@bendyline/gilde 0.1.38 → 0.1.39

package/data/craftbook-templates/ch/chrome-extension/versions/1.0.2/test.json

@@ -0,0 +1,100 @@
+{
+  "schemaVersion": 1,
+  "title": "Browser Extension smoke eval",
+  "objective": "Self-contained smoke eval for the Browser Extension 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": "Browser Extension Eval",
+    "about": "Self-contained eval project for chrome-extension. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/index.html.",
+    "missionObjectives": "Use the Browser Extension 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": "# Browser Extension 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: chrome-extension - Browser Extension.\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"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "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"
+  ]
+}

package/data/craftbook-templates/ci/ci-pipeline/versions/1.0.2/craftbook.json

@@ -0,0 +1,144 @@
+{
+  "id": "ci-pipeline",
+  "name": "CI Pipeline from Scratch",
+  "description": "Build a continuous-integration pipeline that installs, lints, tests, and builds on every push/PR — fast, cached, and gating merges on green. Scopes the pipeline contract FIRST — triggers, the job/stage graph, the matrix, caching strategy, and the gates — then writes the CI workflow YAML, then a reviewer validates the syntax, stage ordering, caching, and that it actually fails on a broken build. Covers CI triggers, job/stage dependencies, dependency caching, build matrices, status checks, fail-fast gating, and a valid workflow file.\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 pipeline (planner) — lock triggers, stages, matrix, caching, gates → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Write the workflow (developer) — implement the CI workflow YAML → gated on `.github/workflows/ci.yml` (yaml-spec)\n3. Verify the workflow (reviewer) — confirm syntax, ordering, caching, gating → gated on artifact `{{workPath}}/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": "scope",
+  "triggers": [
+    "set up ci",
+    "create a ci pipeline",
+    "github actions workflow",
+    "build a ci/cd pipeline",
+    "add automated testing on push"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the pipeline",
+      "description": "lock triggers, stages, matrix, caching, gates",
+      "prompt": "Scope the CI pipeline before writing YAML. Step 1: Decide the triggers (push to which branches, pull requests, manual). Step 2: Lay out the job/stage graph: install → lint → test → build, including which stages can run in parallel and which depend on others. Step 3: Decide the matrix (e.g. OS/runtime versions) and the caching strategy (cache the dependency store keyed on the lockfile) to keep runs fast. Step 4: Define the gates: which stages must pass to mark the check green and block a merge, and fail-fast behavior. Step 5: Write a numbered acceptance-criteria checklist of 5-9 items (e.g. 'the workflow triggers on push and PR', 'dependencies are cached', 'a failing test fails the pipeline and blocks merge', 'lint/test/build run in a sensible order'). `write_task_note` the scope + 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"
+    },
+    {
+      "id": "build",
+      "name": "Write the workflow",
+      "description": "implement the CI workflow YAML",
+      "prompt": "Author the CI workflow file to the scope. Step 1: Set the triggers and the matrix exactly as scoped. Step 2: Define the jobs/stages with their dependency edges (test depends on install, etc.) and a checkout + runtime-setup step. Step 3: Add dependency caching keyed on the lockfile so repeat runs are fast. Step 4: Run lint, test, and build as gating steps so any non-zero exit fails the job. Step 5: Ensure the file is valid YAML for the target CI system and that the failing-test case would actually fail the run. Write the workflow to the produces path. On a loop-back, fix only the named gaps. `write_task_note` the file path and which criteria now pass.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": ".github/workflows/ci.yml",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": ".github/workflows/ci.yml",
+            "bytes": 200
+          },
+          {
+            "kind": "sniff",
+            "file": ".github/workflows/ci.yml",
+            "sniff": "nonempty"
+          }
+        ],
+        "onReject": "build",
+        "maxAttempts": 3
+      },
+      "next": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify the workflow",
+      "description": "confirm syntax, ordering, caching, gating",
+      "prompt": "Verify the CI workflow. Step 1: Confirm the file parses as valid YAML and conforms to the target CI system's schema (lint it if a linter is available). Step 2: Confirm the triggers, matrix, and stage-dependency ordering match the scope. Step 3: Confirm caching is wired to the lockfile and the cache key is sensible. Step 4: Trace the gating logic and confirm a failing lint/test/build step would fail the run and block a merge (no `continue-on-error` masking failures). Write a verification note with the YAML-validity result and the gating trace to the produces path.\n\nThe deliverable `{{workPath}}/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",
+      "advanceWhen": {
+        "file": "{{workPath}}/verify.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": ".github/workflows/ci.yml",
+            "bytes": 200
+          },
+          {
+            "kind": "sniff",
+            "file": ".github/workflows/ci.yml",
+            "sniff": "nonempty"
+          }
+        ],
+        "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": "Validate the workflow file. For EACH acceptance criterion: confirm it is valid YAML for the target CI system, confirm triggers/matrix/stage-ordering match the scope, confirm dependency caching is wired correctly, and confirm a failing test would fail the pipeline and block merge (nothing masks failures). 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": ".github/workflows/ci.yml"
+        }
+      ],
+      "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": "1.0.2",
+  "releasedAt": "2026-08-21T00:00:00Z",
+  "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}}"
+      }
+    }
+  },
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/ci/ci-pipeline/versions/1.0.2/test.json

