@bendyline/gilde 0.1.38 → 0.1.40

package/data/craftbook-templates/re/release-readiness-review/versions/1.0.2/craftbook.json

@@ -0,0 +1,153 @@
+{
+  "id": "release-readiness-review",
+  "name": "Release Readiness Review",
+  "description": "Run a go/no-go release readiness review against a structured pre-launch checklist and produce a sign-off report with a clear ship decision. First scopes the release and locks a readiness checklist (acceptance criteria met, tests and CI green, no open blockers, migrations and rollback ready, monitoring and alerts in place, docs and changelog updated, feature flags and config set, and on-call/comms prepared), then verifies each item by inspecting the actual state rather than assuming, then writes a go/no-go report listing every blocker that must clear before ship and the residual risks. Use this for a release readiness review, a go/no-go decision, a pre-launch checklist, a ship-readiness gate, a launch review, or deciding if a change is safe to deploy — it produces an evidence-backed ship decision rather than a gut-feel 'looks good'.\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 readiness checklist (reviewer) — lock the release scope + a go/no-go checklist → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Verify readiness (developer) — check each item against the real state → gated on artifact `{{workPath}}/verify.md` (markdown-notes)\n3. Write the go/no-go report (reviewer) — ship decision + blockers + residual risk → gated on artifact `{{workPath}}/release-readiness.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "release readiness review",
+    "are we ready to ship",
+    "go no go decision",
+    "pre-launch checklist",
+    "is this safe to deploy",
+    "ship readiness review"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the readiness checklist",
+      "description": "lock the release scope + a go/no-go checklist",
+      "prompt": "Step 1: Define the release: what is shipping (features/changes), to whom, and the rollout mechanism (full deploy / staged / flagged). Step 2: Write a readiness acceptance-criteria checklist covering: the feature's own acceptance criteria are met; the test suite and CI are green; there are no open blocking bugs or unresolved review comments; database migrations are reversible and a rollback path exists; monitoring, logging, and alerts cover the new code; user-facing docs, release notes, and changelog are updated; feature flags and config/secrets are set correctly for the target env; and on-call ownership and a comms/rollback plan are ready. Step 3: For each item, state the concrete pass condition and HOW it will be verified (where to look). Step 4: Mark which items are hard blockers vs advisory. Write the release definition + checklist to `write_task_note` AND `{{workPath}}/scope.md`. No verification yet.\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 readiness",
+      "description": "check each item against the real state",
+      "prompt": "Step 1: For EACH checklist item, VERIFY the actual state — do not assume. Run/inspect the tests and CI status; search for open issues/TODOs/blocking review comments; check that the migration has a down path and that a rollback is documented; confirm alerts/dashboards reference the new code paths; open the docs/changelog/release notes to confirm they are updated; check the flag and config/secret values for the target environment; confirm on-call and the rollback/comms plan exist. Step 2: For each item record PASS/FAIL/NA with the EVIDENCE (the command output, the file, the config value, the issue link) — a claim without evidence is not a pass. Step 3: Classify every FAIL as a hard blocker or an accepted risk. Step 4: Note residual risks even where items pass (e.g. 'migration is reversible but locks the table for ~30s'). Good looks like: every item backed by an observation, not 'should be fine'. Stage the verification log to `write_task_note`. Do not write the 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": "developer",
+      "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": "Write the go/no-go report",
+      "description": "ship decision + blockers + residual risk",
+      "prompt": "Step 1: Open `{{workPath}}/release-readiness.md` and write the DECISION at the top: GO / NO-GO / GO-WITH-CONDITIONS, in one sentence with the deciding factor. Step 2: Add a '## Checklist' table: each item with PASS/FAIL/NA and its evidence. Step 3: Add a '## Blockers' section listing every must-clear item before ship, with the concrete action to clear it and an owner. Step 4: Add a '## Residual risks' section (accepted risks and watch-items for after deploy) and a '## Rollback' note summarizing how to back out. Step 5: If GO-WITH-CONDITIONS, list the exact conditions. The decision must follow from the evidence — no GO with an open hard blocker. On a loop-back, fix only the named gaps. `write_task_note` the report path, the decision, and the count of open blockers.\n\nThe deliverable `{{workPath}}/release-readiness.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}}/release-readiness.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/release-readiness.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/release-readiness.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}}/release-readiness.md` and grade it against the scope checklist. Check EACH criterion and write PASS/FAIL with a one-line reason: (1) every checklist item has a PASS/FAIL/NA with concrete evidence (not an assumption); (2) tests/CI status was actually checked; (3) migration reversibility and a rollback path are confirmed; (4) monitoring/alerts and docs/changelog were verified; (5) flags/config for the target env were checked; (6) all blockers are listed with an action and owner, and residual risks are stated; (7) the GO/NO-GO decision is consistent with the evidence (no GO with an open hard blocker). If any criterion fails, name the exact gap and loop back.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/release-readiness.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}}/release-readiness.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"
+}

