@wildo-ai/framework-knowledge 1.1.2 → 1.1.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (289) hide show
  1. package/dist/esm/framework-knowledge.definitions.d.ts +1 -1
  2. package/dist/esm/framework-knowledge.definitions.d.ts.map +1 -1
  3. package/dist/esm/framework-knowledge.definitions.js +351 -18
  4. package/dist/esm/framework-knowledge.definitions.js.map +1 -1
  5. package/dist/esm/framework-knowledge.loader.d.ts.map +1 -1
  6. package/dist/esm/framework-knowledge.schemas.d.ts +1 -2
  7. package/dist/esm/framework-knowledge.schemas.d.ts.map +1 -1
  8. package/dist/esm/framework-knowledge.schemas.js.map +1 -1
  9. package/dist/esm/index.d.ts.map +1 -1
  10. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts +3 -4
  11. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts.map +1 -1
  12. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js +4 -4
  13. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js.map +1 -1
  14. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts +3 -4
  15. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts.map +1 -1
  16. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js +4 -4
  17. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js.map +1 -1
  18. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts +0 -1
  19. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts.map +1 -1
  20. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js +0 -1
  21. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js.map +1 -1
  22. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts +0 -1
  23. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts.map +1 -1
  24. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js +0 -1
  25. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js.map +1 -1
  26. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts +1 -2
  27. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts.map +1 -1
  28. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js +1 -2
  29. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js.map +1 -1
  30. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts +2 -3
  31. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts.map +1 -1
  32. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js +3 -3
  33. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js.map +1 -1
  34. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts +1 -2
  35. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts.map +1 -1
  36. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js +1 -2
  37. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js.map +1 -1
  38. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.d.ts +0 -1
  39. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.d.ts.map +1 -1
  40. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.js +0 -1
  41. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.js.map +1 -1
  42. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.d.ts +0 -1
  43. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.d.ts.map +1 -1
  44. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js +0 -1
  45. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js.map +1 -1
  46. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts +0 -1
  47. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts.map +1 -1
  48. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js +0 -1
  49. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js.map +1 -1
  50. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts +0 -1
  51. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts.map +1 -1
  52. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js +0 -1
  53. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js.map +1 -1
  54. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.d.ts +0 -1
  55. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.d.ts.map +1 -1
  56. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.js +0 -1
  57. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.js.map +1 -1
  58. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts +0 -2
  59. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts.map +1 -1
  60. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js +2 -2
  61. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js.map +1 -1
  62. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts +0 -1
  63. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts.map +1 -1
  64. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js +0 -1
  65. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js.map +1 -1
  66. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.d.ts +0 -1
  67. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.d.ts.map +1 -1
  68. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.js +0 -1
  69. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.js.map +1 -1
  70. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts +0 -1
  71. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts.map +1 -1
  72. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js +0 -1
  73. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js.map +1 -1
  74. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.d.ts +0 -1
  75. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.d.ts.map +1 -1
  76. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.js +0 -1
  77. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.js.map +1 -1
  78. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.d.ts +0 -2
  79. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.d.ts.map +1 -1
  80. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.js +9 -4
  81. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.js.map +1 -1
  82. package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.d.ts +0 -1
  83. package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.d.ts.map +1 -1
  84. package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.js +0 -1
  85. package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.js.map +1 -1
  86. package/dist/esm/playbooks/top_down.market-research/playbook.definition.d.ts +0 -1
  87. package/dist/esm/playbooks/top_down.market-research/playbook.definition.d.ts.map +1 -1
  88. package/dist/esm/playbooks/top_down.market-research/playbook.definition.js +0 -1
  89. package/dist/esm/playbooks/top_down.market-research/playbook.definition.js.map +1 -1
  90. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.d.ts +0 -1
  91. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.d.ts.map +1 -1
  92. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js +0 -1
  93. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js.map +1 -1
  94. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts +0 -1
  95. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts.map +1 -1
  96. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js +0 -1
  97. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js.map +1 -1
  98. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.d.ts +0 -1
  99. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.d.ts.map +1 -1
  100. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js +0 -1
  101. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js.map +1 -1
  102. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts +0 -1
  103. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts.map +1 -1
  104. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js +0 -1
  105. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js.map +1 -1
  106. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.d.ts +0 -1
  107. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.d.ts.map +1 -1
  108. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.js +0 -1
  109. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.js.map +1 -1
  110. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts +0 -1
  111. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts.map +1 -1
  112. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js +0 -1
  113. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js.map +1 -1
  114. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/authority-basis.json +1 -1
  115. package/dist/knowledge/manifest.json +8 -9
  116. package/dist/knowledge/playbooks/bottom_up.build-decompose/method.md +13 -70
  117. package/dist/knowledge/playbooks/bottom_up.build-decompose/playbook.json +11 -19
  118. package/dist/knowledge/playbooks/bottom_up.build-dispatch/method.md +5 -88
  119. package/dist/knowledge/playbooks/bottom_up.build-dispatch/playbook.json +15 -8
  120. package/dist/knowledge/playbooks/bottom_up.build-scale/method.md +4 -5
  121. package/dist/knowledge/playbooks/bottom_up.build-scale/playbook.json +15 -8
  122. package/dist/knowledge/playbooks/bottom_up.domain-plan/method.md +4 -0
  123. package/dist/knowledge/playbooks/bottom_up.domain-plan/playbook.json +8 -7
  124. package/dist/knowledge/playbooks/bottom_up.foundation/method.md +22 -49
  125. package/dist/knowledge/playbooks/bottom_up.foundation/playbook.json +8 -17
  126. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/method.md +15 -780
  127. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/playbook.json +11 -11
  128. package/dist/knowledge/playbooks/refinement.document-facts/method.md +20 -141
  129. package/dist/knowledge/playbooks/refinement.document-facts/playbook.json +15 -10
  130. package/dist/knowledge/playbooks/top_down.brand-identity/method.md +3 -2
  131. package/dist/knowledge/playbooks/top_down.brand-identity/playbook.json +16 -11
  132. package/dist/knowledge/playbooks/top_down.business-model/playbook.json +14 -6
  133. package/dist/knowledge/playbooks/top_down.capability-map/method.md +4 -2
  134. package/dist/knowledge/playbooks/top_down.capability-map/playbook.json +16 -7
  135. package/dist/knowledge/playbooks/top_down.compliance-posture/method.md +4 -21
  136. package/dist/knowledge/playbooks/top_down.compliance-posture/playbook.json +65 -16
  137. package/dist/knowledge/playbooks/{top_down.market-snapshot-produce → top_down.market-analysis}/evaluation-protocol.json +1 -1
  138. package/dist/knowledge/playbooks/{top_down.market-snapshot-produce → top_down.market-analysis}/evaluation-treatment.json +1 -1
  139. package/dist/knowledge/playbooks/top_down.market-analysis/method.md +165 -51
  140. package/dist/knowledge/playbooks/top_down.market-analysis/playbook.json +43 -23
  141. package/dist/knowledge/playbooks/top_down.phase-gate/method.md +4 -8
  142. package/dist/knowledge/playbooks/top_down.phase-gate/playbook.json +7 -9
  143. package/dist/knowledge/playbooks/top_down.requirements-definition/method.md +7 -9
  144. package/dist/knowledge/playbooks/top_down.requirements-definition/playbook.json +15 -7
  145. package/dist/knowledge/playbooks/top_down.scope-roadmap/method.md +3 -3
  146. package/dist/knowledge/playbooks/top_down.scope-roadmap/playbook.json +16 -11
  147. package/dist/knowledge/playbooks/top_down.value-proposition/method.md +4 -2
  148. package/dist/knowledge/playbooks/top_down.value-proposition/playbook.json +15 -7
  149. package/dist/knowledge/playbooks/top_down.vision-elicitation/method.md +2 -2
  150. package/dist/knowledge/playbooks/top_down.vision-elicitation/playbook.json +16 -11
  151. package/dist/knowledge/references/build-plan.task-graph.config.md +1 -45
  152. package/dist/knowledge/references/companion.technical-doc.service.md +2 -102
  153. package/dist/knowledge/references/example.config.app-shell.full.md +5 -0
  154. package/dist/knowledge/references/example.module.companion-exports.full.md +0 -1
  155. package/dist/knowledge/references/example.provider.backend-module-shape.md +0 -7
  156. package/dist/knowledge/references/example.resource.add-resource.module-factory-map.md +1 -0
  157. package/dist/knowledge/references/platform.config.saas.md +0 -51
  158. package/dist/knowledge/references/presets.models.surface-policy.md +10 -19
  159. package/dist/knowledge/references/saas.external-data.admin-endpoints.md +48 -0
  160. package/dist/knowledge/references/saas.frontend.app-level-component.configuration.md +11 -31
  161. package/dist/knowledge/references/saas.frontend.app-level-component.vocabulary.md +1 -0
  162. package/dist/knowledge/references/saas.frontend.composite-view.authoring.md +0 -45
  163. package/dist/knowledge/references/saas.frontend.resource-operation-frontend-config.md +0 -198
  164. package/dist/knowledge/references/saas.models.data-mode-read-list.md +0 -164
  165. package/dist/knowledge/references/saas.models.engine-capabilities.md +6 -26
  166. package/dist/knowledge/references/saas.models.http-api-binding.md +29 -3
  167. package/dist/knowledge/references/saas.models.provider-capabilities.md +3 -4
  168. package/dist/knowledge/references/saas.models.resource-config.builder-parameters.md +2 -4
  169. package/dist/knowledge/references/saas.models.resource-config.resource-configuration.md +0 -2
  170. package/dist/knowledge/references/saas.models.resource-config.resources-registry.md +0 -14
  171. package/dist/knowledge/references/saas.specifications.application-document-fact-specification.contract.md +31 -11
  172. package/dist/knowledge/references/saas.specifications.assurance-document-blueprint.contract.md +2 -32
  173. package/dist/knowledge/references/saas.specifications.assurance-program.contract.md +6 -29
  174. package/dist/knowledge/references/saas.specifications.companion-exports.contract.md +0 -56
  175. package/dist/knowledge/references/saas.specifications.resource-spec-config.md +0 -22
  176. package/dist/knowledge/references/zod.decorators.chainable-runtime.md +0 -26
  177. package/dist/knowledge/references/zod.decorators.decorator-vocabulary.md +0 -45
  178. package/dist/knowledge/references/zod.decorators.display-edit-modes.md +1 -7
  179. package/dist/knowledge/references/zod.decorators.field-spec-params.md +5 -31
  180. package/dist/knowledge/references/zod.decorators.per-primitive-ui.md +1 -44
  181. package/dist/knowledge/references/zod.decorators.primitive-ui.md +0 -3
  182. package/dist/knowledge/references/zod.decorators.schema-metadata.md +0 -1
  183. package/dist/knowledge/references/zod.decorators.shared-structural-params.md +0 -15
  184. package/dist/knowledge/registries/assurance-authority-bases.json +2 -3
  185. package/dist/knowledge/registries/framework-topics.json +11 -146
  186. package/dist/knowledge/registries/playbooks.json +18 -154
  187. package/dist/knowledge/registries/source-tags.json +630 -883
  188. package/dist/knowledge/skills/INDEX.md +3 -4
  189. package/dist/knowledge/skills/brand-logo-authoring/SKILL.md +1 -2
  190. package/dist/knowledge/skills/compliance-document-authoring/SKILL.md +2 -16
  191. package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-governance.md +9 -31
  192. package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-privacy-notice.md +74 -252
  193. package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-service-terms.md +8 -26
  194. package/dist/knowledge/skills/compliance-document-authoring/references/framework-application-document-fact-specification-contract.md +53 -97
  195. package/dist/knowledge/skills/compliance-document-authoring/references/framework-assurance-document-blueprint-contract.md +21 -84
  196. package/dist/knowledge/skills/config-app-shell/SKILL.md +9 -31
  197. package/dist/knowledge/skills/config-app-shell/references/framework-app-shell-api.md +12 -31
  198. package/dist/knowledge/skills/config-design-system/SKILL.md +1 -23
  199. package/dist/knowledge/skills/config-design-system/references/framework-surface-policy-api.md +10 -19
  200. package/dist/knowledge/skills/config-navigation/SKILL.md +2 -75
  201. package/dist/knowledge/skills/config-saas/SKILL.md +2 -19
  202. package/dist/knowledge/skills/config-saas/references/framework-provider-capabilities-api.md +9 -30
  203. package/dist/knowledge/skills/config-saas/references/framework-wildo-saas-config-api.md +0 -51
  204. package/dist/knowledge/skills/configure-billing/references/example-backend-provider-module-shape.md +0 -7
  205. package/dist/knowledge/skills/flows-actors-a2a-exposure/SKILL.md +1 -2
  206. package/dist/knowledge/skills/flows-actors-a2a-exposure/references/framework-flows-actors-a2a-contract.md +3 -4
  207. package/dist/knowledge/skills/market-companion-prompt-enrichment/SKILL.md +0 -56
  208. package/dist/knowledge/skills/market-companion-prompt-enrichment/references/framework-companion-behavior-api.md +0 -56
  209. package/dist/knowledge/skills/module-companion-exports/SKILL.md +0 -1
  210. package/dist/knowledge/skills/module-companion-exports/references/companion-exports-by-package.md +0 -56
  211. package/dist/knowledge/skills/resource-add-field/SKILL.md +3 -3
  212. package/dist/knowledge/skills/resource-add-field/references/framework-field-cross-layer-api.md +0 -213
  213. package/dist/knowledge/skills/resource-add-resource/SKILL.md +1 -2
  214. package/dist/knowledge/skills/resource-add-resource/references/framework-new-resource-core-config-api.md +2 -4
  215. package/dist/knowledge/skills/resource-config-wiring/SKILL.md +0 -15
  216. package/dist/knowledge/skills/resource-config-wiring/references/framework-saas-models-resource-config-api.md +2 -224
  217. package/dist/knowledge/skills/resource-custom-view/references/custom-view-contracts.md +0 -198
  218. package/dist/knowledge/skills/resource-external-data/SKILL.md +2 -0
  219. package/dist/knowledge/skills/resource-external-data/references/framework-http-api-binding-api.md +29 -3
  220. package/dist/knowledge/skills/resource-external-data/references/framework-pipeline-admin-endpoints-api.md +70 -0
  221. package/dist/knowledge/skills/resource-mcp-tool-exposure/SKILL.md +1 -22
  222. package/dist/knowledge/skills/resource-rag-source-fields/references/framework-embeddings-capability-api.md +8 -28
  223. package/dist/knowledge/skills/resource-schema-authoring/SKILL.md +0 -1
  224. package/dist/knowledge/skills/resource-schema-authoring/references/decorator-layer-map.md +0 -17
  225. package/dist/knowledge/skills/resource-schema-authoring/references/framework-decorator-vocabulary-api.md +0 -46
  226. package/dist/knowledge/skills/resource-schema-authoring/references/framework-shared-structural-params-api.md +0 -15
  227. package/dist/knowledge/skills/resource-schema-authoring/references/framework-zod-lifecycle-and-chainable-api.md +0 -26
  228. package/dist/knowledge/skills/resource-ui-behavior/references/framework-display-edit-modes-api.md +1 -7
  229. package/dist/knowledge/skills/resource-ui-behavior/references/framework-frontend-resource-ui-contracts-api.md +0 -198
  230. package/dist/knowledge/skills/resource-ui-behavior/references/framework-per-primitive-ui-api.md +1 -44
  231. package/dist/knowledge/skills/resource-ui-behavior/references/framework-primitive-ui-api.md +0 -3
  232. package/dist/knowledge/skills/spec-companion-exports/SKILL.md +0 -1
  233. package/dist/knowledge/skills/spec-companion-exports/references/framework-companion-exports-contract-api.md +0 -56
  234. package/dist/knowledge/skills/spec-resource-update/references/framework-field-spec-params-api.md +5 -31
  235. package/dist/knowledge/skills/spec-resource-update/references/framework-spec-resource-contracts-api.md +0 -22
  236. package/dist/knowledge/skills/views-composite-authoring/references/framework-composite-view-contracts-api.md +0 -45
  237. package/dist/knowledge/topic-index.json +220 -725
  238. package/dist/tsconfig.build.tsbuildinfo +1 -1
  239. package/dist/tsconfig.tsbuildinfo +1 -1
  240. package/package.json +4 -4
  241. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/external-framework-mapping.json +0 -1
  242. package/dist/knowledge/playbooks/bottom_up.assemble-verify/method.md +0 -51
  243. package/dist/knowledge/playbooks/bottom_up.assemble-verify/playbook.json +0 -43
  244. package/dist/knowledge/playbooks/bottom_up.placement-plan/method.md +0 -185
  245. package/dist/knowledge/playbooks/bottom_up.placement-plan/playbook.json +0 -64
  246. package/dist/knowledge/playbooks/top_down.compliance-analysis/method.md +0 -41
  247. package/dist/knowledge/playbooks/top_down.compliance-analysis/playbook.json +0 -100
  248. package/dist/knowledge/playbooks/top_down.compliance-conception/method.md +0 -117
  249. package/dist/knowledge/playbooks/top_down.compliance-conception/playbook.json +0 -86
  250. package/dist/knowledge/playbooks/top_down.compliance-evidence-adequacy/method.md +0 -61
  251. package/dist/knowledge/playbooks/top_down.compliance-evidence-adequacy/playbook.json +0 -41
  252. package/dist/knowledge/playbooks/top_down.compliance-research/method.md +0 -76
  253. package/dist/knowledge/playbooks/top_down.compliance-research/playbook.json +0 -42
  254. package/dist/knowledge/playbooks/top_down.market-evidence-adequacy/method.md +0 -56
  255. package/dist/knowledge/playbooks/top_down.market-evidence-adequacy/playbook.json +0 -42
  256. package/dist/knowledge/playbooks/top_down.market-research/method.md +0 -68
  257. package/dist/knowledge/playbooks/top_down.market-research/playbook.json +0 -44
  258. package/dist/knowledge/playbooks/top_down.market-snapshot-produce/method.md +0 -239
  259. package/dist/knowledge/playbooks/top_down.market-snapshot-produce/playbook.json +0 -67
  260. package/dist/knowledge/references/placement-plan.config.md +0 -330
  261. package/dist/knowledge/references/saas.frontend.display-layout.reading-measure.md +0 -34
  262. package/dist/knowledge/references/saas.frontend.navigation.operation-override.md +0 -45
  263. package/dist/knowledge/references/saas.frontend.public-shell.identity-mode.md +0 -65
  264. package/dist/knowledge/references/saas.frontend.settings-hub.engine-destinations.md +0 -58
  265. package/dist/knowledge/references/saas.frontend.settings-hub.placement.md +0 -118
  266. package/dist/knowledge/references/saas.models.file-upload-grant.md +0 -179
  267. package/dist/knowledge/references/saas.models.navigation.surface-vocabulary.md +0 -124
  268. package/dist/knowledge/references/saas.models.navigation.transition-vocabulary.md +0 -99
  269. package/dist/knowledge/references/saas.models.navigation.zone-declaration.md +0 -127
  270. package/dist/knowledge/references/saas.models.resource-config.operation-variant-client-timeout.md +0 -42
  271. package/dist/knowledge/references/saas.specifications.application-authored-document-fact-specification.contract.md +0 -29
  272. package/dist/knowledge/references/zod.decorators.data-categories.md +0 -197
  273. package/dist/knowledge/rules/resource-schema-awareness.md +0 -77
  274. package/dist/knowledge/skills/config-app-shell/references/framework-public-shell-identity-api.md +0 -124
  275. package/dist/knowledge/skills/config-design-system/references/loading-placeholder-authoring.md +0 -47
  276. package/dist/knowledge/skills/config-navigation/references/framework-content-width-api.md +0 -98
  277. package/dist/knowledge/skills/config-navigation/references/framework-navigation-operation-override-api.md +0 -54
  278. package/dist/knowledge/skills/config-navigation/references/framework-navigation-vocabulary-api.md +0 -232
  279. package/dist/knowledge/skills/config-navigation/references/framework-navigation-zone-declaration-api.md +0 -149
  280. package/dist/knowledge/skills/config-navigation/references/how-navigation-resolves.md +0 -114
  281. package/dist/knowledge/skills/config-navigation/references/navigation-configuration-map.md +0 -133
  282. package/dist/knowledge/skills/config-saas/references/compliance-declarations.md +0 -111
  283. package/dist/knowledge/skills/resource-config-wiring/references/framework-personal-data-declaration-api.md +0 -622
  284. package/dist/knowledge/skills/resource-mcp-tool-exposure/references/framework-file-upload-grant-contract.md +0 -192
  285. package/dist/knowledge/skills/resource-schema-authoring/references/framework-personal-data-category-api.md +0 -245
  286. package/dist/knowledge/skills/settings-placement-authoring/SKILL.md +0 -134
  287. package/dist/knowledge/skills/settings-placement-authoring/references/framework-settings-destinations-catalog.md +0 -65
  288. package/dist/knowledge/skills/settings-placement-authoring/references/framework-settings-placement-api.md +0 -127
  289. /package/dist/knowledge/playbooks/{top_down.market-snapshot-produce → top_down.market-analysis}/structured-artifact-action.json +0 -0
@@ -1,18 +1,17 @@
1
1
  {
2
2
  "artifactVersion": "3",
3
- "frameworkVersion": "1.1.2",
4
- "generatorVersion": "1.1.2",
5
- "generatedAt": "2026-09-05T12:54:53.265Z",
3
+ "frameworkVersion": "1.1.0",
4
+ "generatorVersion": "1.1.0",
5
+ "generatedAt": "2026-08-29T22:33:33.791Z",
6
6
  "packageName": "@wildo-ai/framework-knowledge",
7
- "topicCount": 547,
8
- "referenceFileCount": 547,
7
+ "topicCount": 534,
8
+ "referenceFileCount": 534,
9
9
  "payload": {
10
10
  "topicIndexPath": "topic-index.json",
11
11
  "registriesDirectory": "registries",
12
12
  "referencesDirectory": "references",
13
13
  "skillsDirectory": "skills",
14
14
  "playbooksDirectory": "playbooks",
15
- "rulesDirectory": "rules",
16
15
  "assuranceAuthorityBasesDirectory": "assurance-authority-bases",
17
16
  "skillsIndexPath": "skills/INDEX.md"
18
17
  },
@@ -21,19 +20,19 @@
21
20
  "registryName": "source-tags",
22
21
  "filePath": "registries/source-tags.json",
23
22
  "description": "Source-derived tag registry for extracted framework references.",
24
- "entryCount": 440
23
+ "entryCount": 428
25
24
  },
26
25
  {
27
26
  "registryName": "framework-topics",
28
27
  "filePath": "registries/framework-topics.json",
29
28
  "description": "Topic registry derived from extracted framework-knowledge tags.",
30
- "entryCount": 547
29
+ "entryCount": 534
31
30
  },
32
31
  {
33
32
  "registryName": "playbooks",
34
33
  "filePath": "registries/playbooks.json",
35
34
  "description": "Compiled meta-workflow playbooks (app-creation methodology definitions).",
36
- "entryCount": 26
35
+ "entryCount": 17
37
36
  },
38
37
  {
39
38
  "registryName": "assurance-authority-bases",
@@ -67,9 +67,10 @@ anything:
67
67
  sequenced before later ones) and the **requirements** + **feature-drafts** (the
68
68
  prose contracts each task's brief points the coding agent at).
69
69
 
