@bendyline/gilde 0.1.38 → 0.1.39

package/data/craftbook-templates/de/dependency-audit/versions/1.1.2/craftbook.json

@@ -0,0 +1,153 @@
+{
+  "id": "dependency-audit",
+  "name": "Dependency Audit",
+  "description": "Audit a project's dependencies for security, staleness, license, and maintenance risk, then produce a prioritized remediation report. First scans the manifest and lockfile to inventory every dependency with its installed vs latest version, known CVEs, license, and maintenance signals, then assesses each into a risk tier weighing severity, exploitability, breaking-change cost, and removability, then writes a report with a concrete upgrade/replace/remove action and order for each risky dependency. Use this for a dependency audit, supply-chain review, checking for vulnerable or outdated packages, license compliance, npm/pip audit triage, or reducing dependency risk — it turns a raw audit dump into a prioritized, justified action plan rather than a wall of warnings.\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. Scan the dependency tree (developer) — inventory deps with versions, CVEs, licenses → gated on artifact `{{workPath}}/scan.md` (markdown-notes)\n2. Assess risk (reviewer) — tier each dep by risk and remediation cost → gated on artifact `{{workPath}}/assess.md` (markdown-notes)\n3. Write the audit report (reviewer) — prioritized upgrade/replace/remove plan → gated on artifact `{{workPath}}/dependency-audit.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n\nEvidence discipline:\n\n- Treat supplied manifests, lockfiles, audit JSON, and dependency notes as the source of truth. Do not invent CVEs, licenses, package age, or network-audit results that are not in the evidence.\n- If evidence says no patched version exists, do not recommend a patch upgrade; recommend replacement, containment, or a human decision.\n- If evidence names a copyleft or incompatible license, the License flags section must name the package and license. Do not write that no license flags were found.\n- Dependencies with no seeded CVE, license issue, or maintenance issue should be explicitly deferred, not inflated into security or replacement work.\n- Recommended order is risk-first: critical no-patch security items come before unused cleanup and low-effort maintenance upgrades, even when the cleanup is easier.\n- Maintenance-only upgrades can still be recommended, but label them maintenance-only; do not describe them as security posture work unless the evidence names a vulnerability.\n- Copy exact license identifiers and exact target versions from the evidence, such as `GPL-3.0-only` or `4.18.3`; do not replace them with vague family labels or \"monitor later\" language.\n- Copy named replacement alternatives from the evidence, such as `chart.js 4.x`; do not replace them with vague \"find an alternative\" language.\n- If a dependency has no seeded CVE, avoid words like security, advisory, vulnerability, patch, or posture in that dependency's action unless the evidence explicitly supports them.\n- Do not infer missing licenses. If the evidence does not state a license for a dependency, say the license was not provided rather than guessing MIT or writing \"assumed.\"\n",
+  "entryStepId": "scan",
+  "triggers": [
+    "dependency audit",
+    "are my dependencies safe",
+    "check for outdated packages",
+    "supply chain review",
+    "npm audit triage",
+    "license compliance check"
+  ],
+  "steps": [
+    {
+      "id": "scan",
+      "name": "Scan the dependency tree",
+      "description": "inventory deps with versions, CVEs, licenses",
+      "prompt": "Step 1: Read the manifest and lockfile (package.json/lock, requirements/poetry, go.mod, Cargo.toml, etc.) to inventory direct and notable transitive dependencies. Step 2: For each, gather: installed version vs latest, the semver gap (patch/minor/major behind), known vulnerabilities (run the ecosystem audit tool if available — `npm audit`, `pip-audit`, `cargo audit` — and capture CVE id + severity), license, and maintenance signals (last release date, archived/deprecated, single-maintainer). If the task already provides audit output or dependency notes, treat those files as authoritative evidence and do not replace them with fresh network assumptions. Step 3: Flag duplicates/multiple versions of the same package and obviously unused or trivially-replaceable dependencies. Step 4: Write the acceptance-criteria checklist for the audit, e.g. 'every direct dependency is inventoried', 'all CVEs at high+ are captured with an id', 'each license is recorded and flagged if copyleft/incompatible', 'staleness is measured by both semver gap and release recency'. Step 5: Save the inventory table to `write_task_note` AND `{{workPath}}/scan.md`. No prioritization yet — this phase is the raw inventory.\n\nThe deliverable `{{workPath}}/scan.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}}/scan.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/scan.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/scan.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "scan",
