codebase-review-findings.json",
+        "kind": "json",
+        "artifact": true,
+        "minBytes": 100,
+        "checks": [
+          {
+            "kind": "sniff",
+            "file": "tasks/eval/codebase-review-findings.json",
+            "sniff": "json-valid",
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/codebase-review-findings.json",
+            "pattern": "\"severity\"[\\s\\S]*\"remediation\"",
+            "label": "structured findings with severity and remediation",
+            "artifact": true
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/codebase-review.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "verification",
+        "description": "Findings cite real files and lines; the duplicated parser, SQL string-building, hardcoded token, debug print, dead export, and storage-imports-routes boundary leak are found rather than invented."
+      },
+      {
+        "name": "synthesis",
+        "description": "Findings cluster into root-cause themes with blast radius; the scorecard grades follow the evidence."
+      },
+      {
+        "name": "actionability",
+        "description": "Quick wins are safe and bounded; strategic recommendations name seams, sequence, and behavior-preserving tests; deeper specialist reviews are suggested where warranted."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "verified findings across dimensions",
+    "honest coverage statement",
+    "consultant-grade prioritization"
+  ]
+}

package/data/craftbook-templates/co/config-scaffold/versions/1.0.3/craftbook.json

@@ -0,0 +1,215 @@
+{
+  "id": "config-scaffold",
+  "name": "Project Config Scaffold",
+  "description": "Bootstrap a project's configuration — the tooling, linter, formatter, tsconfig/compiler, scripts, and ignore files — into a coherent, conflict-free baseline that actually works together. Scopes the config surface FIRST — every tool, its config file, the settings, and how they must agree (formatter vs linter, strict compiler) — then writes the config files and scripts, then verifies the toolchain runs clean with no conflicts. Covers linter/formatter config, compiler/tsconfig, package scripts, editorconfig, gitignore, and ensuring tools do not fight each other.\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 config (planner) — lock the tools, files, settings, and agreements → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Write the config (developer) — create the config files + scripts to the plan → gated on `package.json` (json)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "scaffold project config",
+    "set up linting and formatting",
+    "bootstrap a project",
+    "create config files",
+    "tooling setup"
+  ],
+  "paramSchema": {
+    "type": "object",
+    "properties": {
+      "workPath": {
+        "type": "string",
+        "title": "Working folder",
+        "description": "Per-task working folder in the artifacts drawer. Defaults to this task's own folder so runs never collide; override with a stable name when you deliberately want runs to share files.",
+        "default": "{{task.dir}}"
+      }
+    }
+  },
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the config",
+      "description": "lock the tools, files, settings, and agreements",
+      "prompt": "Scope the configuration before writing files. Step 1: List the tools the project needs (formatter, linter, compiler/type-checker, test runner, etc.) and the config file each one reads. Step 2: For each, decide the key settings (e.g. strict compiler, line width, rule set). Step 3: Crucially, decide how the tools must AGREE so they do not fight — e.g. the linter defers formatting to the formatter, the compiler target matches the runtime. Step 4: Decide the package scripts (lint, format, typecheck, test, build) and the ignore files (.gitignore, tool ignores, .editorconfig). Step 5: Write a numbered acceptance-criteria checklist of 5-9 items (e.g. 'every script runs without error', 'formatter and linter do not conflict', 'the type-checker passes on the scaffold', 'ignore files exclude build output and deps'). `write_task_note` the config plan + checklist and write the same to the produces path.\n\nThe deliverable `{{workPath}}/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": "{{workPath}}/scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "scope",
+        "maxAttempts": 3
+      },
+      "next": "build",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "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": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "build",
+      "name": "Write the config",
+      "description": "create the config files + scripts to the plan",
+      "prompt": "Create the configuration files to the plan. Step 1: Write each tool's config file with the scoped settings, and the package manifest's scripts (lint/format/typecheck/test/build) wired to real commands. Step 2: Configure the linter and formatter to defer to each other so they do not conflict, and align the compiler target with the runtime. Step 3: Write the ignore files (.gitignore, tool-specific ignores, .editorconfig) excluding deps and build output. Step 4: Run each script (lint, format --check, typecheck) on the scaffold and confirm they pass without errors or conflicting complaints. Write the primary manifest/config to the produces path. On a loop-back, fix only the named conflict/gap. `write_task_note` the file paths and which criteria now pass.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "package.json",
+        "minBytes": 1,
+        "sniff": "json-valid"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "package.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "package.json"
+            }
+          }
+        ],
+        "onReject": "build",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web"
+        ],
+        "outputMedium": "workspace",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Run each configured script on the scaffold. For EACH acceptance criterion: confirm lint, format-check, typecheck, and build/test scripts run without error, confirm the formatter and linter do NOT fight each other (no rule both formats and lints in conflict), confirm the type-checker passes, and confirm ignore files exclude deps/build output. Write PASS/FAIL per criterion; a formatter-vs-linter conflict is a FAIL.\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": "package.json"
+        }
+      ],
+      "next": "build",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "task-note"
+      }
+    },
+    {
+      "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,
+      "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": "task-note"
+      }
+    }
+  ],
+  "version": "1.0.3",
+  "releasedAt": "2026-09-01T20:00:00Z",
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/co/config-scaffold/versions/1.0.3/test.json