@@ -0,0 +1,165 @@
+{
+  "schemaVersion": 1,
+  "title": "CI Pipeline from Scratch smoke eval",
+  "objective": "Self-contained smoke eval for the CI Pipeline from Scratch craftbook using the external generic harness.",
+  "tags": [
+    "external"
+  ],
+  "prompt": "Theres a fake ops service wired up for this so nothing real gets touched — the endpoints are in mocks/services.md, and the ready-made mock-probe script talks to them for you. Can you run the automation against it and write up how it went in automation.md?",
+  "setup": {
+    "projectName": "CI Pipeline from Scratch Eval",
+    "about": "Self-contained eval project for ci-pipeline. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/automation.md.",
+    "missionObjectives": "Use the CI Pipeline from Scratch craftbook/template, read the seeded local fixtures, and write automation.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# CI Pipeline from Scratch 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: ci-pipeline - CI Pipeline from Scratch.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [
+    {
+      "kind": "http",
+      "id": "ops",
+      "description": "Fake operations service for this eval. GET /api/bookings/open lists the open work items; POST /api/bookings/dry-run records a simulated submission and returns DRY_RUN_OK.",
+      "credential": {
+        "name": "mock.ops"
+      },
+      "routes": [
+        {
+          "method": "GET",
+          "path": "/api/bookings/open",
+          "body": {
+            "items": [
+              "BKG-1001",
+              "BKG-1002",
+              "BKG-1003"
+            ]
+          }
+        },
+        {
+          "method": "POST",
+          "path": "/api/bookings/dry-run",
+          "status": 201,
+          "body": {
+            "status": "DRY_RUN_OK",
+            "recorded": 3
+          }
+        }
+      ]
+    },
+    {
+      "kind": "webhook",
+      "id": "notify",
+      "description": "Notification receiver. POST a JSON completion notice here when the run finishes.",
+      "path": "/hooks/notify"
+    },
+    {
+      "kind": "cli",
+      "id": "probe",
+      "description": "Provenance-trusted project script `mock-probe` that exercises the fake ops service through http.authed and returns the raw responses.",
+      "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 ops service for this eval: lists the open work items and records a dry-run submission. Outputs the raw JSON responses as evidence for the write-up.',\n  inputs: {},\n  outputs: {\n    open: { type: 'string', description: 'Raw JSON body from the open-items listing.' },\n    dryRun: { type: 'string', description: 'Raw JSON body from the dry-run submission.' },\n  },\n  requires: ['workspace.read', 'network', 'credential:mock.ops'],\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 \"${id}\" is not listed in mocks/services.json`);\n  return service.baseUrl;\n};\n\nconst open = await gezel.http.authed(`${base('ops')}/api/bookings/open`, {\n  credential: 'mock.ops',\n});\nif (!open.ok) throw new Error(`open-items listing failed: ${open.status} ${open.body}`);\n\nconst dryRun = await gezel.http.authed(`${base('ops')}/api/bookings/dry-run`, {\n  credential: 'mock.ops',\n  method: 'POST',\n  body: JSON.stringify({ items: JSON.parse(open.body).items, mode: 'dry-run' }),\n});\nif (!dryRun.ok) throw new Error(`dry-run submission failed: ${dryRun.status} ${dryRun.body}`);\n\ngezel.output({ open: open.body, dryRun: dryRun.body });\n"
+      }
+    }
+  ],
+  "success": {
+    "summary": "automation.md is grounded in live fake-service responses: the open items were actually listed and a dry-run actually recorded (request-log assertions), with safety guards and signals described.",
+    "deliverables": [
+      {
+        "path": "automation.md",
+        "kind": "markdown-report",
+        "minBytes": 900,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "DRY_RUN_OK|dry-run|dry run",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "fake-ci|fake-github|/api/bookings",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "no real|credentials|safety|guard",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "success|failure|retry|abort",
+            "flags": "i"
+          }
+        ]
+      }
+    ],
+    "mocks": [
+      {
+        "service": "ops",
+        "minRequests": 2,
+        "requiredPaths": [
+          "^/api/bookings/open$",
+          "^/api/bookings/dry-run$"
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "automation.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "safety",
+        "description": "Dry-run posture is explicit: no real credentials, clear stop-before-side-effect boundary."
+      },
+      {
+        "name": "mapping",
+        "description": "Fake endpoints/commands are mapped completely to the workflow steps."
+      },
+      {
+        "name": "signals",
+        "description": "Success, failure, retry, and abort conditions are all defined."
+      },
+      {
+        "name": "containment",
+        "description": "The plan cannot accidentally reach a real service from a mock context."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "dry-run safety",
+    "fake tool mapping",
+    "side-effect containment"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "ci-pipeline-fake-service-fixture",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local fake service contract replacing live CLIs, HTTP APIs, credentials, and side effects."
+      }
+    ]
+  }
+}

