@hybridlabor-api/aos 4.4.0 → 4.4.2-beta.0

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 (306) hide show
  1. package/.agents/skills/firecrawl/SKILL.md +149 -0
  2. package/.agents/skills/firecrawl/rules/install.md +82 -0
  3. package/.agents/skills/firecrawl/rules/security.md +26 -0
  4. package/.agents/skills/firecrawl-agent/SKILL.md +58 -0
  5. package/.agents/skills/firecrawl-build/SKILL.md +39 -0
  6. package/.agents/skills/firecrawl-build-interact/SKILL.md +68 -0
  7. package/.agents/skills/firecrawl-build-onboarding/SKILL.md +103 -0
  8. package/.agents/skills/firecrawl-build-onboarding/references/auth-flow.md +39 -0
  9. package/.agents/skills/firecrawl-build-onboarding/references/project-setup.md +20 -0
  10. package/.agents/skills/firecrawl-build-onboarding/references/sdk-installation.md +17 -0
  11. package/.agents/skills/firecrawl-build-scrape/SKILL.md +69 -0
  12. package/.agents/skills/firecrawl-build-search/SKILL.md +69 -0
  13. package/.agents/skills/firecrawl-crawl/SKILL.md +59 -0
  14. package/.agents/skills/firecrawl-download/SKILL.md +70 -0
  15. package/.agents/skills/firecrawl-interact/SKILL.md +84 -0
  16. package/.agents/skills/firecrawl-map/SKILL.md +51 -0
  17. package/.agents/skills/firecrawl-scrape/SKILL.md +69 -0
  18. package/.agents/skills/firecrawl-search/SKILL.md +60 -0
  19. package/.claude/hooks/memb-inject.mjs +6 -0
  20. package/CLAUDE.md +573 -0
  21. package/README.de.md +0 -8
  22. package/README.md +0 -8
  23. package/README.pt.md +0 -8
  24. package/assets/brand/ao-ant-mark.svg +91 -0
  25. package/assets/brand/bdb-core-mark.svg +34 -0
  26. package/assets/brand/heimdall-guardian-mark.svg +16 -0
  27. package/assets/brand/memb-crystal-mark.svg +18 -0
  28. package/bin/aos-config.mjs +89 -0
  29. package/bin/aos-dashboard.mjs +608 -0
  30. package/bin/aos-uninstall.mjs +227 -0
  31. package/docs/sessions/audit-2026-09-14-silent-failures.md +114 -0
  32. package/docs/skills_table.md +0 -3
  33. package/installer.js +428 -237
  34. package/mcps/RhinoMCP/cc-plugin/.claude/settings.json +10 -0
  35. package/mcps/after-effects-mcp/build/index.js +840 -0
  36. package/mcps/after-effects-mcp/build/scripts/applyEffect.jsx +153 -0
  37. package/mcps/after-effects-mcp/build/scripts/applyEffectTemplate.jsx +218 -0
  38. package/mcps/after-effects-mcp/build/scripts/createComposition.jsx +71 -0
  39. package/mcps/after-effects-mcp/build/scripts/createShapeLayer.jsx +147 -0
  40. package/mcps/after-effects-mcp/build/scripts/createSolidLayer.jsx +114 -0
  41. package/mcps/after-effects-mcp/build/scripts/createTextLayer.jsx +115 -0
  42. package/mcps/after-effects-mcp/build/scripts/getLayerInfo.jsx +192 -0
  43. package/mcps/after-effects-mcp/build/scripts/getProjectInfo.jsx +90 -0
  44. package/mcps/after-effects-mcp/build/scripts/listCompositions.jsx +50 -0
  45. package/mcps/after-effects-mcp/build/scripts/mcp-bridge-auto.jsx +1773 -0
  46. package/mcps/after-effects-mcp/build/scripts/setLayerProperties.jsx +160 -0
  47. package/mcps/computer-use-mcp/dist/client.d.ts +150 -0
  48. package/mcps/computer-use-mcp/dist/client.js +136 -0
  49. package/mcps/computer-use-mcp/dist/entrypoint.d.ts +16 -0
  50. package/mcps/computer-use-mcp/dist/entrypoint.js +26 -0
  51. package/mcps/computer-use-mcp/dist/native.d.ts +212 -0
  52. package/mcps/computer-use-mcp/dist/native.js +50 -0