70
- (Both are already in your brief: the domain plan renders under "# Accepted application truth", and
71
- the real module/resource state arrives as the declared `workspace_truth` context section of your brief. There is no command to
72
- run in this mode.)
70
+ // TODO CLI COMMAND: wildo context journey-status
71
+ // (read current journey scope + approved domain plan + any existing build plan)
72
+ // TODO CLI COMMAND: wildo context domain-plan
73
+ // (read the module decomposition + per-module resource inventory to decompose)
73
74
 
74
75
  You **read** `domain-plan` (incl. its relationship drafts) + `roadmap` + `requirements` +
75
76
  `feature-drafts`; you **write** the `build-plan` family.
@@ -94,14 +95,9 @@ chain — so keep them separate and satisfy both:
94
95
  `Depends On`): `configure_application_foundation` → `model_domain_graph` →
95
96
  `define_interaction_semantics` → app-level `shape_user_experience` →
96
97
  `extend_application` → `connect_runtime_and_external_capabilities` →
97
- `assemble_verify_and_iterate`. You author neither the foundation nor the final
98
- assemble/verify — you decompose the middle bands (Topics 2–6). Topic 1 IS a sibling
99
- playbook (`bottom_up.foundation`), and Topic 7 IS one again
100
- (`bottom_up.assemble-verify`, rebuilt under issue #147 after its producer was removed
101
- with the verification/digest demolition). You still emit no Topic 7 task, and the reason
102
- is structural rather than a delegation: `BuildPlanTaskTargetKind` has no verification
103
- member, so app-wide verification cannot be expressed as a build-plan task at all — see
104
- the verify/quality-gate exclusion below. The edges you must respect: an
98
+ `assemble_verify_and_iterate`. You author neither the foundation (a sibling
99
+ playbook, Topic 1) nor the final assemble/verify (a sibling playbook, Topic 7) —
100
+ you decompose the middle bands (Topics 2–6). The edges you must respect: an
105
101
  operation task after the resources it acts on; an **app-level** view / navigation
106
102
  task after the interaction semantics and resources it composes; an extension after
107
103
  the UX it extends; an integration after the resources it connects.
@@ -186,38 +182,6 @@ Rules for a buildable domain-graph band:
186
182
  reminder date" — is objective-writing, not field authoring; listing concrete
187
183
  field-by-field types would be.)
188
184
 
189
- ## Step 1b — Emit the shell-placement tasks (when a placement plan exists)
190
-
191
- The **placement plan** decides WHERE every settings destination, resource operation
192
- and view sits in the shell, and why. It runs before you — it depends on the domain
193
- plan, not on your output, which is what keeps the two from forming a cycle. You do
194
- not re-decide any of it; you turn it into buildable work.
195
-
196
- Emit **one task per SURFACE the plan actually places something on**, never one per
197
- decision — the config files are per-surface, so a task per decision would have N
198
- tasks editing one file:
199
-
200
- | Task | Functional topic | Skill (the HOW) |
201
- |---|---|---|
202
- | Author the `<surface>` placement config from the accepted placement plan | `shape_user_experience` | `settings-placement-authoring` |
203
-
204
- Rules:
205
-
206
- - **Target kind is `SHELL_PLACEMENT`, carrying the surface.** Not
207
- `COMPANION_GENERATION_STEP` — that kind is "never a coding-agent run" and this is
208
- one. The host derives the mutation scope from the kind, so borrowing a neighbour's
209
- gives the task the wrong permissions.
210
- - **A surface the plan places nothing on gets no task.** An empty settings rail is
211
- not something to author.
212
- - **Order after the resources and views a surface references.** Placing a resource's
213
- LIST in the sidebar before that resource exists is a task that cannot verify.
214
- - **Carry the decision, not the config.** The task names the surface and points at
215
- the skill; which category a destination lands in and in what order is IN the plan,
216
- read by the coding agent at dispatch. Do not restate placements in the objective.
217
- - **No placement plan? Emit nothing here and say so.** Do not invent placement — a
218
- guessed arrangement is exactly what the plan exists to replace, and it would be
219
- invisible to the reader who assumes a placement task came from a decision.
220
-
221
185
  ## Step 2 — Emit the relationship-wiring tasks
222
186
 
223
187
  For each **relationship-draft**, emit one wiring task:
@@ -262,16 +226,6 @@ skill folder). Do **not** guess a skill name; route through the index.
262
226
  - **`connect_runtime_and_external_capabilities`** — providers, external connectors,
263
227
  billing wiring, email / notification wiring, storage, infra / environment config.
264
228
 