package/data/craftbook-templates/ci/citation-audit/versions/1.0.2/craftbook.json

@@ -0,0 +1,158 @@
+{
+  "id": "citation-audit",
+  "name": "Citation Audit",
+  "description": "Audit an existing document's claims against its citations and report every mismatch: a reviewer pairs each cited claim with the citation it depends on and locks the audit rubric, a researcher opens each cited source and verifies the claim is actually supported, and a reviewer compiles a per-citation audit report with verdicts and fixes. The ordering matters because auditing without first pairing claims to citations misses unsupported claims, and a report without a fixed verdict scale is inconsistent; building the claim-citation pairing and rubric first makes the audit exhaustive and the report actionable. Use this for checking that citations support their claims, source-verification of a draft, catching citation drift or unsupported statements, and 'do these references actually back up the text' reviews.\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 audit (reviewer) — pair each cited claim to its citation + lock the rubric → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Verify each citation (researcher) — open each source, confirm it backs the paired claim → gated on artifact `{{workPath}}/verify.md` (markdown-notes)\n3. Compile the audit report (reviewer) — per-citation verdicts, justifying quotes, and fixes → gated on artifact `{{workPath}}/audit.md` (markdown-report)\n\nSource discipline:\n\n- Audit only claims that appear in the supplied draft or source bundle.\n- Keep the draft's citation labels verbatim, such as `Claim [A]`, so each verdict is traceable.\n- Treat uncited factual sentences in the draft as `Uncited-Claim`; do not create new claims to make the report longer.\n- If a source excerpt is missing or contradicts the draft, say that directly and propose a correction or citation fix.\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "audit the citations",
+    "check citations support the claims",
+    "verify the references in this doc",
+    "citation accuracy check",
+    "are these sources legit"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the audit",
+      "description": "pair each cited claim to its citation + lock the rubric",
+      "prompt": "1. Read the target document and build a pairing table in {{workPath}}/scope.md: for every inline citation, record a pair id (P1, P2, ...), the exact claim sentence it supports, and the citation/reference it points to. 2. Also flag every factual claim that has NO citation as a candidate (these are audit findings too). 3. Lock the verdict rubric: Supported (source clearly backs the claim), Partially-Supported (source backs part / overstates), Not-Supported (source does not back it), Source-Missing/Dead (citation cannot be located), Uncited-Claim. 4. Write an acceptance-criteria checklist (e.g. 'every inline citation is paired and audited', 'uncited factual claims are listed', 'each pair gets exactly one verdict from the rubric', 'each Not-Supported/Partial verdict quotes the source to justify it', 'a fix is proposed per problem'). 5. Record decisions. Call write_task_note with the pairing table + rubric + checklist; write the same to {{workPath}}/scope.md.\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": "reviewer",
+      "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": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify each citation",