+        "maxAttempts": 3
+      },
+      "next": "assess"
+    },
+    {
+      "id": "assess",
+      "name": "Assess risk",
+      "description": "tier each dep by risk and remediation cost",
+      "prompt": "Step 1: For each dependency in the inventory, assign a risk tier (Critical / High / Medium / Low) weighing: CVE severity AND whether the vulnerable code path is actually used, how far behind it is, whether the upgrade is a breaking major (and the migration cost), license incompatibility, and abandonment/maintenance risk. Step 2: Decide the remediation per dep: patch-upgrade (safe), minor/major upgrade (note breaking changes to handle), replace (name the alternative), remove (if unused), or defer (if no seeded issue is present). If the evidence says no patched version exists, do not recommend an update-to-patch; recommend replacement, containment, or a human decision instead. Step 3: Determine a sensible ORDER — critical/no-patch security items first, then other high CVEs, then cleanup and low-effort maintenance; do not put unused cleanup or low-risk maintenance ahead of a critical no-patch replacement just because it is easy. Step 4: Distinguish real exposure from theoretical (a CVE in an unreachable code path is lower risk — say so), and distinguish maintenance-only upgrades from security fixes. Step 5: Note anything needing human judgment (license/legal, a major framework bump). Good looks like: a tier justified by both severity and actual exposure, not just the audit tool's color. Stage the tiered list to `write_task_note`. Do not write the report yet.\n\nThe deliverable `{{workPath}}/assess.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}}/assess.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/assess.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/assess.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "assess",
+        "maxAttempts": 3
+      },
+      "next": "report"
+    },
+    {
+      "id": "report",
+      "name": "Write the audit report",
+      "description": "prioritized upgrade/replace/remove plan",
+      "prompt": "Step 1: Open `{{workPath}}/dependency-audit.md` and write a '## Summary' line: total deps, count by risk tier, and the headline risk. Step 2: Add an '## Action plan' ordered by priority; each entry: `package@installed → action (target version / replacement / remove / defer)` with the reason (CVE id + severity, semver gap, license, abandonment, or no seeded issue), the breaking-change note if any, and the migration effort. Keep exact target versions and named replacement alternatives from the evidence; do not downgrade a named maintenance upgrade to vague monitoring or replace a named alternative with generic wording. Step 3: Add a '## License flags' section for any copyleft/incompatible licenses; if the source names GPL/copyleft, the section must name that package and exact license identifier, not say no flags were found. Do not infer missing licenses; say license not provided when the evidence does not name one. Step 4: Add a '## Needs human decision' section for legal/major-bump/no-patch calls. Step 5: Add a one-paragraph '## Recommended order' (what to do this week vs later), keeping critical no-patch CVEs ahead of unused cleanup and low-effort maintenance upgrades. Every action must name a concrete target and a justification — no 'update your packages'. On a loop-back, fix only the named gaps. `write_task_note` the report path and the counts by tier.\n\nThe deliverable `{{workPath}}/dependency-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",
+      "advanceWhen": {