@@ -0,0 +1,120 @@
+{
+  "schemaVersion": 1,
+  "title": "Project package config scaffold",
+  "objective": "Measure whether the config-scaffold craftbook scopes runtime/tooling choices and writes a coherent package.json.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "In the `Config Scaffold Eval` project, write `package.json` for a TypeScript Vite widget library called `harbor-widget-kit`. Include module type, exports, files, engines, scripts for dev/build/test/lint/typecheck, dependencies for @vitejs/plugin-react or vite/react as appropriate, devDependencies for TypeScript, Vitest, ESLint, and Prettier, and a packageManager field. Keep it valid JSON.",
+  "setup": {
+    "projectName": "Config Scaffold Eval",
+    "about": "Self-contained eval project for config-scaffold. The deliverable is workspace/package.json.",
+    "missionObjectives": "Produce a valid, coherent package.json scaffold for a TypeScript Vite widget library.",
+    "files": [],
+    "worker": {
+      "name": "Melle",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "package.json is valid JSON and includes the expected package metadata, scripts, engines, and tool dependencies.",
+    "deliverables": [
+      {
+        "path": "package.json",
+        "kind": "json",
+        "minBytes": 600,
+        "checks": [
+          {
+            "kind": "sniff",
+            "file": "package.json",
+            "sniff": "json-valid"
+          },
+          {
+            "kind": "contains",
+            "file": "package.json",
+            "pattern": "harbor-widget-kit",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "package.json",
+            "pattern": "scripts",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "package.json",
+            "pattern": "dev|build|test|lint|typecheck",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "package.json",
+            "pattern": "dependencies|devDependencies",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "package.json",
+            "pattern": "typescript|tsc",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "package.json",
+            "pattern": "vite",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "package.json",
+            "pattern": "vitest",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "package.json",
+            "pattern": "eslint|prettier",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "package.json",
+            "pattern": "engines|packageManager",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "package.json",
+      "kind": "json"
+    },
+    "axes": [
+      {
+        "name": "grounding",
+        "description": "Seeded facts appear faithfully and the source is cited."
+      },
+      {
+        "name": "structure",
+        "description": "Sections progress logically for the artifact class."
+      },
+      {
+        "name": "completeness",
+        "description": "Required elements (risks, next actions, scope) are all present."
+      },
+      {
+        "name": "tone",
+        "description": "The register fits the audience and artifact class."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "config completeness",
+    "tooling coherence",
+    "valid JSON"
+  ]
+}