  53. package/mcps/computer-use-mcp/dist/server.d.ts +32 -0
  54. package/mcps/computer-use-mcp/dist/server.js +342 -0
  55. package/mcps/computer-use-mcp/dist/session.d.ts +101 -0
  56. package/mcps/computer-use-mcp/dist/session.js +2372 -0
  57. package/package.json +13 -4
  58. package/skills/global_config/aos-project-init/SKILL.md +97 -130
  59. package/skills/global_config/aos-project-init/assets/openwikiignore.template +62 -0
  60. package/skills/global_config/aos-project-init/scripts/aos-project-doctor.mjs +38 -1
  61. package/skills/global_config/aos-setup/SKILL.md +110 -11
  62. package/skills/global_config/aos-setup/scripts/aos-doctor.mjs +48 -4
  63. package/skills/global_config/ask-tim/SKILL.md +2 -7
  64. package/skills/global_config/openwiki-skill/scripts/openwiki_daemon.py +65 -12
  65. package/bin/setup-saas.mjs +0 -792
  66. package/mcps/blender-mcp-server/.dockerignore +0 -19
  67. package/mcps/blender-mcp-server/.github/workflows/ci.yml +0 -67
  68. package/mcps/blender-mcp-server/.github/workflows/publish-pypi.yml +0 -54
  69. package/mcps/blender-mcp-server/CHANGELOG.md +0 -64
  70. package/mcps/blender-mcp-server/CONTRIBUTING.md +0 -107
  71. package/mcps/blender-mcp-server/Dockerfile +0 -19
  72. package/mcps/blender-mcp-server/LICENSE +0 -21
  73. package/mcps/blender-mcp-server/README.md +0 -409
  74. package/mcps/blender-mcp-server/addon/__init__.py +0 -1440
  75. package/mcps/blender-mcp-server/addon/models.py +0 -223
  76. package/mcps/blender-mcp-server/pyproject.toml +0 -120
  77. package/mcps/blender-mcp-server/scripts/blender_bridge_request.py +0 -71
  78. package/mcps/blender-mcp-server/scripts/blender_create_test_cube.py +0 -49
  79. package/mcps/blender-mcp-server/scripts/blender_scene_info.py +0 -38
  80. package/mcps/blender-mcp-server/scripts/build_addon_zip.sh +0 -29
  81. package/mcps/blender-mcp-server/scripts/demos/README.md +0 -186
  82. package/mcps/blender-mcp-server/scripts/demos/dam_break_scene.py +0 -276
  83. package/mcps/blender-mcp-server/scripts/demos/open_dam_break_gui.py +0 -33
  84. package/mcps/blender-mcp-server/scripts/demos/pipe_movement_study.py +0 -518
  85. package/mcps/blender-mcp-server/scripts/demos/pipe_pressure_failure_scene.py +0 -806
  86. package/mcps/blender-mcp-server/scripts/demos/procedural_dam_break_scene.py +0 -600
  87. package/mcps/blender-mcp-server/scripts/demos/run_dam_break.py +0 -510
  88. package/mcps/blender-mcp-server/scripts/launch_blender_gui.py +0 -41
  89. package/mcps/blender-mcp-server/scripts/library/README.md +0 -64
  90. package/mcps/blender-mcp-server/scripts/library/apply_transforms.py +0 -46
  91. package/mcps/blender-mcp-server/scripts/library/camera.py +0 -51
  92. package/mcps/blender-mcp-server/scripts/library/collections.py +0 -65
  93. package/mcps/blender-mcp-server/scripts/library/create_mesh.py +0 -41
  94. package/mcps/blender-mcp-server/scripts/library/effector.py +0 -48
  95. package/mcps/blender-mcp-server/scripts/library/fluid_domain.py +0 -80
  96. package/mcps/blender-mcp-server/scripts/library/fluid_inflow.py +0 -98
  97. package/mcps/blender-mcp-server/scripts/library/frame_range.py +0 -35
  98. package/mcps/blender-mcp-server/scripts/library/keyframes.py +0 -59
  99. package/mcps/blender-mcp-server/scripts/library/rigid_body.py +0 -52
  100. package/mcps/blender-mcp-server/scripts/library/save_blend.py +0 -40