+        "file": "{{workPath}}/dependency-audit.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/dependency-audit.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/dependency-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}}/dependency-audit.md` and grade it against the scan checklist. Check EACH criterion and write PASS/FAIL with a one-line reason: (1) every direct dependency is inventoried with installed vs latest; (2) all high+ CVEs are captured with an id and severity; (3) each risky dep has a concrete action (upgrade target / replacement / remove / defer) and a justification; (4) breaking-change/migration cost is noted for major upgrades; (5) licenses are recorded and incompatibilities flagged, especially any GPL/copyleft source note; (6) the plan is prioritized with a recommended order that puts critical/no-patch security items before unused cleanup and maintenance-only upgrades; (7) risk tiers reflect actual exposure, not just the tool's raw severity; (8) no dependency with no seeded issue is inflated into a security/replacement recommendation; (9) no dependency with no patched version is described as patch-upgradeable. If any criterion fails, name the exact gap and loop back.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/dependency-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}}/dependency-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": "1.1.2",
+  "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/de/dependency-audit/versions/1.1.2/test.json

@@ -0,0 +1,111 @@
+{
+  "schemaVersion": 1,
+  "title": "Dependency Audit evidence-discipline eval",
+  "objective": "Measure whether the audit prioritizes supplied vulnerability and license evidence without inventing package facts or patch versions.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "Use the Dependency Audit craftbook for the weekly maintenance review. Treat evidence/dependencies.json as authoritative and write tasks/eval/dependency-audit.md. Do not use the network or modify package files.",
+  "setup": {
+    "projectName": "Dependency Maintenance Eval",
+    "about": "A package fixture with authoritative offline dependency evidence.",
+    "missionObjectives": "Prioritize the no-patch critical dependency, exact license issue, maintenance-only upgrade, and clean defer correctly.",
+    "files": [
+      {
+        "path": "package.json",
+        "content": "{\n  \"name\": \"returns-desk\",\n  \"dependencies\": {\n    \"legacy-parser\": \"1.2.0\",\n    \"chart-kit\": \"2.0.0\",\n    \"stable-lib\": \"4.2.0\"\n  }\n}\n"
+      },
+      {
+        "path": "evidence/dependencies.json",
+        "content": "[\n  {\"name\":\"legacy-parser\",\"installed\":\"1.2.0\",\"latest\":\"1.2.0\",\"advisory\":\"CVE-2026-4242\",\"severity\":\"critical\",\"patchedVersion\":null,\"reachableFrom\":\"src/import.ts\",\"replacement\":\"safe-parser 3.x\",\"license\":\"MIT\"},\n  {\"name\":\"chart-kit\",\"installed\":\"2.0.0\",\"latest\":\"3.1.0\",\"advisory\":null,\"maintenance\":\"major version available\",\"license\":\"GPL-3.0-only\",\"replacement\":\"chart.js 4.x\"},\n  {\"name\":\"stable-lib\",\"installed\":\"4.2.0\",\"latest\":\"4.2.0\",\"advisory\":null,\"maintenance\":null,\"license\":\"MIT\"}\n]\n"
+      },
+      {
+        "path": "src/import.ts",
+        "content": "import { parse } from 'legacy-parser';\nexport const importRows = (text: string) => parse(text);\n"
+      }
+    ],
+    "worker": {
+      "name": "Rae",
+      "role": "Reviewer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "tasks/eval/dependency-audit.md follows the evidence, orders the critical no-patch action first, and handles license and clean dependencies honestly.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/dependency-audit.md",
+        "kind": "markdown-report",
+        "minBytes": 1300,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/dependency-audit.md",
+            "pattern": "legacy-parser[\\s\\S]{0,300}CVE-2026-4242",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/dependency-audit.md",
+            "pattern": "safe-parser 3\\.x|no patched version|contain",
+            "flags": "i",
+            "label": "no-patch action"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/dependency-audit.md",
+            "pattern": "chart-kit[\\s\\S]{0,300}GPL-3\\.0-only",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/dependency-audit.md",
+            "pattern": "chart\\.js 4\\.x",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/dependency-audit.md",
+            "pattern": "stable-lib[\\s\\S]{0,200}(defer|no action|current)",
+            "flags": "i"
+          },
+          {
+            "kind": "notContains",
+            "file": "tasks/eval/dependency-audit.md",
+            "pattern": "legacy-parser[\\s\\S]{0,120}(patch upgrade|upgrade to 1\\.)",
+            "flags": "i",
+            "label": "do not invent a patch"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/dependency-audit.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "evidence discipline",
+        "description": "Package facts and versions come only from supplied evidence."
+      },
+      {
+        "name": "prioritization",
+        "description": "Risk, reachability, license, and migration cost drive a sensible order."