265
- ## Posture constraints are work, not commentary
266
-
267
- The vision family's compliance posture and constraints are INPUT on equal footing with the
268
- requirements: an obligation the posture states — a retention/erasure rule over customer data, a
269
- terminal-access (cookie/telemetry) posture, an operational-vs-marketing email distinction — needs a
270
- task that lands it, serving the nfr it substantiates. Do not compress a posture into an adjective
271
- inside another task's objective ("GDPR-appropriate handling"): an adjective is not schedulable,
272
- reviewable or landable. If the posture states an obligation and no task expresses it, the
273
- decomposition is incomplete.
274
-
275
229
  (Seed authoring and the label / email generation are companion-owned generation steps —
276
230
  see Step 4 — not coding-agent extension tasks.)
277
231
 
@@ -279,7 +233,7 @@ Rules:
279
233
 
280
234
  - **Every task names a real topic + a real skill.** A task with an invented topic or a
281
235
  skill folder that does not exist is a GAP (the dispatch playbook would have nothing
282
- to run). Route through the declared `skill_catalog` context section of your brief; do not invent.
236
+ to run). Route through the skills index; do not invent.
283
237
  - **Respect the topic dependency edges.** An operation task after the resources it acts
284
238
  on; an app-level view / navigation task after the interaction semantics **and** every
285
239
  resource it composes; an extension after the UX it extends; an integration after the
@@ -301,12 +255,6 @@ surfaces whose output they consume**:
301
255
  after the resources / ui-behavior / views whose labels it generates.
302
256
  - **`email-templates`** — email template + label generation and label translation.
303
257
  Order it after the notification/email surfaces it renders.
304
- - **`logo`** — the brand mark: an expert panel derives creative directions, marks are
305
- generated, a vision judge scores them, and the winner is promoted into the
306
- specifications brand SSOT. Order it after the brand brief exists; it depends on no
307
- code surface, so it may run early and in parallel with resource work. Author it at
308
- most once — an application has one accepted mark, and the step skips itself without
309
- calling a model when one is already accepted.
310
258
 
311
259
  Seed generation joins this vocabulary when its companion pipeline exists. Until then,
312
260
  do **not** author a seeds generation step — an unknown `generationStepRef` refuses at
@@ -352,14 +300,9 @@ Keep this playbook at decomposition depth. Explicitly **out of scope here**:
352
300
  are the dispatch playbook's concern — NOT modelled here. A task that describes *how* it
353
301
  is captured or locked is out of this playbook's depth.
354
302
  - **Verify / quality-gate mechanics.** Running typecheck, validators, tests, or reviewer
355
- agents *around* a dispatched task is the dispatch playbook's verify step — you do not model it.
356
- The app-wide assemble / verify phase (Topic 7) you also do not emit, and the reason is
357
- STRUCTURAL rather than delegation: a build-plan task's `target.kind` is one of `MODULE`,
358
- `RESOURCE_STAGE`, `RELATIONSHIP` or `COMPANION_GENERATION_STEP`, and none of them can express
359
- "verify the assembled application". There is no vocabulary for it, so a task claiming to do it
360
- would be a task no executor could run.
361
- **Do not read that as "a sibling playbook covers it" — none does today** (issue #147). Per-task
362
- verification exists; app-wide verification does not. You decompose Topics 2–6 only.
303
+ agents *around* a dispatched task is the dispatch playbook's verify step, and the app-wide
304
+ assemble / verify phase (Topic 7) is its own sibling playbook — you emit **neither**. You
305
+ decompose Topics 2–6 only.
363
306
  - **Multi-agent scale + interleaving.** Parallelising tasks across multiple coding
364
307
  agents, and interleaving the companion generation steps concurrently with coding-agent
365
308
  runs, is the **scale** playbook. You produce a linear-enough ordered graph with prose
@@ -381,7 +324,7 @@ playbooks.
381
324
 
382
325
  One artifact for this journey:
383
326
 
384
- - The **build-plan** at `specifications/src/build-plan/index.ts` — an ordered task
327
+ - The **build-plan** at `.wildo-saas/journey/<journeyId>/build-plan/` — an ordered task
385
328
  graph: the per-resource (schema / config / ui-behavior / spec) tasks, the
386
329
  relationship-wiring tasks, the interaction / UX / extension / integration tasks, any
387
330
  module-ensure tasks foundation did not cover, and the interleaved companion-generation
@@ -421,4 +364,4 @@ turn into dispatched, verified coding-agent runs.
421
364
 
422
365
  Formerly authored as an `llm_judge` quality gate; the generic rubric-only gate kind was retired at the flexible-intelligence hard cut (judgment now runs only through a compiled Evaluation Treatment). The checklist itself is creator-facing review guidance and is kept here, verbatim, minus the retired runner's closing sentence:
423
366
 