  101. package/mcps/blender-mcp-server/scripts/server_start.sh +0 -26
  102. package/mcps/blender-mcp-server/src/blender_mcp_server/__init__.py +0 -3
  103. package/mcps/blender-mcp-server/src/blender_mcp_server/headless.py +0 -330
  104. package/mcps/blender-mcp-server/src/blender_mcp_server/server.py +0 -606
  105. package/mcps/davinci-mcp-professional/.bandit +0 -35
  106. package/mcps/davinci-mcp-professional/.claude/commands/security-review.md +0 -191
  107. package/mcps/davinci-mcp-professional/.claude/settings.json +0 -1
  108. package/mcps/davinci-mcp-professional/.editorconfig +0 -27
  109. package/mcps/davinci-mcp-professional/.gitattributes +0 -207
  110. package/mcps/davinci-mcp-professional/.github/CODEOWNERS +0 -2
  111. package/mcps/davinci-mcp-professional/.github/ISSUE_TEMPLATE/bug_report.md +0 -33
  112. package/mcps/davinci-mcp-professional/.github/ISSUE_TEMPLATE/feature_request.md +0 -19
  113. package/mcps/davinci-mcp-professional/.github/PULL_REQUEST_TEMPLATE.md +0 -20
  114. package/mcps/davinci-mcp-professional/.github/SECURITY.md +0 -97
  115. package/mcps/davinci-mcp-professional/.github/dependabot.yml +0 -27
  116. package/mcps/davinci-mcp-professional/.github/workflows/ci.yml +0 -39
  117. package/mcps/davinci-mcp-professional/ATTRIBUTION.md +0 -4
  118. package/mcps/davinci-mcp-professional/AUTHORS.md +0 -9
  119. package/mcps/davinci-mcp-professional/BUGS.md +0 -55
  120. package/mcps/davinci-mcp-professional/CLAUDE.md +0 -229
  121. package/mcps/davinci-mcp-professional/CONTRIBUTING.md +0 -51
  122. package/mcps/davinci-mcp-professional/COPYING.md +0 -228
  123. package/mcps/davinci-mcp-professional/Doxyfile +0 -379
  124. package/mcps/davinci-mcp-professional/README.md +0 -143
  125. package/mcps/davinci-mcp-professional/SECURITY.md +0 -40
  126. package/mcps/davinci-mcp-professional/USING.md +0 -301
  127. package/mcps/davinci-mcp-professional/VERSION.md +0 -13
  128. package/mcps/davinci-mcp-professional/build.py +0 -169
  129. package/mcps/davinci-mcp-professional/claude_desktop_config_template.json +0 -11
  130. package/mcps/davinci-mcp-professional/hooks/ci-check.sh +0 -29
  131. package/mcps/davinci-mcp-professional/hooks/pre-push +0 -46
  132. package/mcps/davinci-mcp-professional/main.py +0 -40
  133. package/mcps/davinci-mcp-professional/mcp_server.py +0 -30
  134. package/mcps/davinci-mcp-professional/pyproject.toml +0 -115
  135. package/mcps/davinci-mcp-professional/security_audit.py +0 -379
  136. package/mcps/davinci-mcp-professional/src/davinci_mcp/__init__.py +0 -19
  137. package/mcps/davinci-mcp-professional/src/davinci_mcp/cli.py +0 -138
  138. package/mcps/davinci-mcp-professional/src/davinci_mcp/resolve_client.py +0 -342
  139. package/mcps/davinci-mcp-professional/src/davinci_mcp/resources/__init__.py +0 -60
  140. package/mcps/davinci-mcp-professional/src/davinci_mcp/server.py +0 -185
  141. package/mcps/davinci-mcp-professional/src/davinci_mcp/tools/__init__.py +0 -146
  142. package/mcps/davinci-mcp-professional/src/davinci_mcp/types.py +0 -125
  143. package/mcps/davinci-mcp-professional/src/davinci_mcp/utils/__init__.py +0 -19
  144. package/mcps/davinci-mcp-professional/src/davinci_mcp/utils/platform.py +0 -239
  145. package/mcps/davinci-mcp-professional/test.py +0 -186
  146. package/mcps/davinci-mcp-professional/uv.lock +0 -2073