+      },
+      {
+        "name": "actionability",
+        "description": "Each package receives an exact upgrade, replace, contain, or defer action."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "offline evidence fidelity",
+    "no-patch handling",
+    "license accuracy"
+  ]
+}

package/data/craftbook-templates/de/deploy-checklist/versions/1.0.2/craftbook.json

@@ -0,0 +1,171 @@
+{
+  "id": "deploy-checklist",
+  "name": "Deploy Checklist",
+  "description": "Author and then actually execute a pre-deploy verification checklist for shipping a release to production — the concrete gates that must be green before the deploy button is pressed: tests passing, build clean, migrations reviewed, config/secrets present, feature flags set, rollback path confirmed, and observability/alerts ready. A planner scopes the checklist tailored to this service and risk level, a developer runs each item and records real evidence (command output, links, screenshots) for pass or fail, and a reviewer signs off go/no-go. Use this before a production deploy, a release cut-over, or any 'are we ready to ship?' gate where skipping a step causes outages.\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 checklist (planner) — define the go/no-go gates for THIS service and release → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Verify each gate (developer) — execute every checklist item and record real evidence → gated on `deploy-checklist.md` (markdown-doc)\n3. Sign off go/no-go (reviewer) — audit the evidence and confirm the go/no-go decision → gated on artifact `{{workPath}}/report.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": [
+    "pre-deploy checklist",
+    "are we ready to deploy",
+    "go/no-go for release",
+    "production deploy checklist",
+    "ship readiness check"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the checklist",
+      "description": "define the go/no-go gates for THIS service and release",
+      "prompt": "1. Identify what is being deployed (service, version, target environment) and its blast radius / risk level. 2. Build the checklist of pre-deploy gates tailored to this service — at minimum: CI green (tests + lint + build), schema/data migrations reviewed and reversible, required config and secrets present in the target env, feature flags in their intended state, dependencies/external services healthy, a confirmed rollback path, and observability (dashboards, alerts, on-call) ready. 3. Drop any gate that genuinely does not apply and note why; add service-specific gates (cache warmups, queue drains, third-party rate limits) that do. 4. For each gate, write the EXACT verification step (the command to run, the URL to check, the artifact to inspect) and the explicit pass condition. 5. Good looks like: an ordered, unambiguous checklist where any engineer could execute each item and objectively decide pass/fail, and where each item has a defined pass condition. Write this as an acceptance-criteria checklist (each gate IS a criterion) plus the deploy context to the notes file via write_task_note AND 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": "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": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify each gate",
+      "description": "execute every checklist item and record real evidence",
+      "prompt": "1. Open {{workPath}}/scope.md and work through every gate IN ORDER, actually running the verification step (run the command, hit the endpoint, inspect the artifact) — do not assume, do not skip. 2. For each gate record: the step taken, the real evidence (command output, status, link), and a PASS or FAIL with the pass condition met or not. 3. If a gate FAILS, mark it FAIL with the specific reason — do not silently soften it; a failed gate is a no-go signal. 4. Render the result as a markdown checklist where every item is checked [x] only when its evidence genuinely supports PASS. 5. Conclude with an overall GO (all gates PASS) or NO-GO (any gate FAIL) recommendation and the single biggest risk. 6. Good looks like: a completed checklist where every gate from scope.md has attached evidence and an honest verdict, with a clear top-line go/no-go. Write the executed checklist to deploy-checklist.md.\n\nBefore working, open the artifact input `{{workPath}}/scope.md` with `read_artifact`; do not look for it in the workspace.",
+      "suggestedRole": "developer",
+      "consumes": [
+        {
+          "file": "{{workPath}}/scope.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "deploy-checklist.md",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "deploy-checklist.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "deploy-checklist.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "verify",
+        "maxAttempts": 3
+      },
+      "next": "report"
+    },
+    {
+      "id": "report",
+      "name": "Sign off go/no-go",
+      "description": "audit the evidence and confirm the go/no-go decision",
+      "prompt": "1. Open deploy-checklist.md and audit each gate's EVIDENCE, not just its checkbox — a checked box with weak or missing evidence is a FAIL. 2. Confirm every gate from {{workPath}}/scope.md is present and that no gate was dropped without a recorded reason. 3. Re-derive the overall verdict: if any gate is FAIL, the deploy is NO-GO regardless of the recorded recommendation. 4. Note any gate whose evidence is ambiguous and must be re-verified. 5. Write a PASS/FAIL per gate and a final, defensible GO or NO-GO with the deciding factors. 6. Any insufficient evidence routes back to the verify phase to re-run that gate. Write your sign-off to {{workPath}}/report.md.\n\nBefore working, open the artifact input `{{workPath}}/scope.md` with `read_artifact`; do not look for it in the workspace.\n\nThe deliverable `{{workPath}}/report.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}}/scope.md",