package/data/craftbook-templates/re/release-readiness-review/versions/1.0.2/test.json

@@ -0,0 +1,113 @@
+{
+  "schemaVersion": 1,
+  "title": "Release Readiness Review smoke eval",
+  "objective": "Self-contained smoke eval for the Release Readiness Review craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a release readiness review for the returns-desk work. The backgound info is in source/brief.md — have a look and write it up in report.md.",
+  "setup": {
+    "projectName": "Release Readiness Review Eval",
+    "about": "Self-contained eval project for release-readiness-review. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Release Readiness Review craftbook/template, read the seeded local fixtures, and write report.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Release Readiness Review 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: release-readiness-review - Release Readiness Review.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Writer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "report.md is a source-grounded markdown artifact with required facts and actions.",
+    "deliverables": [
+      {
+        "path": "report.md",
+        "kind": "markdown-report",
+        "minBytes": 1000,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "source/brief\\.md|Brief",
+            "flags": "i",
+            "label": "cite or name the seeded source"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "18\\b[\\s\\S]{0,30}\\bSKUs",
+            "flags": "i",
+            "label": "include the 18-SKU pilot scope"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "18\\s*hours|6\\s*hours",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "14\\.2%|8\\.9%",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "status silence|photo submission",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "automated status emails|barcode|Finance",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "report.md",
+      "kind": "markdown"
+    },
+    "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": [
+    "source-grounded prose",
+    "section structure",
+    "next-action clarity"
+  ]
+}

package/data/craftbook-templates/re/reliability-review/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "reliability-review",
   "role": "maintenance-review",
+  "category": "code-ops",
   "name": "Reliability & Resilience Review",
   "description": "Review a codebase for production reliability and resilience risks across asynchronous work, external dependencies, state transitions, resource lifecycles, and recovery paths. Uses the repository and per-file indexes to map failure domains, verifies likely issues in source and tests, and leaves a prioritized morning report covering timeouts, retries, idempotency, cancellation, concurrency, backpressure, cleanup, graceful shutdown, observability, and disaster recovery. Use for a weekly reliability sweep, resilience review, failure-mode audit, or pre-production hardening review.",
   "tags": [

package/data/craftbook-templates/re/reliability-review/versions/1.0.2/craftbook.json