424
- Judge whether the drafted build plan is a coherent, complete, correctly-ordered decomposition of the approved domain plan into coding-agent tasks — WITHOUT straying into how those tasks execute. Assess seven invariants and mark each PASS / CONCERN / GAP with a one-line evidence note. (1) MODULE + RESOURCE COVERAGE — every resource in every module's inventory (mainResources + supportingResources) has build tasks; a resource with no task is a GAP (the build would not produce it). Task `moduleRef` values must be module ids the workspace section lists (an invented module id is a GAP — the dispatcher cannot route it), and a task whose objective CREATES a resource the workspace section shows already exists — instead of enriching it — is a CONCERN (it dispatches a no-op). Module slices are scaffolded by the foundation step (a sibling playbook), so a module needs a dedicated ensure-module task ONLY where foundation did not establish it — a module whose resources have tasks but which carries no redundant scaffold task is NOT a GAP (do not flag the absence of a module-scaffold task foundation already owns); a module added to the plan after foundation with neither a foundation slice nor an ensure-module task IS a GAP. (2) TASK WELL-FORMEDNESS — every task names exactly ONE functional topic that is a real MetaWorkflow_FunctionalTopic value (configure_application_foundation / model_domain_graph / define_interaction_semantics / shape_user_experience / extend_application / connect_runtime_and_external_capabilities / assemble_verify_and_iterate) and at least one skill that is a real folder in the app-knowledge skill catalog; a task with an invented topic or a dangling skill is a GAP. (3) PER-RESOURCE STAGE ORDER — for each resource, its tasks respect the inner order schema -> config -> ui-behavior -> spec; a config task ordered before that resource's schema task, or a spec task before its ui-behavior task, is a GAP (the build stage would run against a missing prerequisite). A supportingResource (e.g. a pure junction / lookup entity) may legitimately OMIT stages it does not need — a junction with schema + config and no ui-behavior is fine; only an out-of-ORDER stage (or a mainResource missing schema/config) is a GAP, not an intentionally-omitted stage on a supporting resource. (4) TOPIC DEPENDENCY ORDER — tasks respect the topic dependency edges (model_domain_graph before define_interaction_semantics; app-level shape_user_experience [views / navigation composing multiple resources or operations] after the interaction semantics and resources it composes; extend_application after the UX it extends; connect_runtime_and_external_capabilities after the resources it connects). Note the deliberate exception: a resource's OWN ui-behavior (its field displays / forms, a shape_user_experience task) depends only on that resource's own schema + config and MAY precede cross-resource operations — that is NOT a violation. What IS a GAP: an app-level view composing resources/operations placed before they exist, an integration task before the resources it connects, or any user-experience task before that resource's schema task. The per-resource spec task is a documentation capstone (topic model_domain_graph) and must be ordered after the schema / config / ui-behavior stages it documents; a spec task before its ui-behavior stage is a GAP. (5) RELATIONSHIP COVERAGE — every relationship-draft has a wiring task (bound to the module-relationships skill) ordered AFTER both endpoint resources' schema tasks; a relationship with no wiring task, or one ordered before its endpoints exist, is a GAP. (6) COMPANION-GENERATION INTERLEAVE — the executable companion-owned generation steps (`i18n-labels`, `email-templates`, `logo`) are present and placed AFTER the resources / modules whose output they consume; a labels-generation task ordered before the resources it labels, or a missing executable generation step for authored surfaces, is a CONCERN. `logo` is the exception to the ordering half — it consumes the brand brief rather than any code surface, so it is unordered with respect to resource work and only its ABSENCE (on an application with a brand brief) is a CONCERN. Do NOT flag the absence of a seeds step — seed generation has no companion pipeline yet and must not be authored. (7) BOUNDARY DISCIPLINE — the plan stays at DECOMPOSITION depth: it names tasks, their topic, their skill(s), their target, and their ordering intent; it does NOT specify how a task is DISPATCHED (single-flight locking, change-set capture, git baseline, verify/quality-gate mechanics = the dispatch-orchestration playbook) and does NOT solve multi-agent SCALE or interleaving concurrency (= the scale playbook). Any task that describes how a task EXECUTES rather than WHAT it builds, or that authors a schema / resolves a cardinality into a concrete FK / generates code, is a CONCERN (scope creep out of the decomposition phase). (The checklist is declarative: nothing executes it; the deterministic gates and the creator's approval remain the floors.)
367
+ Judge whether the drafted build plan is a coherent, complete, correctly-ordered decomposition of the approved domain plan into coding-agent tasks — WITHOUT straying into how those tasks execute. Assess seven invariants and mark each PASS / CONCERN / GAP with a one-line evidence note. (1) MODULE + RESOURCE COVERAGE — every resource in every module's inventory (mainResources + supportingResources) has build tasks; a resource with no task is a GAP (the build would not produce it). Task `moduleRef` values must be module ids the workspace section lists (an invented module id is a GAP — the dispatcher cannot route it), and a task whose objective CREATES a resource the workspace section shows already exists — instead of enriching it — is a CONCERN (it dispatches a no-op). Module slices are scaffolded by the foundation step (a sibling playbook), so a module needs a dedicated ensure-module task ONLY where foundation did not establish it — a module whose resources have tasks but which carries no redundant scaffold task is NOT a GAP (do not flag the absence of a module-scaffold task foundation already owns); a module added to the plan after foundation with neither a foundation slice nor an ensure-module task IS a GAP. (2) TASK WELL-FORMEDNESS — every task names exactly ONE functional topic that is a real MetaWorkflow_FunctionalTopic value (configure_application_foundation / model_domain_graph / define_interaction_semantics / shape_user_experience / extend_application / connect_runtime_and_external_capabilities / assemble_verify_and_iterate) and at least one skill that is a real folder in the app-knowledge skill catalog; a task with an invented topic or a dangling skill is a GAP. (3) PER-RESOURCE STAGE ORDER — for each resource, its tasks respect the inner order schema -> config -> ui-behavior -> spec; a config task ordered before that resource's schema task, or a spec task before its ui-behavior task, is a GAP (the build stage would run against a missing prerequisite). A supportingResource (e.g. a pure junction / lookup entity) may legitimately OMIT stages it does not need — a junction with schema + config and no ui-behavior is fine; only an out-of-ORDER stage (or a mainResource missing schema/config) is a GAP, not an intentionally-omitted stage on a supporting resource. (4) TOPIC DEPENDENCY ORDER — tasks respect the topic dependency edges (model_domain_graph before define_interaction_semantics; app-level shape_user_experience [views / navigation composing multiple resources or operations] after the interaction semantics and resources it composes; extend_application after the UX it extends; connect_runtime_and_external_capabilities after the resources it connects). Note the deliberate exception: a resource's OWN ui-behavior (its field displays / forms, a shape_user_experience task) depends only on that resource's own schema + config and MAY precede cross-resource operations — that is NOT a violation. What IS a GAP: an app-level view composing resources/operations placed before they exist, an integration task before the resources it connects, or any user-experience task before that resource's schema task. The per-resource spec task is a documentation capstone (topic model_domain_graph) and must be ordered after the schema / config / ui-behavior stages it documents; a spec task before its ui-behavior stage is a GAP. (5) RELATIONSHIP COVERAGE — every relationship-draft has a wiring task (bound to the module-relationships skill) ordered AFTER both endpoint resources' schema tasks; a relationship with no wiring task, or one ordered before its endpoints exist, is a GAP. (6) COMPANION-GENERATION INTERLEAVE — the executable companion-owned generation steps (`i18n-labels`, `email-templates`) are present and placed AFTER the resources / modules whose output they consume; a labels-generation task ordered before the resources it labels, or a missing executable generation step for authored surfaces, is a CONCERN. Do NOT flag the absence of a seeds step — seed generation has no companion pipeline yet and must not be authored. (7) BOUNDARY DISCIPLINE — the plan stays at DECOMPOSITION depth: it names tasks, their topic, their skill(s), their target, and their ordering intent; it does NOT specify how a task is DISPATCHED (single-flight locking, change-set capture, git baseline, verify/quality-gate mechanics = the dispatch-orchestration playbook) and does NOT solve multi-agent SCALE or interleaving concurrency (= the scale playbook). Any task that describes how a task EXECUTES rather than WHAT it builds, or that authors a schema / resolves a cardinality into a concrete FK / generates code, is a CONCERN (scope creep out of the decomposition phase). (The checklist is declarative: nothing executes it; the deterministic gates and the creator's approval remain the floors.)
@@ -1,10 +1,14 @@
1
1
  {
2
2
  "ref": "bottom_up.build-decompose",
3
- "version": "0.2.0",
3
+ "version": "0.1.0",
4
4
  "phase": "bottom_up",
5
- "intent": "Bottom-up build decomposition — the FIRST build-execution playbook, the pivot from planning the domain (the domain-plan) to decomposing the BUILD. Reads the approved domain-plan (the ModuleBusinessSemantics module drafts + per-module resource inventory), the relationship drafts inside it (the inter-resource relationship intents), and the definition set (roadmap for phasing, requirements + feature-drafts for task-brief context), and the PLACEMENT PLAN (where each settings destination, resource operation and view sits in the shell, decided upstream), and DECOMPOSES the build work into an ordered set of coding-agent tasks. Each task is bound onto (a) the 7-topic functional taxonomy (configure_application_foundation -> model_domain_graph -> define_interaction_semantics -> shape_user_experience -> extend_application -> connect_runtime_and_external_capabilities -> assemble_verify_and_iterate) and (b) the app-knowledge skill catalog (each task names the skill(s) that carry its technical HOW). The tasks follow the per-resource inner order (schema -> config -> ui-behavior -> spec, then operations / interaction semantics, then UX, then extensions, then integrations), with companion-owned generation steps (labels / i18n, email templates, seeds) interleaved at the points their inputs exist. This playbook PRODUCES the ordered task graph (a build-plan artifact); it does NOT dispatch tasks to coding agents (that is the dispatch-orchestration playbook downstream), does NOT capture change-sets / single-flight-lock / verify, and does NOT solve multi-agent scale or interleaving. It authors no schemas and generates no code. v1 scaffold methodology — a typed build-task-graph contract, a dependency-DAG solver, and a collection validator are a later depth phase, not here.",
5
+ "intent": "Bottom-up build decomposition — the FIRST build-execution playbook, the pivot from planning the domain (the domain-plan) to decomposing the BUILD. Reads the approved domain-plan (the ModuleBusinessSemantics module drafts + per-module resource inventory), the relationship drafts inside it (the inter-resource relationship intents), and the definition set (roadmap for phasing, requirements + feature-drafts for task-brief context), and DECOMPOSES the build work into an ordered set of coding-agent tasks. Each task is bound onto (a) the 7-topic functional taxonomy (configure_application_foundation -> model_domain_graph -> define_interaction_semantics -> shape_user_experience -> extend_application -> connect_runtime_and_external_capabilities -> assemble_verify_and_iterate) and (b) the app-knowledge skill catalog (each task names the skill(s) that carry its technical HOW). The tasks follow the per-resource inner order (schema -> config -> ui-behavior -> spec, then operations / interaction semantics, then UX, then extensions, then integrations), with companion-owned generation steps (labels / i18n, email templates, seeds) interleaved at the points their inputs exist. This playbook PRODUCES the ordered task graph (a build-plan artifact); it does NOT dispatch tasks to coding agents (that is the dispatch-orchestration playbook downstream), does NOT capture change-sets / single-flight-lock / verify, and does NOT solve multi-agent scale or interleaving. It authors no schemas and generates no code. v1 scaffold methodology — a typed build-task-graph contract, a dependency-DAG solver, and a collection validator are a later depth phase, not here.",
6
6
  "functionalTopics": [],
7
7
  "preconditions": [
8
+ {
9
+ "kind": "phase_is",
10
+ "phase": "bottom_up"
11
+ },
8
12
  {
9
13
  "kind": "artifact_exists",
10
14
  "selector": {
@@ -24,24 +28,18 @@
24
28
  },
25
29
  {
26
30
  "family": "feature-drafts"
27
- },
28
- {
29
- "family": "placement-plan"
30
- },
31
- {
32
- "family": "vision-brief"
33
31
  }
34
32
  ],
35
33
  "outputs": [
36
34
  {
37
35
  "family": "build-plan",
38
36
  "schemaRef": "saas-specifications:BuildPlanTaskGraph",
39
- "description": "The build decomposition — an ORDERED set of coding-agent build tasks (a task graph) that turns the approved domain plan into a sequence of buildable units. Each task carries: a stable task ref, the target it builds (a module, a resource + one of its build stages, a relationship, a companion-generation step, a shell-surface placement config), the ONE functional topic it belongs to (a real MetaWorkflow_FunctionalTopic value), the skill(s) that carry its technical HOW (real folders from the app-knowledge skill catalog, resolved via the skills router), and its ordering intent (which tasks must precede it — expressed as prose prerequisite references, NOT a solved DAG). The ordering respects two axes: (a) the cross-app topic dependency edges (model_domain_graph before define_interaction_semantics before app-level shape_user_experience before extend_application before connect_runtime_and_external_capabilities; foundation and assemble/verify are owned by sibling playbooks) and (b) the per-resource stage sequence schema -> config -> ui-behavior -> spec — which deliberately CROSSES topics (ui-behavior is shape_user_experience; the spec is a model_domain_graph documentation capstone ordered last) and so is not monotonic on axis (a); a roadmap-driven MVP-first preference breaks ties within a band. TYPED since the flexible-intelligence Block 3: the `_core` build-task-graph contract (`BuildPlanTaskGraph` — `tasks[]` with a stable `taskRef`, a closed `BuildPlanTaskTargetKind` target (MODULE / RESOURCE_STAGE / RELATIONSHIP / COMPANION_GENERATION_STEP / SHELL_PLACEMENT), exactly one `functionalTopic`, `skillRefs`, DECLARED `prerequisiteTaskRefs` the host resolves for readiness, and traceability `servesRefs`) is the family schema; the provider answers the strict `BuildPlanTaskGraphGeneration` shape and the trusted runtime stamps refs and version. The task never carries paths, commands, prompts or runtime controls — the dispatch host derives mutation scope and verification from the target kind. `validateBuildPlanTaskGraph` is the deterministic validator (prerequisite cycles are a hard floor; a resource stage without its predecessor stage is an authoring warning); the coherence reviewer checklist (`build-plan-coherent`, in the method) remains the semantic check and the creator's approve_result review the trust floor. Consumed by the bottom-up DISPATCH-ORCHESTRATION playbook (which single-flight-dispatches each task through the coding-agent contract) and the SCALE playbook (which parallelises + interleaves the companion generation steps) — both downstream of this decomposition."
37
+ "placement": ".wildo-saas/journey/<journeyId>/build-plan/",
38
+ "description": "The build decomposition — an ORDERED set of coding-agent build tasks (a task graph) that turns the approved domain plan into a sequence of buildable units. Each task carries: a stable task ref, the target it builds (a module, a resource + one of its build stages, a relationship, a companion-generation step), the ONE functional topic it belongs to (a real MetaWorkflow_FunctionalTopic value), the skill(s) that carry its technical HOW (real folders from the app-knowledge skill catalog, resolved via the skills router), and its ordering intent (which tasks must precede it — expressed as prose prerequisite references, NOT a solved DAG). The ordering respects two axes: (a) the cross-app topic dependency edges (model_domain_graph before define_interaction_semantics before app-level shape_user_experience before extend_application before connect_runtime_and_external_capabilities; foundation and assemble/verify are owned by sibling playbooks) and (b) the per-resource stage sequence schema -> config -> ui-behavior -> spec — which deliberately CROSSES topics (ui-behavior is shape_user_experience; the spec is a model_domain_graph documentation capstone ordered last) and so is not monotonic on axis (a); a roadmap-driven MVP-first preference breaks ties within a band. TYPED since the flexible-intelligence Block 3: the `_core` build-task-graph contract (`BuildPlanTaskGraph` — `tasks[]` with a stable `taskRef`, a closed `BuildPlanTaskTargetKind` target (MODULE / RESOURCE_STAGE / RELATIONSHIP / COMPANION_GENERATION_STEP), exactly one `functionalTopic`, `skillRefs`, DECLARED `prerequisiteTaskRefs` the host resolves for readiness, and traceability `servesRefs`) is the family schema; the provider answers the strict `BuildPlanTaskGraphGeneration` shape and the trusted runtime stamps refs and version. The task never carries paths, commands, prompts or runtime controls — the dispatch host derives mutation scope and verification from the target kind. `validateBuildPlanTaskGraph` is the deterministic validator (prerequisite cycles are a hard floor; a resource stage without its predecessor stage is an authoring warning); the coherence reviewer checklist (`build-plan-coherent`, in the method) remains the semantic check and the creator's approve_result review the trust floor. Consumed by the bottom-up DISPATCH-ORCHESTRATION playbook (which single-flight-dispatches each task through the coding-agent contract) and the SCALE playbook (which parallelises + interleaves the companion generation steps) — both downstream of this decomposition."
40
39
  }
41
40
  ],
42
- "stepOutputs": [],
43
41
  "method": {
44
- "guidance": "# Build Decompose — Domain Plan → Ordered Coding-Agent Task Graph (v1 scaffold)\n\n### Target Application Framing\n\nThis knowledge is for configuring behavior in the target application.\nWildo is the framework surface being used, not the product being built.\n\nRead and apply these patterns from the application-developer point of view:\n\n- how the application should configure the relevant app-level file\n- how the application should use framework-provided factories, enums, and helpers\n- how the application should avoid mixing frontend, backend, and infrastructure concerns\n\n\n> **This is a v1 scaffold methodology.** It is a working first cut meant to be\n> iterated. The decomposition heuristic, the per-resource stage order, and the\n> task-shape convention below are deliberately explicit so they can be tuned against\n> real runs — treat them as a starting rubric, not a frozen contract. The *analytical\n> depth* of build planning (a typed task-graph contract, a dependency-DAG solver with\n> transitive ordering, a collection validator, cost/effort estimation) is intentionally\n> shallow here and is deepened in a later phase; do not perfect it in this playbook.\n\n## Where you are in the journey\n\nThis is the **first build-execution playbook** — the pivot from **planning the\ndomain** (the domain-plan: modules, per-module resource inventory, relationship\nintents) to **decomposing the build** (the ordered set of buildable tasks). It runs\nin the **bottom-up phase**, after the domain plan exists (`artifact_exists\ndomain-plan`). You are not re-opening domain questions here — you are turning an\n*approved* domain plan into the *ordered work that builds it*.\n\nDownstream of this playbook, two further playbooks consume your output: the\n**dispatch-orchestration** playbook single-flight-dispatches each task through the\ncoding-agent contract, and the **scale** playbook parallelises and interleaves the\ncompanion generation steps. **You author neither of those concerns** — see the\nboundary section below.\n\n## What this playbook does\n\nYou are the **build planner**. This playbook reads the approved domain plan and the\ndefinition set and drafts the **build plan**: the answer to *\"what ordered sequence\nof coding-agent tasks turns this domain plan into a running app?\"* You produce **one\nartifact**: the **build-plan** family — an **ordered task graph**, each task bound\nonto the **7-topic functional taxonomy** and the **app-knowledge skill catalog**.\n\nThis is a **decomposition pass**. You name tasks, their target, their topic, their\nskill(s), and their ordering intent. You do **not** dispatch any task, capture any\nchange-set, author any schema, or generate any code — that is the job of the\ndownstream dispatch / scale playbooks and the coding agents they run.\n\n## Read state first — what you read, the one artifact you write\n\nThis playbook is **idempotent** and, on a re-run, a *refinement*. Before decomposing\nanything:\n\n1. Read the current journey state and scope through the `journey-status` skill (it\n owns the read; do not re-derive it here). Confirm the domain plan is present and\n approved, and check whether a `build-plan` already exists from an earlier run\n (refine it, do not re-author — see below).\n2. Read the approved domain plan and the definition set. **Load-bearing** (these drive\n the decomposition): the **domain-plan** (`domain-plan` — the module decomposition +\n each module's `mainResources` / `supportingResources` inventory) and the\n **relationship drafts** (inside the domain-plan value — the inter-resource relationship\n intents, each with two ends + cardinality intent + ownership direction).\n **Contextual** (they shape ordering and task briefs, not the core decomposition):\n the **roadmap** (`roadmap` — the release phasing, so MVP-critical modules are\n sequenced before later ones) and the **requirements** + **feature-drafts** (the\n prose contracts each task's brief points the coding agent at).\n\n(Both are already in your brief: the domain plan renders under \"# Accepted application truth\", and\nthe real module/resource state arrives as the declared `workspace_truth` context section of your brief. There is no command to\nrun in this mode.)\n\nYou **read** `domain-plan` (incl. its relationship drafts) + `roadmap` + `requirements` +\n`feature-drafts`; you **write** the `build-plan` family.\n\n3. Read the **current application workspace** section supplied with this brief (the real\n module ids and each resource's present schema fields). It is BINDING, in both directions:\n - Every task's `moduleRef` MUST be one of the listed module ids, exactly — a module id\n the workspace does not carry is an invented address the dispatcher cannot route.\n - A resource the workspace already lists exists as a **compose-born starter skeleton**\n (registered, typechecking, carrying the fields shown). Its stage tasks are\n **enrichment** tasks: their objective states what domain content to ADD or CHANGE.\n An objective that asks to \"create\" or \"scaffold\" such a resource describes work that\n is already done, and the dispatched coding run will correctly change nothing.\n\n## The two ordering axes\n\nEvery task you emit is placed on **two ordering axes**. They are **distinct** — the\nper-resource sequence deliberately *spans* topics and is not monotonic on the topic\nchain — so keep them separate and satisfy both:\n\n1. **The topic dependency edges** (across the whole app — from the taxonomy's\n `Depends On`): `configure_application_foundation` → `model_domain_graph` →\n `define_interaction_semantics` → app-level `shape_user_experience` →\n `extend_application` → `connect_runtime_and_external_capabilities` →\n `assemble_verify_and_iterate`. You author neither the foundation nor the final\n assemble/verify — you decompose the middle bands (Topics 2–6). Topic 1 IS a sibling\n playbook (`bottom_up.foundation`), and Topic 7 IS one again\n (`bottom_up.assemble-verify`, rebuilt under issue #147 after its producer was removed\n with the verification/digest demolition). You still emit no Topic 7 task, and the reason\n is structural rather than a delegation: `BuildPlanTaskTargetKind` has no verification\n member, so app-wide verification cannot be expressed as a build-plan task at all — see\n the verify/quality-gate exclusion below. The edges you must respect: an\n operation task after the resources it acts on; an **app-level** view / navigation\n task after the interaction semantics and resources it composes; an extension after\n the UX it extends; an integration after the resources it connects.\n2. **The per-resource inner stage order** (within one resource):\n **schema → config → ui-behavior → spec.** This is a *dependency* sequence (each\n stage needs the prior artifact) and it deliberately **crosses topics**: schema +\n config are `model_domain_graph`, ui-behavior is `shape_user_experience`, and the\n spec is the `model_domain_graph` documentation capstone authored last. Two\n consequences to get right:\n - A resource's **own** ui-behavior (its field displays / forms) depends only on\n that resource's schema + config — so it may be ordered **before** cross-resource\n operations. That is **not** a topic-chain violation; only *app-level* UX\n (views / navigation composing multiple resources or operations) waits on the\n interaction-semantics band.\n - The **spec** task is a documentation capstone: order it **after** the stages it\n documents (schema, config, ui-behavior), regardless of its `model_domain_graph`\n topic binding. Its topic says *what* it documents; its ordering says *after what*.\n\n**Sequencing tiebreaker — MVP first.** The two axes constrain *relative* order but leave\nfreedom in which module to build first. Break that tie with the **roadmap** — but note the\nroadmap is requirement-addressed, not module-addressed: a phase delivers\n`deliversRequirementRefs` / `deliversSuccessCriterionRefs`, not modules. So trace each\nmodule's requirements to the earliest roadmap phase that delivers them, then sequence the\nmodules whose requirements land in an earlier phase (NOW / MVP) before those whose\nrequirements land later (NEXT / LATER), so a partial build is a coherent MVP slice rather\nthan a scattered half of every module. This is a soft ordering preference, not a hard\nprerequisite — never let it override the two hard axes above.\n\n## Step 1 — Emit the module + resource tasks (the domain-graph band)\n\nWalk the domain plan module by module. For each **module**, first check whether the\n**foundation step** (a sibling playbook) already scaffolded its slice — it normally has,\nbecause foundation materialises every module in the domain plan. Emit a module task only\nwhere that is not guaranteed; then, for each **resource** in that module's inventory,\nemit the ordered per-resource stage tasks:\n\n| Task | Functional topic | Skill (the HOW) |\n|---|---|---|\n| **(only when needed)** Ensure module `<id>` slice exists + is registered across runtimes — **normally already done by the foundation step**; emit this only for a module the foundation step did NOT establish (e.g. one added to the plan after foundation ran). Idempotent, never a blind re-scaffold | `model_domain_graph` | `resource-add-module` + `module-registration` |\n| Resource `<name>` — domain schema (fields, enums, structural decorators). **Workspace-aware**: when the resource already exists as a compose-born starter (see the workspace section), the objective names the DOMAIN content to add to it; only a resource the workspace does not list gets a skeleton-creation objective | `model_domain_graph` | `resource-add-resource` (skeleton, only when the resource does not exist yet) + `resource-schema-authoring` (the persisted shape) |\n| Resource `<name>` — config (registry presence, core operation verbs, access / role scope — but NOT cross-resource relationships, which are the dedicated Step 2 tasks) | `model_domain_graph` | `resource-config-wiring` |\n| Resource `<name>` — ui-behavior (field displays / forms / enum chrome — the resource's own UX) | `shape_user_experience` | `resource-ui-behavior` |\n| Resource `<name>` — spec (canonical business semantics — the per-resource documentation capstone) | `model_domain_graph` | `spec-resource-update` |\n\n> **Two things this table is careful about.** (a) **`ui-behavior` is `shape_user_experience`,\n> not interaction semantics** — a resource's field-display / form chrome is UX (Topic 4's\n> \"resource displays / forms\"); the resource's *operations* (custom verbs, access, scope) are a\n> SEPARATE interaction-semantics band, Step 3. (b) The **`spec` task is a documentation\n> capstone**: it documents the resource's fields (domain), operations (interaction), and frontend\n> (UX), so its single topic binding is `model_domain_graph` (the spec's canonical role is business\n> semantics), but its *ordering* is \"after the stages it documents\", not a topic-chain position —\n> see the ordering axes below. (c) **Module scaffolding + registration is the foundation\n> step's job** (a sibling playbook that materialises every domain-plan module). Do NOT emit a\n> module-scaffold or module-registration task for a module foundation already established — that\n> double-counts foundation. The build loop's domain-graph band is per-**resource**; only ensure a\n> module slice where foundation genuinely did not (e.g. a module added to the plan after\n> foundation ran).\n\nRules for a buildable domain-graph band:\n\n- **Cover every module and every resource** in the inventory (both `mainResources`\n and `supportingResources`). A module or resource with no task is a coverage GAP (the\n build would not produce it).\n- **Not every resource needs every stage.** A `mainResource` (the entity the module is\n about) typically earns the full schema → config → ui-behavior → spec sequence. A\n `supportingResource` may not: a pure junction / lookup entity needs schema + config\n but no ui-behavior (it has no first-class UX surface). Emit the stages the resource\n genuinely needs, and say why a stage is omitted — do NOT pad every supporting\n resource with a UX task it will never use.\n- **Respect the per-resource stage order** (schema → config → ui-behavior → spec) as\n prose prerequisite references on each task (\"depends on: resource `<name>` — schema\").\n- **State objectives against workspace reality.** A task for a resource the workspace\n section already lists says what to ENRICH (\"author the deal-pipeline stage enum and\n amount/close-date fields the domain plan declares on `deals`\"), never \"create the\n `deals` resource\" — that file exists and a creation objective dispatches a no-op.\n `moduleRef` values come from the workspace section verbatim.\n- **Do not author fields or schemas here.** The task *names* the resource and its\n stage and points the coding agent at the skill; *what* fields the resource carries\n is resolved by the coding agent at dispatch time, from the domain plan + the skill.\n If you catch yourself writing a field list, stop — that is the coding agent's job.\n (Naming the domain CONCERN a stage must cover — \"the pipeline stages\", \"the follow-up\n reminder date\" — is objective-writing, not field authoring; listing concrete\n field-by-field types would be.)\n\n## Step 1b — Emit the shell-placement tasks (when a placement plan exists)\n\nThe **placement plan** decides WHERE every settings destination, resource operation\nand view sits in the shell, and why. It runs before you — it depends on the domain\nplan, not on your output, which is what keeps the two from forming a cycle. You do\nnot re-decide any of it; you turn it into buildable work.\n\nEmit **one task per SURFACE the plan actually places something on**, never one per\ndecision — the config files are per-surface, so a task per decision would have N\ntasks editing one file:\n\n| Task | Functional topic | Skill (the HOW) |\n|---|---|---|\n| Author the `<surface>` placement config from the accepted placement plan | `shape_user_experience` | `settings-placement-authoring` |\n\nRules:\n\n- **Target kind is `SHELL_PLACEMENT`, carrying the surface.** Not\n `COMPANION_GENERATION_STEP` — that kind is \"never a coding-agent run\" and this is\n one. The host derives the mutation scope from the kind, so borrowing a neighbour's\n gives the task the wrong permissions.\n- **A surface the plan places nothing on gets no task.** An empty settings rail is\n not something to author.\n- **Order after the resources and views a surface references.** Placing a resource's\n LIST in the sidebar before that resource exists is a task that cannot verify.\n- **Carry the decision, not the config.** The task names the surface and points at\n the skill; which category a destination lands in and in what order is IN the plan,\n read by the coding agent at dispatch. Do not restate placements in the objective.\n- **No placement plan? Emit nothing here and say so.** Do not invent placement — a\n guessed arrangement is exactly what the plan exists to replace, and it would be\n invisible to the reader who assumes a placement task came from a decision.\n\n## Step 2 — Emit the relationship-wiring tasks\n\nFor each **relationship-draft**, emit one wiring task:\n\n| Task | Functional topic | Skill (the HOW) |\n|---|---|---|\n| Wire relationship `<A> <-> <B>` (`<cardinality>`, `<owner>` holds the ref) | `model_domain_graph` | `module-relationships` |\n\nRules:\n\n- **This is the single home for cross-resource relationships.** A relationship is wired\n ONCE, here, by the `module-relationships` skill (which coordinates the FK across the\n owner's schema + config, the target's relationship map, and both specs coherently). Do\n NOT also wire it inside the per-resource config task in Step 1 — that config task\n establishes the resource's registry presence and core verbs, not its cross-resource\n FKs. Emitting the relationship in both places double-counts the work.\n- **Order after both endpoints' schema tasks.** A relationship-wiring task references\n two resources; both must have a schema task ordered before it (a relationship wired\n before an endpoint exists is a GAP).\n- **Carry the intent, not the resolution.** The task states the two ends, the\n cardinality intent, and the ownership direction from the relationship-draft. The\n cardinality-to-FK-holder resolution (discriminator / conditional relationships, the\n physical FK placement) is the `module-relationships` skill's job **at dispatch\n time**, not decided here.\n\n## Step 3 — Emit the interaction, UX, extension, and integration tasks\n\nOnce the domain graph is decomposed, emit the tasks for the later topic bands, drawn\nfrom the requirements + feature-drafts. Bind each task to **one** functional topic and\nto the skill(s) that carry its HOW, resolved from the **skills router**\n(`.claude/skills/INDEX.md` in the app — the catalog index that routes a task to its\nskill folder). Do **not** guess a skill name; route through the index.\n\n- **`define_interaction_semantics`** — custom operations, lifecycle behaviour, access /\n role / scope rules, rate limits — interaction beyond the default resource verbs.\n- **`shape_user_experience`** — app-level composite views, navigation, layouts, the app\n shell, design-system application, charts (the cross-resource UX; a resource's own\n field-display ui-behavior was already emitted in Step 1).\n- **`extend_application`** — custom UI components / widgets, custom implementation\n logic, PDF templates / renderers, workers / minions and other auxiliary execution\n surfaces (the controlled extension points where the declarative model is not enough).\n- **`connect_runtime_and_external_capabilities`** — providers, external connectors,\n billing wiring, email / notification wiring, storage, infra / environment config.\n\n## Posture constraints are work, not commentary\n\nThe vision family's compliance posture and constraints are INPUT on equal footing with the\nrequirements: an obligation the posture states — a retention/erasure rule over customer data, a\nterminal-access (cookie/telemetry) posture, an operational-vs-marketing email distinction — needs a\ntask that lands it, serving the nfr it substantiates. Do not compress a posture into an adjective\ninside another task's objective (\"GDPR-appropriate handling\"): an adjective is not schedulable,\nreviewable or landable. If the posture states an obligation and no task expresses it, the\ndecomposition is incomplete.\n\n(Seed authoring and the label / email generation are companion-owned generation steps —\nsee Step 4 — not coding-agent extension tasks.)\n\nRules:\n\n- **Every task names a real topic + a real skill.** A task with an invented topic or a\n skill folder that does not exist is a GAP (the dispatch playbook would have nothing\n to run). Route through the declared `skill_catalog` context section of your brief; do not invent.\n- **Respect the topic dependency edges.** An operation task after the resources it acts\n on; an app-level view / navigation task after the interaction semantics **and** every\n resource it composes; an extension after the UX it extends; an integration after the\n resources it connects. (A resource's own field-display ui-behavior was already emitted\n in Step 1 and needs only that resource's schema/config — see the ordering axes.)\n- **Draw tasks from the definition set, not a blank page.** A UX or operation task\n earns its existence from a requirement or feature-draft; a task justified by nothing\n in the definition set is a CONCERN (speculative work).\n\n## Step 4 — Interleave the companion-owned generation steps\n\nSome build steps are **companion-owned deterministic generation**, not coding-agent\nwork. Emit these as tasks too — `target.kind: COMPANION_GENERATION_STEP` with\n`generationStepRef` set to the EXACT step slug below (the companion executes only this\nclosed vocabulary; any other slug refuses at dispatch) — and **order them after the\nsurfaces whose output they consume**:\n\n- **`i18n-labels`** — label generation + translation to every enabled locale. Order it\n after the resources / ui-behavior / views whose labels it generates.\n- **`email-templates`** — email template + label generation and label translation.\n Order it after the notification/email surfaces it renders.\n- **`logo`** — the brand mark: an expert panel derives creative directions, marks are\n generated, a vision judge scores them, and the winner is promoted into the\n specifications brand SSOT. Order it after the brand brief exists; it depends on no\n code surface, so it may run early and in parallel with resource work. Author it at\n most once — an application has one accepted mark, and the step skips itself without\n calling a model when one is already accepted.\n\nSeed generation joins this vocabulary when its companion pipeline exists. Until then,\ndo **not** author a seeds generation step — an unknown `generationStepRef` refuses at\ndispatch instead of parking the build.\n\nYou **place** these steps in the order; you do **not** design how they run\nconcurrently with coding-agent tasks (that interleaving-at-scale concern is the scale\nplaybook's job — see the boundary below).\n\n## Refine, don't re-author\n\n- **Keep what still holds.** On a re-run, do not re-decompose modules or resources\n whose tasks are already correct. Only add a task, re-order where a prerequisite\n changed, or add/correct a relationship-wiring task where the domain plan genuinely\n changed.\n- **Reuse existing task refs.** A task that already exists keeps its ref — never mint a\n second ref for the same unit of work.\n- **Never orphan an ordering reference.** A task's prerequisite reference must name a\n task that is actually in the plan. If you remove or rename a task, follow it into\n every prerequisite reference.\n\n## Quality gate — `build-plan-coherent` (declarative at scaffold depth)\n\nThe build plan is checked against the `build-plan-coherent` **reviewer checklist** (see the end of this method):\nseven invariants (module + resource coverage, task well-formedness, per-resource stage\norder, topic dependency order, relationship coverage, companion-generation interleave,\nand decomposition-depth boundary discipline), each marked PASS / CONCERN / GAP.