+          "artifact": true
+        },
+        {
+          "file": "deploy-checklist.md"
+        }
+      ],
+      "advanceWhen": {
+        "file": "{{workPath}}/report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "deploy-checklist.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "deploy-checklist.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "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 deploy-checklist.md and verify it against the gates locked in {{workPath}}/scope.md, PASS/FAIL each gate. Confirm: (a) every gate from scope.md appears with a recorded verification step; (b) each gate has REAL evidence (command output, link, or artifact), not just a checked box; (c) no gate was dropped without a stated reason; (d) the pass condition for each gate is genuinely met where marked PASS; (e) the document ends with a clear GO/NO-GO that is consistent with the gates (any FAIL ⇒ NO-GO). Any gate lacking evidence or wrongly marked routes back to the verify phase to re-run it.\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: \"verify\" })` 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": "deploy-checklist.md"
+        }
+      ],
+      "next": "verify"
+    },
+    {
+      "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/de/deploy-checklist/versions/1.0.2/test.json

@@ -0,0 +1,168 @@
+{
+  "schemaVersion": 1,
+  "title": "Go/no-go deploy checklist from seeded evidence",
+  "objective": "Measure whether the deploy-checklist craftbook turns release evidence into an auditable go/no-go checklist and refuses to approve a failed gate.",
+  "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": "Deploy Checklist Eval",
+    "about": "Self-contained eval project for deploy-checklist. The deploy context and command outputs are seeded in workspace/source.",
+    "missionObjectives": "Write an evidence-backed deploy checklist with CI/build, migrations, config/secrets, dependencies, rollback, observability, and a consistent go/no-go decision.",
+    "files": [
+      {
+        "path": "source/release-context.md",
+        "content": "# Ledger API 3.8.0\n\nTarget: production. Blast radius: customer invoice posting and webhook delivery. Release includes a reversible invoice index migration, a webhook retry queue, and a new PAYMENTS_WEBHOOK_SECRET config key. Rollback: redeploy 3.7.4 and run `npm run migrate:down 20260627_invoice_idx`.\n"
+      },
+      {
+        "path": "source/deploy-evidence.md",
+        "content": "# Verification evidence\n\n- `npm test`: PASS, 842 tests.\n- `npm run lint`: PASS.\n- `npm run build`: PASS, artifact ledger-api-3.8.0.tgz created.\n- Migration review: reversible, migrate:down script present.\n- Config/secrets in production: `DATABASE_URL` present, `PAYMENTS_WEBHOOK_SECRET` MISSING.\n- Dependency health: Stripe status operational, queue depth normal at 14 jobs.\n- Observability: dashboard `ledger-api-prod` updated; alert `webhook retry failures > 5/min` enabled.\n- On-call: Priya is primary, Marcus is backup.\n"
+      }
+    ],
+    "worker": {
+      "name": "Kai",
+      "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} ${dryRun.body}`);\n\ngezel.output({ open: open.body, dryRun: dryRun.body });\n"
+      }
+    }
+  ],
+  "success": {
+    "summary": "automation.md is grounded in live fake-service responses: the open items were actually listed and a dry-run actually recorded (request-log assertions), with safety guards and signals described.",
+    "deliverables": [
+      {
+        "path": "deploy-checklist.md",
+        "kind": "markdown-report",
+        "minBytes": 1800,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "deploy-checklist.md",
+            "pattern": "CI|test|lint|build|migration|config|secret|rollback|observability|on-call",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "deploy-checklist.md",
+            "pattern": "842|ledger-api-3\\.8\\.0|3\\.7\\.4"
+          },
+          {
+            "kind": "contains",
+            "file": "deploy-checklist.md",
+            "pattern": "PAYMENTS_WEBHOOK_SECRET|missing",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "deploy-checklist.md",
+            "pattern": "NO-GO|do not deploy|hold|blocked",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "deploy-checklist.md",
+            "pattern": "\\[x\\]|PASS|FAIL",
+            "flags": "i"
+          }
+        ]
+      }
+    ],
+    "mocks": [
+      {
+        "service": "ops",
+        "minRequests": 2,
+        "requiredPaths": [
+          "^/api/bookings/open$",
+          "^/api/bookings/dry-run$"
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "deploy-checklist.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": [
+    "evidence per gate",
+    "honest no-go",
+    "rollback and observability"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "seeded-deploy-evidence",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Local command-output evidence replacing real CI, secret, and status checks."
+      }
+    ]
+  }
+}