+      "description": "open each source, confirm it backs the paired claim",
+      "prompt": "1. For each pair id, locate and open the cited source and read the relevant part. 2. Log to {{workPath}}/verify.md: the pair id, whether the source was reachable, the exact passage/figure the claim relies on (quote it), and a proposed verdict from the locked rubric with a one-line reason. 3. Be strict: a source on the right topic that does not actually state the specific claim is Not-Supported, not Supported. 4. For dead or unfindable citations, record Source-Missing/Dead and what you searched. 5. For each problem, draft a concrete fix (correct the claim, swap the source, or add a citation). Good looks like a verify log where every pair's verdict is justified by a quote. Do not write the final report yet.\n\nThe deliverable `{{workPath}}/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": "researcher",
+      "advanceWhen": {
+        "file": "{{workPath}}/verify.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/verify.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/verify.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "verify",
+        "maxAttempts": 3
+      },
+      "next": "report"
+    },
+    {
+      "id": "report",
+      "name": "Compile the audit report",
+      "description": "per-citation verdicts, justifying quotes, and fixes",
+      "prompt": "1. Write {{workPath}}/audit.md with a summary (counts per verdict, and the count of uncited claims) then one entry per pair id: the claim, the citation, the verdict from the rubric, the justifying quote from the source, and the proposed fix for any non-Supported verdict. 2. Add a dedicated 'Uncited claims' section listing factual statements that lack a citation. 3. Use ONLY rubric verdicts and base each strictly on {{workPath}}/verify.md. 4. Make it actionable — an editor should be able to apply every fix directly. 5. On a loop-back, fix only the named gaps. 6. Call write_task_note with the report path and which criteria now pass.\n\nBefore working, open the artifact input `{{workPath}}/verify.md` with `read_artifact`; do not look for it in the workspace.\n\nThe deliverable `{{workPath}}/audit.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": "{{workPath}}/verify.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "{{workPath}}/audit.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/audit.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/audit.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 {{workPath}}/audit.md and check EACH criterion PASS/FAIL: (1) every citation paired in {{workPath}}/scope.md has an audited entry — none skipped; (2) an uncited-claims section lists statements lacking citations; (3) each entry has exactly one rubric verdict; (4) every Not-Supported/Partially-Supported/Dead verdict is justified by a quoted source passage (spot-check 3 against {{workPath}}/verify.md); (5) each problem has a concrete, applicable fix; (6) the summary counts match the entries. A report that marks a topically-related-but-non-supporting source as Supported, or skips a citation, FAILS.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/audit.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": "{{workPath}}/audit.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": "1.0.2",
+  "releasedAt": "2026-08-21T00:00:00Z",
+  "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}}"
+      }
+    }
+  },
+  "minGezelVersion": "1.26233"
+}