\n\nThis checklist is **declarative**: no runtime executes it (rubric-only judge gates were retired at the flexible-intelligence hard cut — judgment runs only through a compiled Evaluation Treatment, and this playbook has none yet), so it ships as the **creator's review checklist** — nothing runs it automatically. The **trust floor** for accepting the build plan today is the\ncreator's `approve_result` review of the produced task graph. There is intentionally\n**no deterministic gate**: no typed build-task-graph contract or collection validator\nexists at this phase (see the boundary below).\n\n## Scaffold-depth boundary (deferred to a later depth phase, or owned by a sibling)\n\nKeep this playbook at decomposition depth. Explicitly **out of scope here**:\n\n- **Dispatch execution.** You do NOT dispatch any task, spawn any coding agent, build a\n context pack, or run the coding-agent contract. That is the **dispatch-orchestration**\n playbook, downstream of this decomposition.\n- **Workspace-mutation safety.** Single-flight locking, clean-worktree preconditions,\n change-set capture (git baseline / diff), and the failure-policy revert/flag mechanics\n are the dispatch playbook's concern — NOT modelled here. A task that describes *how* it\n is captured or locked is out of this playbook's depth.\n- **Verify / quality-gate mechanics.** Running typecheck, validators, tests, or reviewer\n agents *around* a dispatched task is the dispatch playbook's verify step — you do not model it.\n The app-wide assemble / verify phase (Topic 7) you also do not emit, and the reason is\n STRUCTURAL rather than delegation: a build-plan task's `target.kind` is one of `MODULE`,\n `RESOURCE_STAGE`, `RELATIONSHIP` or `COMPANION_GENERATION_STEP`, and none of them can express\n \"verify the assembled application\". There is no vocabulary for it, so a task claiming to do it\n would be a task no executor could run.\n **Do not read that as \"a sibling playbook covers it\" — none does today** (issue #147). Per-task\n verification exists; app-wide verification does not. You decompose Topics 2–6 only.\n- **Multi-agent scale + interleaving.** Parallelising tasks across multiple coding\n agents, and interleaving the companion generation steps concurrently with coding-agent\n runs, is the **scale** playbook. You produce a linear-enough ordered graph with prose\n prerequisite intent; you do NOT solve the concurrency schedule.\n- **Schema / field authoring + code generation.** You name resources and stages; you do\n NOT author fields, enums, decorators, Zod schemas, or any code, and you do NOT resolve\n a cardinality intent into a concrete FK. That is the coding agent at dispatch time.\n- **A typed build-task-graph contract + a collection validator.** The `build-plan`\n family has **no schemaRef** because the framework ships no `_core` build-task-graph\n shape, and it has no deterministic gate because no task-graph validator exists. A typed\n task contract, a dependency-DAG solver, and a module-set coverage validator are all a\n filed depth-phase item — do **NOT** reshape `_core` here.\n\nIf you find yourself perfecting any of the above, stop and leave the slice at\ndecomposition depth — depth is a dedicated later pass, and dispatch/scale are sibling\nplaybooks.\n\n## What you emit\n\nOne artifact for this journey:\n\n- The **build-plan** at `specifications/src/build-plan/index.ts` — an ordered task\n graph: the per-resource (schema / config / ui-behavior / spec) tasks, the\n relationship-wiring tasks, the interaction / UX / extension / integration tasks, any\n module-ensure tasks foundation did not cover, and the interleaved companion-generation\n steps — each carrying its target, its one functional topic, its skill(s), and its prose\n ordering intent.\n\nThe creator reviews the result (approval posture `approve_result`) before it is accepted\nas the journey's build plan, which the dispatch-orchestration and scale playbooks then\nturn into dispatched, verified coding-agent runs.\n\n## References\n\n- `.claude/skills/journey-status/SKILL.md` — read the current journey state and scope,\n and confirm the approved domain plan is in place to decompose the build from.\n- `.claude/skills/resource-add-module/SKILL.md` — the module-scaffolding vocabulary, for\n the conditional ensure-module task (only where the foundation step did not establish the\n module slice).\n- `.claude/skills/resource-add-resource/SKILL.md` — the resource vocabulary (the\n resource-skeleton task in the schema stage).\n- `.claude/skills/resource-schema-authoring/SKILL.md` — the schema stage (first\n per-resource task).\n- `.claude/skills/resource-config-wiring/SKILL.md` — the config stage (second\n per-resource task).\n- `.claude/skills/resource-ui-behavior/SKILL.md` — the ui-behavior stage (third\n per-resource task).\n- `.claude/skills/spec-resource-update/SKILL.md` — the spec stage (fourth per-resource\n task).\n- `.claude/skills/module-relationships/SKILL.md` — the relationship-wiring task's HOW\n (cardinality-to-FK-holder resolution, at dispatch time — named here, not performed).\n- `.claude/skills/module-registration/SKILL.md` — the cross-runtime module-registration\n task's HOW.\n- `.claude/skills/INDEX.md` — the skills router: consult it to bind each interaction /\n UX / extension / integration task to its real skill folder from the full catalog. Do\n not invent skill names; route through the index.\n\n## Reviewer checklist — `build-plan-coherent`\n\nFormerly authored as an `llm_judge` quality gate; the generic rubric-only gate kind was retired at the flexible-intelligence hard cut (judgment now runs only through a compiled Evaluation Treatment). The checklist itself is creator-facing review guidance and is kept here, verbatim, minus the retired runner's closing sentence:\n\nJudge whether the drafted build plan is a coherent, complete, correctly-ordered decomposition of the approved domain plan into coding-agent tasks — WITHOUT straying into how those tasks execute. Assess seven invariants and mark each PASS / CONCERN / GAP with a one-line evidence note. (1) MODULE + RESOURCE COVERAGE — every resource in every module's inventory (mainResources + supportingResources) has build tasks; a resource with no task is a GAP (the build would not produce it). Task `moduleRef` values must be module ids the workspace section lists (an invented module id is a GAP — the dispatcher cannot route it), and a task whose objective CREATES a resource the workspace section shows already exists — instead of enriching it — is a CONCERN (it dispatches a no-op). Module slices are scaffolded by the foundation step (a sibling playbook), so a module needs a dedicated ensure-module task ONLY where foundation did not establish it — a module whose resources have tasks but which carries no redundant scaffold task is NOT a GAP (do not flag the absence of a module-scaffold task foundation already owns); a module added to the plan after foundation with neither a foundation slice nor an ensure-module task IS a GAP. (2) TASK WELL-FORMEDNESS — every task names exactly ONE functional topic that is a real MetaWorkflow_FunctionalTopic value (configure_application_foundation / model_domain_graph / define_interaction_semantics / shape_user_experience / extend_application / connect_runtime_and_external_capabilities / assemble_verify_and_iterate) and at least one skill that is a real folder in the app-knowledge skill catalog; a task with an invented topic or a dangling skill is a GAP. (3) PER-RESOURCE STAGE ORDER — for each resource, its tasks respect the inner order schema -> config -> ui-behavior -> spec; a config task ordered before that resource's schema task, or a spec task before its ui-behavior task, is a GAP (the build stage would run against a missing prerequisite). A supportingResource (e.g. a pure junction / lookup entity) may legitimately OMIT stages it does not need — a junction with schema + config and no ui-behavior is fine; only an out-of-ORDER stage (or a mainResource missing schema/config) is a GAP, not an intentionally-omitted stage on a supporting resource. (4) TOPIC DEPENDENCY ORDER — tasks respect the topic dependency edges (model_domain_graph before define_interaction_semantics; app-level shape_user_experience [views / navigation composing multiple resources or operations] after the interaction semantics and resources it composes; extend_application after the UX it extends; connect_runtime_and_external_capabilities after the resources it connects). Note the deliberate exception: a resource's OWN ui-behavior (its field displays / forms, a shape_user_experience task) depends only on that resource's own schema + config and MAY precede cross-resource operations — that is NOT a violation. What IS a GAP: an app-level view composing resources/operations placed before they exist, an integration task before the resources it connects, or any user-experience task before that resource's schema task. The per-resource spec task is a documentation capstone (topic model_domain_graph) and must be ordered after the schema / config / ui-behavior stages it documents; a spec task before its ui-behavior stage is a GAP. (5) RELATIONSHIP COVERAGE — every relationship-draft has a wiring task (bound to the module-relationships skill) ordered AFTER both endpoint resources' schema tasks; a relationship with no wiring task, or one ordered before its endpoints exist, is a GAP. (6) COMPANION-GENERATION INTERLEAVE — the executable companion-owned generation steps (`i18n-labels`, `email-templates`, `logo`) are present and placed AFTER the resources / modules whose output they consume; a labels-generation task ordered before the resources it labels, or a missing executable generation step for authored surfaces, is a CONCERN. `logo` is the exception to the ordering half — it consumes the brand brief rather than any code surface, so it is unordered with respect to resource work and only its ABSENCE (on an application with a brand brief) is a CONCERN. Do NOT flag the absence of a seeds step — seed generation has no companion pipeline yet and must not be authored. (7) BOUNDARY DISCIPLINE — the plan stays at DECOMPOSITION depth: it names tasks, their topic, their skill(s), their target, and their ordering intent; it does NOT specify how a task is DISPATCHED (single-flight locking, change-set capture, git baseline, verify/quality-gate mechanics = the dispatch-orchestration playbook) and does NOT solve multi-agent SCALE or interleaving concurrency (= the scale playbook). Any task that describes how a task EXECUTES rather than WHAT it builds, or that authors a schema / resolves a cardinality into a concrete FK / generates code, is a CONCERN (scope creep out of the decomposition phase). (The checklist is declarative: nothing executes it; the deterministic gates and the creator's approval remain the floors.)\n",
42
+ "guidance": "# Build Decompose — Domain Plan → Ordered Coding-Agent Task Graph (v1 scaffold)\n\n### Target Application Framing\n\nThis knowledge is for configuring behavior in the target application.\nWildo is the framework surface being used, not the product being built.\n\nRead and apply these patterns from the application-developer point of view:\n\n- how the application should configure the relevant app-level file\n- how the application should use framework-provided factories, enums, and helpers\n- how the application should avoid mixing frontend, backend, and infrastructure concerns\n\n\n> **This is a v1 scaffold methodology.** It is a working first cut meant to be\n> iterated. The decomposition heuristic, the per-resource stage order, and the\n> task-shape convention below are deliberately explicit so they can be tuned against\n> real runs — treat them as a starting rubric, not a frozen contract. The *analytical\n> depth* of build planning (a typed task-graph contract, a dependency-DAG solver with\n> transitive ordering, a collection validator, cost/effort estimation) is intentionally\n> shallow here and is deepened in a later phase; do not perfect it in this playbook.\n\n## Where you are in the journey\n\nThis is the **first build-execution playbook** — the pivot from **planning the\ndomain** (the domain-plan: modules, per-module resource inventory, relationship\nintents) to **decomposing the build** (the ordered set of buildable tasks). It runs\nin the **bottom-up phase**, after the domain plan exists (`artifact_exists\ndomain-plan`). You are not re-opening domain questions here — you are turning an\n*approved* domain plan into the *ordered work that builds it*.\n\nDownstream of this playbook, two further playbooks consume your output: the\n**dispatch-orchestration** playbook single-flight-dispatches each task through the\ncoding-agent contract, and the **scale** playbook parallelises and interleaves the\ncompanion generation steps. **You author neither of those concerns** — see the\nboundary section below.\n\n## What this playbook does\n\nYou are the **build planner**. This playbook reads the approved domain plan and the\ndefinition set and drafts the **build plan**: the answer to *\"what ordered sequence\nof coding-agent tasks turns this domain plan into a running app?\"* You produce **one\nartifact**: the **build-plan** family — an **ordered task graph**, each task bound\nonto the **7-topic functional taxonomy** and the **app-knowledge skill catalog**.\n\nThis is a **decomposition pass**. You name tasks, their target, their topic, their\nskill(s), and their ordering intent. You do **not** dispatch any task, capture any\nchange-set, author any schema, or generate any code — that is the job of the\ndownstream dispatch / scale playbooks and the coding agents they run.\n\n## Read state first — what you read, the one artifact you write\n\nThis playbook is **idempotent** and, on a re-run, a *refinement*. Before decomposing\nanything:\n\n1. Read the current journey state and scope through the `journey-status` skill (it\n owns the read; do not re-derive it here). Confirm the domain plan is present and\n approved, and check whether a `build-plan` already exists from an earlier run\n (refine it, do not re-author — see below).\n2. Read the approved domain plan and the definition set. **Load-bearing** (these drive\n the decomposition): the **domain-plan** (`domain-plan` — the module decomposition +\n each module's `mainResources` / `supportingResources` inventory) and the\n **relationship drafts** (inside the domain-plan value — the inter-resource relationship\n intents, each with two ends + cardinality intent + ownership direction).\n **Contextual** (they shape ordering and task briefs, not the core decomposition):\n the **roadmap** (`roadmap` — the release phasing, so MVP-critical modules are\n sequenced before later ones) and the **requirements** + **feature-drafts** (the\n prose contracts each task's brief points the coding agent at).\n\n// TODO CLI COMMAND: wildo context journey-status\n// (read current journey scope + approved domain plan + any existing build plan)\n// TODO CLI COMMAND: wildo context domain-plan\n// (read the module decomposition + per-module resource inventory to decompose)\n\nYou **read** `domain-plan` (incl. its relationship drafts) + `roadmap` + `requirements` +\n`feature-drafts`; you **write** the `build-plan` family.\n\n3. Read the **current application workspace** section supplied with this brief (the real\n module ids and each resource's present schema fields). It is BINDING, in both directions:\n - Every task's `moduleRef` MUST be one of the listed module ids, exactly — a module id\n the workspace does not carry is an invented address the dispatcher cannot route.\n - A resource the workspace already lists exists as a **compose-born starter skeleton**\n (registered, typechecking, carrying the fields shown). Its stage tasks are\n **enrichment** tasks: their objective states what domain content to ADD or CHANGE.\n An objective that asks to \"create\" or \"scaffold\" such a resource describes work that\n is already done, and the dispatched coding run will correctly change nothing.\n\n## The two ordering axes\n\nEvery task you emit is placed on **two ordering axes**. They are **distinct** — the\nper-resource sequence deliberately *spans* topics and is not monotonic on the topic\nchain — so keep them separate and satisfy both:\n\n1. **The topic dependency edges** (across the whole app — from the taxonomy's\n `Depends On`): `configure_application_foundation` → `model_domain_graph` →\n `define_interaction_semantics` → app-level `shape_user_experience` →\n `extend_application` → `connect_runtime_and_external_capabilities` →\n `assemble_verify_and_iterate`. You author neither the foundation (a sibling\n playbook, Topic 1) nor the final assemble/verify (a sibling playbook, Topic 7) —\n you decompose the middle bands (Topics 2–6). The edges you must respect: an\n operation task after the resources it acts on; an **app-level** view / navigation\n task after the interaction semantics and resources it composes; an extension after\n the UX it extends; an integration after the resources it connects.\n2. **The per-resource inner stage order** (within one resource):\n **schema → config → ui-behavior → spec.** This is a *dependency* sequence (each\n stage needs the prior artifact) and it deliberately **crosses topics**: schema +\n config are `model_domain_graph`, ui-behavior is `shape_user_experience`, and the\n spec is the `model_domain_graph` documentation capstone authored last. Two\n consequences to get right:\n - A resource's **own** ui-behavior (its field displays / forms) depends only on\n that resource's schema + config — so it may be ordered **before** cross-resource\n operations. That is **not** a topic-chain violation; only *app-level* UX\n (views / navigation composing multiple resources or operations) waits on the\n interaction-semantics band.\n - The **spec** task is a documentation capstone: order it **after** the stages it\n documents (schema, config, ui-behavior), regardless of its `model_domain_graph`\n topic binding. Its topic says *what* it documents; its ordering says *after what*.\n\n**Sequencing tiebreaker — MVP first.** The two axes constrain *relative* order but leave\nfreedom in which module to build first. Break that tie with the **roadmap** — but note the\nroadmap is requirement-addressed, not module-addressed: a phase delivers\n`deliversRequirementRefs` / `deliversSuccessCriterionRefs`, not modules. So trace each\nmodule's requirements to the earliest roadmap phase that delivers them, then sequence the\nmodules whose requirements land in an earlier phase (NOW / MVP) before those whose\nrequirements land later (NEXT / LATER), so a partial build is a coherent MVP slice rather\nthan a scattered half of every module. This is a soft ordering preference, not a hard\nprerequisite — never let it override the two hard axes above.\n\n## Step 1 — Emit the module + resource tasks (the domain-graph band)\n\nWalk the domain plan module by module. For each **module**, first check whether the\n**foundation step** (a sibling playbook) already scaffolded its slice — it normally has,\nbecause foundation materialises every module in the domain plan. Emit a module task only\nwhere that is not guaranteed; then, for each **resource** in that module's inventory,\nemit the ordered per-resource stage tasks:\n\n| Task | Functional topic | Skill (the HOW) |\n|---|---|---|\n| **(only when needed)** Ensure module `<id>` slice exists + is registered across runtimes — **normally already done by the foundation step**; emit this only for a module the foundation step did NOT establish (e.g. one added to the plan after foundation ran). Idempotent, never a blind re-scaffold | `model_domain_graph` | `resource-add-module` + `module-registration` |\n| Resource `<name>` — domain schema (fields, enums, structural decorators). **Workspace-aware**: when the resource already exists as a compose-born starter (see the workspace section), the objective names the DOMAIN content to add to it; only a resource the workspace does not list gets a skeleton-creation objective | `model_domain_graph` | `resource-add-resource` (skeleton, only when the resource does not exist yet) + `resource-schema-authoring` (the persisted shape) |\n| Resource `<name>` — config (registry presence, core operation verbs, access / role scope — but NOT cross-resource relationships, which are the dedicated Step 2 tasks) | `model_domain_graph` | `resource-config-wiring` |\n| Resource `<name>` — ui-behavior (field displays / forms / enum chrome — the resource's own UX) | `shape_user_experience` | `resource-ui-behavior` |\n| Resource `<name>` — spec (canonical business semantics — the per-resource documentation capstone) | `model_domain_graph` | `spec-resource-update` |\n\n> **Two things this table is careful about.** (a) **`ui-behavior` is `shape_user_experience`,\n> not interaction semantics** — a resource's field-display / form chrome is UX (Topic 4's\n> \"resource displays / forms\"); the resource's *operations* (custom verbs, access, scope) are a\n> SEPARATE interaction-semantics band, Step 3. (b) The **`spec` task is a documentation\n> capstone**: it documents the resource's fields (domain), operations (interaction), and frontend\n> (UX), so its single topic binding is `model_domain_graph` (the spec's canonical role is business\n> semantics), but its *ordering* is \"after the stages it documents\", not a topic-chain position —\n> see the ordering axes below. (c) **Module scaffolding + registration is the foundation\n> step's job** (a sibling playbook that materialises every domain-plan module). Do NOT emit a\n> module-scaffold or module-registration task for a module foundation already established — that\n> double-counts foundation. The build loop's domain-graph band is per-**resource**; only ensure a\n> module slice where foundation genuinely did not (e.g. a module added to the plan after\n> foundation ran).\n\nRules for a buildable domain-graph band:\n\n- **Cover every module and every resource** in the inventory (both `mainResources`\n and `supportingResources`). A module or resource with no task is a coverage GAP (the\n build would not produce it).\n- **Not every resource needs every stage.** A `mainResource` (the entity the module is\n about) typically earns the full schema → config → ui-behavior → spec sequence. A\n `supportingResource` may not: a pure junction / lookup entity needs schema + config\n but no ui-behavior (it has no first-class UX surface). Emit the stages the resource\n genuinely needs, and say why a stage is omitted — do NOT pad every supporting\n resource with a UX task it will never use.\n- **Respect the per-resource stage order** (schema → config → ui-behavior → spec) as\n prose prerequisite references on each task (\"depends on: resource `<name>` — schema\").\n- **State objectives against workspace reality.** A task for a resource the workspace\n section already lists says what to ENRICH (\"author the deal-pipeline stage enum and\n amount/close-date fields the domain plan declares on `deals`\"), never \"create the\n `deals` resource\" — that file exists and a creation objective dispatches a no-op.\n `moduleRef` values come from the workspace section verbatim.\n- **Do not author fields or schemas here.** The task *names* the resource and its\n stage and points the coding agent at the skill; *what* fields the resource carries\n is resolved by the coding agent at dispatch time, from the domain plan + the skill.\n If you catch yourself writing a field list, stop — that is the coding agent's job.\n (Naming the domain CONCERN a stage must cover — \"the pipeline stages\", \"the follow-up\n reminder date\" — is objective-writing, not field authoring; listing concrete\n field-by-field types would be.)\n\n## Step 2 — Emit the relationship-wiring tasks\n\nFor each **relationship-draft**, emit one wiring task:\n\n| Task | Functional topic | Skill (the HOW) |\n|---|---|---|\n| Wire relationship `<A> <-> <B>` (`<cardinality>`, `<owner>` holds the ref) | `model_domain_graph` | `module-relationships` |\n\nRules:\n\n- **This is the single home for cross-resource relationships.** A relationship is wired\n ONCE, here, by the `module-relationships` skill (which coordinates the FK across the\n owner's schema + config, the target's relationship map, and both specs coherently). Do\n NOT also wire it inside the per-resource config task in Step 1 — that config task\n establishes the resource's registry presence and core verbs, not its cross-resource\n FKs. Emitting the relationship in both places double-counts the work.\n- **Order after both endpoints' schema tasks.** A relationship-wiring task references\n two resources; both must have a schema task ordered before it (a relationship wired\n before an endpoint exists is a GAP).\n- **Carry the intent, not the resolution.** The task states the two ends, the\n cardinality intent, and the ownership direction from the relationship-draft. The\n cardinality-to-FK-holder resolution (discriminator / conditional relationships, the\n physical FK placement) is the `module-relationships` skill's job **at dispatch\n time**, not decided here.\n\n## Step 3 — Emit the interaction, UX, extension, and integration tasks\n\nOnce the domain graph is decomposed, emit the tasks for the later topic bands, drawn\nfrom the requirements + feature-drafts. Bind each task to **one** functional topic and\nto the skill(s) that carry its HOW, resolved from the **skills router**\n(`.claude/skills/INDEX.md` in the app — the catalog index that routes a task to its\nskill folder). Do **not** guess a skill name; route through the index.\n\n- **`define_interaction_semantics`** — custom operations, lifecycle behaviour, access /\n role / scope rules, rate limits — interaction beyond the default resource verbs.\n- **`shape_user_experience`** — app-level composite views, navigation, layouts, the app\n shell, design-system application, charts (the cross-resource UX; a resource's own\n field-display ui-behavior was already emitted in Step 1).\n- **`extend_application`** — custom UI components / widgets, custom implementation\n logic, PDF templates / renderers, workers / minions and other auxiliary execution\n surfaces (the controlled extension points where the declarative model is not enough).\n- **`connect_runtime_and_external_capabilities`** — providers, external connectors,\n billing wiring, email / notification wiring, storage, infra / environment config.\n\n(Seed authoring and the label / email generation are companion-owned generation steps —\nsee Step 4 — not coding-agent extension tasks.)\n\nRules:\n\n- **Every task names a real topic + a real skill.** A task with an invented topic or a\n skill folder that does not exist is a GAP (the dispatch playbook would have nothing\n to run). Route through the skills index; do not invent.\n- **Respect the topic dependency edges.** An operation task after the resources it acts\n on; an app-level view / navigation task after the interaction semantics **and** every\n resource it composes; an extension after the UX it extends; an integration after the\n resources it connects. (A resource's own field-display ui-behavior was already emitted\n in Step 1 and needs only that resource's schema/config — see the ordering axes.)\n- **Draw tasks from the definition set, not a blank page.** A UX or operation task\n earns its existence from a requirement or feature-draft; a task justified by nothing\n in the definition set is a CONCERN (speculative work).\n\n## Step 4 — Interleave the companion-owned generation steps\n\nSome build steps are **companion-owned deterministic generation**, not coding-agent\nwork. Emit these as tasks too — `target.kind: COMPANION_GENERATION_STEP` with\n`generationStepRef` set to the EXACT step slug below (the companion executes only this\nclosed vocabulary; any other slug refuses at dispatch) — and **order them after the\nsurfaces whose output they consume**:\n\n- **`i18n-labels`** — label generation + translation to every enabled locale. Order it\n after the resources / ui-behavior / views whose labels it generates.\n- **`email-templates`** — email template + label generation and label translation.\n Order it after the notification/email surfaces it renders.\n\nSeed generation joins this vocabulary when its companion pipeline exists. Until then,\ndo **not** author a seeds generation step — an unknown `generationStepRef` refuses at\ndispatch instead of parking the build.\n\nYou **place** these steps in the order; you do **not** design how they run\nconcurrently with coding-agent tasks (that interleaving-at-scale concern is the scale\nplaybook's job — see the boundary below).\n\n## Refine, don't re-author\n\n- **Keep what still holds.** On a re-run, do not re-decompose modules or resources\n whose tasks are already correct. Only add a task, re-order where a prerequisite\n changed, or add/correct a relationship-wiring task where the domain plan genuinely\n changed.\n- **Reuse existing task refs.** A task that already exists keeps its ref — never mint a\n second ref for the same unit of work.\n- **Never orphan an ordering reference.** A task's prerequisite reference must name a\n task that is actually in the plan. If you remove or rename a task, follow it into\n every prerequisite reference.\n\n## Quality gate — `build-plan-coherent` (declarative at scaffold depth)\n\nThe build plan is checked against the `build-plan-coherent` **reviewer checklist** (see the end of this method):\nseven invariants (module + resource coverage, task well-formedness, per-resource stage\norder, topic dependency order, relationship coverage, companion-generation interleave,\nand decomposition-depth boundary discipline), each marked PASS / CONCERN / GAP.\n\nThis checklist is **declarative**: no runtime executes it (rubric-only judge gates were retired at the flexible-intelligence hard cut — judgment runs only through a compiled Evaluation Treatment, and this playbook has none yet), so it ships as the **creator's review checklist** — nothing runs it automatically. The **trust floor** for accepting the build plan today is the\ncreator's `approve_result` review of the produced task graph. There is intentionally\n**no deterministic gate**: no typed build-task-graph contract or collection validator\nexists at this phase (see the boundary below).\n\n## Scaffold-depth boundary (deferred to a later depth phase, or owned by a sibling)\n\nKeep this playbook at decomposition depth. Explicitly **out of scope here**:\n\n- **Dispatch execution.** You do NOT dispatch any task, spawn any coding agent, build a\n context pack, or run the coding-agent contract. That is the **dispatch-orchestration**\n playbook, downstream of this decomposition.\n- **Workspace-mutation safety.** Single-flight locking, clean-worktree preconditions,\n change-set capture (git baseline / diff), and the failure-policy revert/flag mechanics\n are the dispatch playbook's concern — NOT modelled here. A task that describes *how* it\n is captured or locked is out of this playbook's depth.\n- **Verify / quality-gate mechanics.** Running typecheck, validators, tests, or reviewer\n agents *around* a dispatched task is the dispatch playbook's verify step, and the app-wide\n assemble / verify phase (Topic 7) is its own sibling playbook — you emit **neither**. You\n decompose Topics 2–6 only.\n- **Multi-agent scale + interleaving.** Parallelising tasks across multiple coding\n agents, and interleaving the companion generation steps concurrently with coding-agent\n runs, is the **scale** playbook. You produce a linear-enough ordered graph with prose\n prerequisite intent; you do NOT solve the concurrency schedule.\n- **Schema / field authoring + code generation.** You name resources and stages; you do\n NOT author fields, enums, decorators, Zod schemas, or any code, and you do NOT resolve\n a cardinality intent into a concrete FK. That is the coding agent at dispatch time.\n- **A typed build-task-graph contract + a collection validator.** The `build-plan`\n family has **no schemaRef** because the framework ships no `_core` build-task-graph\n shape, and it has no deterministic gate because no task-graph validator exists. A typed\n task contract, a dependency-DAG solver, and a module-set coverage validator are all a\n filed depth-phase item — do **NOT** reshape `_core` here.\n\nIf you find yourself perfecting any of the above, stop and leave the slice at\ndecomposition depth — depth is a dedicated later pass, and dispatch/scale are sibling\nplaybooks.\n\n## What you emit\n\nOne artifact for this journey:\n\n- The **build-plan** at `.wildo-saas/journey/<journeyId>/build-plan/` — an ordered task\n graph: the per-resource (schema / config / ui-behavior / spec) tasks, the\n relationship-wiring tasks, the interaction / UX / extension / integration tasks, any\n module-ensure tasks foundation did not cover, and the interleaved companion-generation\n steps — each carrying its target, its one functional topic, its skill(s), and its prose\n ordering intent.\n\nThe creator reviews the result (approval posture `approve_result`) before it is accepted\nas the journey's build plan, which the dispatch-orchestration and scale playbooks then\nturn into dispatched, verified coding-agent runs.\n\n## References\n\n- `.claude/skills/journey-status/SKILL.md` — read the current journey state and scope,\n and confirm the approved domain plan is in place to decompose the build from.\n- `.claude/skills/resource-add-module/SKILL.md` — the module-scaffolding vocabulary, for\n the conditional ensure-module task (only where the foundation step did not establish the\n module slice).\n- `.claude/skills/resource-add-resource/SKILL.md` — the resource vocabulary (the\n resource-skeleton task in the schema stage).\n- `.claude/skills/resource-schema-authoring/SKILL.md` — the schema stage (first\n per-resource task).\n- `.claude/skills/resource-config-wiring/SKILL.md` — the config stage (second\n per-resource task).\n- `.claude/skills/resource-ui-behavior/SKILL.md` — the ui-behavior stage (third\n per-resource task).\n- `.claude/skills/spec-resource-update/SKILL.md` — the spec stage (fourth per-resource\n task).\n- `.claude/skills/module-relationships/SKILL.md` — the relationship-wiring task's HOW\n (cardinality-to-FK-holder resolution, at dispatch time — named here, not performed).\n- `.claude/skills/module-registration/SKILL.md` — the cross-runtime module-registration\n task's HOW.\n- `.claude/skills/INDEX.md` — the skills router: consult it to bind each interaction /\n UX / extension / integration task to its real skill folder from the full catalog. Do\n not invent skill names; route through the index.\n\n## Reviewer checklist — `build-plan-coherent`\n\nFormerly authored as an `llm_judge` quality gate; the generic rubric-only gate kind was retired at the flexible-intelligence hard cut (judgment now runs only through a compiled Evaluation Treatment). The checklist itself is creator-facing review guidance and is kept here, verbatim, minus the retired runner's closing sentence:\n\nJudge whether the drafted build plan is a coherent, complete, correctly-ordered decomposition of the approved domain plan into coding-agent tasks — WITHOUT straying into how those tasks execute. Assess seven invariants and mark each PASS / CONCERN / GAP with a one-line evidence note. (1) MODULE + RESOURCE COVERAGE — every resource in every module's inventory (mainResources + supportingResources) has build tasks; a resource with no task is a GAP (the build would not produce it). Task `moduleRef` values must be module ids the workspace section lists (an invented module id is a GAP — the dispatcher cannot route it), and a task whose objective CREATES a resource the workspace section shows already exists — instead of enriching it — is a CONCERN (it dispatches a no-op). Module slices are scaffolded by the foundation step (a sibling playbook), so a module needs a dedicated ensure-module task ONLY where foundation did not establish it — a module whose resources have tasks but which carries no redundant scaffold task is NOT a GAP (do not flag the absence of a module-scaffold task foundation already owns); a module added to the plan after foundation with neither a foundation slice nor an ensure-module task IS a GAP. (2) TASK WELL-FORMEDNESS — every task names exactly ONE functional topic that is a real MetaWorkflow_FunctionalTopic value (configure_application_foundation / model_domain_graph / define_interaction_semantics / shape_user_experience / extend_application / connect_runtime_and_external_capabilities / assemble_verify_and_iterate) and at least one skill that is a real folder in the app-knowledge skill catalog; a task with an invented topic or a dangling skill is a GAP. (3) PER-RESOURCE STAGE ORDER — for each resource, its tasks respect the inner order schema -> config -> ui-behavior -> spec; a config task ordered before that resource's schema task, or a spec task before its ui-behavior task, is a GAP (the build stage would run against a missing prerequisite). A supportingResource (e.g. a pure junction / lookup entity) may legitimately OMIT stages it does not need — a junction with schema + config and no ui-behavior is fine; only an out-of-ORDER stage (or a mainResource missing schema/config) is a GAP, not an intentionally-omitted stage on a supporting resource. (4) TOPIC DEPENDENCY ORDER — tasks respect the topic dependency edges (model_domain_graph before define_interaction_semantics; app-level shape_user_experience [views / navigation composing multiple resources or operations] after the interaction semantics and resources it composes; extend_application after the UX it extends; connect_runtime_and_external_capabilities after the resources it connects). Note the deliberate exception: a resource's OWN ui-behavior (its field displays / forms, a shape_user_experience task) depends only on that resource's own schema + config and MAY precede cross-resource operations — that is NOT a violation. What IS a GAP: an app-level view composing resources/operations placed before they exist, an integration task before the resources it connects, or any user-experience task before that resource's schema task. The per-resource spec task is a documentation capstone (topic model_domain_graph) and must be ordered after the schema / config / ui-behavior stages it documents; a spec task before its ui-behavior stage is a GAP. (5) RELATIONSHIP COVERAGE — every relationship-draft has a wiring task (bound to the module-relationships skill) ordered AFTER both endpoint resources' schema tasks; a relationship with no wiring task, or one ordered before its endpoints exist, is a GAP. (6) COMPANION-GENERATION INTERLEAVE — the executable companion-owned generation steps (`i18n-labels`, `email-templates`) are present and placed AFTER the resources / modules whose output they consume; a labels-generation task ordered before the resources it labels, or a missing executable generation step for authored surfaces, is a CONCERN. Do NOT flag the absence of a seeds step — seed generation has no companion pipeline yet and must not be authored. (7) BOUNDARY DISCIPLINE — the plan stays at DECOMPOSITION depth: it names tasks, their topic, their skill(s), their target, and their ordering intent; it does NOT specify how a task is DISPATCHED (single-flight locking, change-set capture, git baseline, verify/quality-gate mechanics = the dispatch-orchestration playbook) and does NOT solve multi-agent SCALE or interleaving concurrency (= the scale playbook). Any task that describes how a task EXECUTES rather than WHAT it builds, or that authors a schema / resolves a cardinality into a concrete FK / generates code, is a CONCERN (scope creep out of the decomposition phase). (The checklist is declarative: nothing executes it; the deterministic gates and the creator's approval remain the floors.)\n",
45
43
  "skillRefs": [
46
44
  "journey-status",
47
45
  "resource-add-module",
@@ -52,16 +50,10 @@
52
50
  "spec-resource-update",
53
51
  "module-relationships",
54
52
  "module-registration"
55
- ],
56
- "contextSources": [
57
- "workspace_truth",
58
- "skill_catalog"
59
- ],
60
- "suspendsForClarification": false,
61
- "briefAdequacyGate": false,
62
- "briefAdequacyExcludedSources": []
53
+ ]
63
54
  },
64
55
  "executor": "companion_agent",
56
+ "qualityGates": [],
65
57
  "approval": "approve_result",
66
58
  "budget": {
67
59
  "maxRuns": 3
@@ -82,20 +82,6 @@ export enum BuildPlanTaskTargetKind {
82
82
  RELATIONSHIP = 'RELATIONSHIP',
83
83
  /** A companion-owned deterministic generation step (labels, seeds, emails…) interleaved by the build loop, never a coding-agent run. */
84
84
  COMPANION_GENERATION_STEP = 'COMPANION_GENERATION_STEP',
85
- /**
86
- * Authoring one SHELL SURFACE's placement configuration from the accepted
87
- * placement plan — the settings rail, the sidebar, the user menu or the
88
- * command palette.
89
- *
90
- * Its own kind rather than a reuse of the neighbours, because none of them is
91
- * true of it: it is not a MODULE or a RESOURCE_STAGE (it is application-wide
92
- * and belongs to no resource), not a RELATIONSHIP, and emphatically not a
93
- * COMPANION_GENERATION_STEP — that kind is documented as "never a coding-agent
94
- * run" and writing `settings-hub.config.ts` is exactly a coding-agent run.
95
- * Borrowing one would hand the host the wrong mutation scope and the wrong
96
- * verification, which is what the closed vocabulary exists to prevent.
97
- */
98
- SHELL_PLACEMENT = 'SHELL_PLACEMENT',
99
85
  }
100
86
 