@@ -0,0 +1,165 @@
+{
+  "id": "reliability-review",
+  "name": "Reliability & Resilience Review",
+  "description": "Review a codebase for production reliability and resilience risks across asynchronous work, external dependencies, state transitions, resource lifecycles, and recovery paths. Uses the repository and per-file indexes to map failure domains, verifies likely issues in source and tests, and leaves a prioritized morning report covering timeouts, retries, idempotency, cancellation, concurrency, backpressure, cleanup, graceful shutdown, observability, and disaster recovery. Use for a weekly reliability sweep, resilience review, failure-mode audit, or pre-production hardening review.\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. Map failure domains (reviewer) — inventory stateful and asynchronous boundaries plus their reliability contract → gated on artifact `{{workPath}}/reliability/failure-map.md` (markdown-notes)\n2. Verify failure handling (reviewer) — trace representative failures through source and tests → gated on artifact `{{workPath}}/reliability/evidence.md` (markdown-notes)\n3. Write the reliability report (reviewer) — ranked failure-mode report with concrete hardening work → gated on artifact `{{workPath}}/reliability-review.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "model",
+  "triggers": [
+    "reliability review",
+    "resilience audit",
+    "review failure modes",
+    "weekly production hardening",
+    "find reliability risks",
+    "nightly reliability sweep"
+  ],
+  "toolsets": [
+    {
+      "toolsetId": "builtin.code-intel",
+      "autoAllow": true,
+      "reason": "map failure domains and verify indexed reliability leads in source"
+    },
+    {
+      "toolsetId": "builtin.code-execution",
+      "autoAllow": true,
+      "reason": "run safe existing tests or focused diagnostic scripts when available"
+    }
+  ],
+  "steps": [
+    {
+      "id": "model",
+      "name": "Map failure domains",
+      "description": "inventory stateful and asynchronous boundaries plus their reliability contract",
+      "prompt": "Call `map_repo`, `list_file_issues`, and targeted `search_code` queries for queues/jobs, timers, promises, subprocesses, network/database/filesystem calls, caches, locks, transactions, startup/shutdown, and persistence. Build a failure-domain map: critical user journeys, state owners, external dependencies, retry boundaries, resource lifecycles, and recovery expectations. For each boundary define the reliability contract: timeout, retry/backoff/jitter, idempotency, cancellation, concurrency limit/backpressure, cleanup, error propagation, monitoring, and recovery. Record index coverage and areas not statically observable. Write the map and prioritized audit plan to `{{workPath}}/reliability/failure-map.md`.\n\nThe deliverable `{{workPath}}/reliability/failure-map.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}}/reliability/failure-map.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/reliability/failure-map.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/reliability/failure-map.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "model",
+        "maxAttempts": 3
+      },
+      "next": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify failure handling",
+      "description": "trace representative failures through source and tests",
+      "prompt": "For each high-impact boundary, inspect the relevant symbols and callers with `file_review`, `outline_file`, `read_symbol`, and `find_references`. Trace representative failures: slow/hung dependency, transient failure, duplicate delivery, partial write, cancellation, concurrent mutation, process restart, disk full/corrupt state, and shutdown during work. Locate tests and run safe existing checks when practical. Confirm whether timeouts are bounded; retries have caps/backoff/jitter and do not multiply side effects; operations are idempotent; cancellations and errors propagate; resources/timers/listeners/subprocesses are released; transactions or durable journals protect multi-step state; startup and shutdown are safe; and operators get useful signals. Record confirmed issues and verified-safe controls with real file:line/test/command evidence in `{{workPath}}/reliability/evidence.md`.\n\nThe deliverable `{{workPath}}/reliability/evidence.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}}/reliability/evidence.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/reliability/evidence.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/reliability/evidence.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "verify",
+        "maxAttempts": 3
+      },
+      "next": "report"
+    },
+    {
+      "id": "report",
+      "name": "Write the reliability report",
+      "description": "ranked failure-mode report with concrete hardening work",
+      "prompt": "Write `{{workPath}}/reliability-review.md` with `## Verdict`, `## Coverage and assumptions`, `## Failure-domain scorecard`, `## Findings`, `## Verified controls`, `## Not verified`, and `## Hardening sequence`. Each finding must cite real file:line or test/command evidence, state the initiating failure, propagation path, user/operator impact, likelihood, severity, and a concrete remediation plus the failure-injection/regression test to add. Rank by impact × likelihood × recoverability. Distinguish a missing control from a merely untested control. Do not demand distributed-systems machinery for local, low-risk code. On a loop-back, fix only named gaps.\n\nThe deliverable `{{workPath}}/reliability-review.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}}/reliability-review.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/reliability-review.md",
+            "bytes": 1800,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/reliability-review.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": "Grade `{{workPath}}/reliability-review.md`: (1) critical failure domains and contracts are mapped; (2) findings cite real source/test/command evidence; (3) timeouts, retries/backoff, idempotency, cancellation, concurrency/backpressure, cleanup, partial writes, restart, and shutdown were considered where relevant; (4) propagation and user/operator impact are explained; (5) each remediation includes a failure-injection or regression test; (6) verified controls and unverified areas are explicit; (7) priorities reflect impact, likelihood, and recoverability without overengineering. PASS all or loop back.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/reliability-review.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}}/reliability-review.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"
+}