101
87
  /** The per-resource build stages, in their fixed order. */
@@ -134,24 +120,6 @@ export const BuildPlanTaskTargetSchema = z.discriminatedUnion('kind', [
134
120
  /** The companion generation step this task runs (e.g. labels, seeds); resolved by the companion, never by a coding agent. */
135
121
  generationStepRef: SlugSchema,
136
122
  }),
137
- z.strictObject({
138
- kind: z.literal(BuildPlanTaskTargetKind.SHELL_PLACEMENT),
139
- /**
140
- * Which shell surface this task authors — the placement family's OWN
141
- * `PlacementSurface`, deliberately not a build-plan copy of it.
142
- *
143
- * A copy was written first and was a defect, caught by probing the landing
144
- * renderer rather than by any test: `PlacementAddress` discriminates on
145
- * `surface` with `z.literal(...)` per option, so only the VALUES survive into
146
- * the schema, and the renderer resolves a discriminator by matching that value
147
- * SET against the exported enums. Two enums with identical values made the
148
- * match ambiguous, the renderer correctly refused to guess an owner, and the
149
- * address discriminator became unnameable — a landed placement plan would have
150
- * emitted `surface: "SETTINGS_HUB"` as a bare string instead of
151
- * `PlacementSurface.SETTINGS_HUB`. One concept, one named source.
152
- */
153
- surface: z.enum(PlacementSurface),
154
- }),
155
123
  ]);
156
124
  export type BuildPlanTaskTarget = z.infer<typeof BuildPlanTaskTargetSchema>;
157
125
 
@@ -172,19 +140,7 @@ export const BuildPlanTaskSchema = z.strictObject({
172
140
  /** One sentence of intent: what this task delivers. */
173
141
  objective: NonEmptyStringSchema,
174
142
  target: BuildPlanTaskTargetSchema,
175
- /**
176
- * Exactly ONE functional topic this task belongs to.
177
- *
178
- * **It does NOT drive ordering** — this said "drives cross-app ordering" until 2026-08-30 and
179
- * nothing ever ordered by it. Sequencing is `prerequisiteTaskRefs`, resolved by the host, and it
180
- * is the only thing that decides what may run next.
181
- *
182
- * What it DOES: the dispatch host stamps it into the coding-agent's task payload beside
183
- * `skillRefs`, so the agent is told which phase of building the application this task belongs to.
184
- * That is context an LLM reads, not a value the runtime branches on — the distinction matters,
185
- * because a reader who believes it orders will look here for a scheduling bug that lives in the
186
- * prerequisite graph. See issue #124.
187
- */
143
+ /** Exactly ONE functional topic this task belongs to (drives cross-app ordering). */
188
144
  functionalTopic: z.enum(MetaWorkflow_FunctionalTopic),
189
145
  /** Installed app-knowledge skill folders that carry the technical HOW; resolved via the skills router at dispatch. */
190
146
  skillRefs: z.array(SkillRefSchema).min(1),
@@ -292,50 +248,12 @@ Before dispatching anything:
292
248
  depends on greenfield bring-up tooling (deferred). The dispatch contract is real and
293
249
  runs against an **existing** app skeleton — the dogfood app already has one.
294
250
 