package/data/craftbook-templates/re/reliability-review/versions/1.0.2/test.json

@@ -0,0 +1,115 @@
+{
+  "schemaVersion": 1,
+  "title": "Reliability & Resilience Review failure-path eval",
+  "objective": "Measure whether the review traces seeded retry, timeout, idempotency, cleanup, and recovery risks and proposes failure-injection tests.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "Use the Reliability & Resilience Review craftbook for a weekly production-hardening pass. Review the seeded worker and write tasks/eval/reliability-review.md. Do not change source.",
+  "setup": {
+    "projectName": "Reliability Maintenance Eval",
+    "about": "A tiny background worker with deliberate unbounded retries, missing timeout/cancellation, duplicate side-effect, and leaked interval risks.",
+    "missionObjectives": "Trace how failures propagate and leave concrete controls plus regression/failure-injection tests.",
+    "files": [
+      {
+        "path": "src/worker.ts",
+        "content": "let running = false;\nexport function startWorker(queue, billing, db) {\n  running = true;\n  setInterval(async () => {\n    if (!running) return;\n    const job = await queue.next();\n    if (!job) return;\n    while (true) {\n      try {\n        await billing.charge(job.customerId, job.amount);\n        await db.markProcessed(job.id);\n        break;\n      } catch (_err) {\n        // retry immediately forever\n      }\n    }\n  }, 10);\n}\nexport function stopWorker() { running = false; }\n"
+      },
+      {
+        "path": "test/worker.test.ts",
+        "content": "test('starts', () => { startWorker(queue, billing, db); expect(true).toBe(true); });\n"
+      },
+      {
+        "path": "docs/slo.md",
+        "content": "# Worker contract\n\nA job may be delivered more than once. Billing must happen at most once. Shutdown must finish or return the active job within 5 seconds. Transient dependencies should be retried with bounded exponential backoff.\n"
+      }
+    ],
+    "worker": {
+      "name": "Rae",
+      "role": "Reviewer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "tasks/eval/reliability-review.md traces every seeded failure mode and pairs remediations with exact failure-injection tests.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/reliability-review.md",
+        "kind": "markdown-report",
+        "minBytes": 1500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/reliability-review.md",
+            "pattern": "src/worker\\.ts:[0-9]+|src/worker\\.ts",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/reliability-review.md",
+            "pattern": "unbounded|while \\(true\\)|retry",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/reliability-review.md",
+            "pattern": "backoff|jitter|retry cap",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/reliability-review.md",
+            "pattern": "timeout|cancellation|Abort",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/reliability-review.md",
+            "pattern": "idempoten|at most once|duplicate.*charge",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/reliability-review.md",
+            "pattern": "clearInterval|interval|shutdown|cleanup",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/reliability-review.md",
+            "pattern": "failure-injection|test[\\s\\S]{0,160}(duplicate|transient|shutdown|timeout)",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/reliability-review.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "failure modeling",
+        "description": "Initiating failures, propagation, and user/operator impact are explicit."
+      },
+      {
+        "name": "control coverage",
+        "description": "Timeouts, retries, idempotency, cancellation, cleanup, and shutdown are addressed."
+      },
+      {
+        "name": "verification plan",
+        "description": "Each remediation has a concrete failure-injection or regression test."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "failure propagation",
+    "bounded resilience controls",
+    "failure-injection tests"
+  ]
+}

package/data/craftbook-templates/re/report-pdf/manifest.json

@@ -3,6 +3,7 @@
   "kind": "craftbook-template",
   "id": "report-pdf",
   "role": "general",
+  "category": "writing",
   "name": "Formatted Report",
   "description": "Produce a polished, print-ready PDF report from Markdown with DocBlocks — no hand-built HTML or browser print translator. Locks the audience, source facts, structure, and acceptance criteria first; writes the complete report as report.md; then converts, previews, and saves report.pdf in the project's artifacts drawer.",
   "tags": [