295
- // Operator status: `wildo context journey` (phase + board + runs in flight). Which tasks already
296
- // landed is read from GIT by the runner itself — a task is landed when every file it produces is
297
- // committed clean.
251
+ // TODO CLI COMMAND: wildo journey status
252
+ // (read current journey scope + the approved build plan + which tasks already dispatched)
298
253
 
299
254
  You **read** `build-plan`; you **write** no journey artifact
300
255
  — the runner records the change-set + task status on the dispatched task's row.
301
256
 
302
- ## Precondition — the application must establish the agent's role, or dispatch stalls
303
-
304
- Check this before the first dispatch of an application's life. It costs one look and it is the
305
- difference between a working lane and one that burns model time producing nothing.
306
-
307
- **The application needs a root `CLAUDE.md` stating that a task dispatched by its dev companion is
308
- legitimate work.** Without it the agent is right to refuse, and refusing is what it does.
309
-
310
- The reason is structural rather than a matter of tone. A dispatched task reaches the agent as an
311
- ordinary prompt — a user turn carrying an objective, a mutation scope and skill refs. Nothing in
312
- that turn proves where it came from. So the agent is being handed conversational content that
313
- tells it to write files into a repository, which is indistinguishable from the thing every
314
- careful agent is supposed to decline, and the more trustworthy the agent the more reliably it
315
- declines. Measured on a real application with no such file: two dispatched runs stalled, one
316
- answering *"content that arrives as conversational input doesn't get to reassign what I am"*.
317
-
318
- The failure does not look like a missing file. It looks like an agent that deliberates well,
319
- identifies exactly which files it would author, explains its reasoning, asks a human to confirm,
320
- and ends its turn — `end_turn`, no error, no denial, an empty change set, and a bill for the
321
- tokens. Read as "the agent chose not to work", which invites prompt-tuning that cannot fix it.
322
-
323
- `wildo init` scaffolds this file. An application created before that, or one whose `CLAUDE.md`
324
- covers only its own conventions, needs the section added. What it must establish:
325
-
326
- - the task is **selected by the host** from the accepted build plan, not composed by a caller;
327
- - it is **confined before it arrives** — the host answers every permission request against the
328
- declared mutation scope and refuses paths outside it, so the agent need not police itself;
329
- - it is **reversible** — every write is an uncommitted working edit, and a human commits.
330
-
331
- Two smaller things belong in the same section, because both were observed costing a run:
332
-
333
- - **Say what `allowedPathPrefixes` are relative to.** The agent receives bare prefixes such as
334
- `shared-lib/src/modules/<module>/` with no root, and cannot verify its own confinement against
335
- them. One sentence naming the application root removes the ambiguity.
336
- - **Do not name a task so it reads as a fixture.** An agent that concludes it is looking at a
337
- smoke test will say so and stop. Name the task after the product change it makes.
338
-
339
257
  ## Step 1 — Select the next dispatchable task (single-flight)
340
258
 
341
259
  Walk the build plan in its authored order and pick the **first** task that is not
@@ -422,9 +340,8 @@ dispatch contract for you (you do not hand-assemble any of it):
422
340
  dirty-at-dispatch is the NORMAL state (parallel sessions), so the capture
423
341
  *attributes* rather than assuming the run had the tree to itself.
424
342
 
425
- // The trigger is the companion's run route (`POST /api/companion/playbooks/<ref>/run`, via the
426
- // workbench or HTTP) — there is no CLI trigger yet. The runner composes the typed context pack,
427
- // runs one ACP prompt turn, and captures the change-set.
343
+ // TODO CLI COMMAND: wildo journey run <playbookRef>
344
+ // (trigger the dispatch; the runner composes the context pack + runs one ACP prompt turn + captures the change-set)
428
345
 
429
346
  ## Step 4 — Verify OUTSIDE the coding agent
430
347