  147. package/mcps/davinci-resolve-mcp/.claude/skills/media-analysis.md +0 -44
  148. package/mcps/davinci-resolve-mcp/.clinerules +0 -17
  149. package/mcps/davinci-resolve-mcp/.cursorrules +0 -17
  150. package/mcps/davinci-resolve-mcp/.github/copilot-instructions.md +0 -17
  151. package/mcps/davinci-resolve-mcp/.github/workflows/npm-publish.yml +0 -109
  152. package/mcps/davinci-resolve-mcp/.windsurfrules +0 -17
  153. package/mcps/davinci-resolve-mcp/AGENTS.md +0 -114
  154. package/mcps/davinci-resolve-mcp/CHANGELOG.md +0 -2648
  155. package/mcps/davinci-resolve-mcp/CLAUDE.md +0 -15
  156. package/mcps/davinci-resolve-mcp/LICENSE +0 -21
  157. package/mcps/davinci-resolve-mcp/README.md +0 -173
  158. package/mcps/davinci-resolve-mcp/SECURITY.md +0 -53
  159. package/mcps/davinci-resolve-mcp/bin/davinci-resolve-mcp.mjs +0 -450
  160. package/mcps/davinci-resolve-mcp/examples/README.md +0 -53
  161. package/mcps/davinci-resolve-mcp/examples/markers/README.md +0 -81
  162. package/mcps/davinci-resolve-mcp/examples/media/README.md +0 -94
  163. package/mcps/davinci-resolve-mcp/examples/timeline/README.md +0 -98
  164. package/mcps/davinci-resolve-mcp/install.py +0 -1687
  165. package/mcps/davinci-resolve-mcp/package.json +0 -52
  166. package/mcps/davinci-resolve-mcp/release-notes/v2.22.0.md +0 -51
  167. package/mcps/davinci-resolve-mcp/release-notes/v2.23.0.md +0 -51
  168. package/mcps/davinci-resolve-mcp/release-notes/v2.23.1.md +0 -35
  169. package/mcps/davinci-resolve-mcp/release-notes/v2.24.1.md +0 -32
  170. package/mcps/davinci-resolve-mcp/scripts/audit_api_parity.py +0 -275
  171. package/mcps/davinci-resolve-mcp/scripts/audit_readwrite_symmetry.py +0 -80
  172. package/mcps/davinci-resolve-mcp/scripts/doctor.py +0 -227
  173. package/mcps/davinci-resolve-mcp/scripts/gen_api_limitations.py +0 -144
  174. package/mcps/davinci-resolve-mcp/scripts/live_media_analysis_polish_probe.py +0 -65
  175. package/mcps/davinci-resolve-mcp/scripts/measure_bridge_cost.py +0 -65
  176. package/mcps/davinci-resolve-mcp/scripts/regen_panel_screenshots.py +0 -76
  177. package/mcps/davinci-resolve-mcp/src/__init__.py +0 -3
  178. package/mcps/davinci-resolve-mcp/src/analysis_dashboard.py +0 -15505
  179. package/mcps/davinci-resolve-mcp/src/batch_cli.py +0 -540
  180. package/mcps/davinci-resolve-mcp/src/control_panel.py +0 -13
  181. package/mcps/davinci-resolve-mcp/src/granular/__init__.py +0 -17
  182. package/mcps/davinci-resolve-mcp/src/granular/common.py +0 -741
  183. package/mcps/davinci-resolve-mcp/src/granular/folder.py +0 -420
  184. package/mcps/davinci-resolve-mcp/src/granular/gallery.py +0 -306
  185. package/mcps/davinci-resolve-mcp/src/granular/graph.py +0 -309
  186. package/mcps/davinci-resolve-mcp/src/granular/media_pool.py +0 -679
  187. package/mcps/davinci-resolve-mcp/src/granular/media_pool_item.py +0 -1020
  188. package/mcps/davinci-resolve-mcp/src/granular/media_storage.py +0 -179
  189. package/mcps/davinci-resolve-mcp/src/granular/project.py +0 -1654
  190. package/mcps/davinci-resolve-mcp/src/granular/resolve_control.py +0 -538
  191. package/mcps/davinci-resolve-mcp/src/granular/timeline.py +0 -1075
  192. package/mcps/davinci-resolve-mcp/src/granular/timeline_item.py +0 -2251
  193. package/mcps/davinci-resolve-mcp/src/resolve_mcp_server.py +0 -43
  194. package/mcps/davinci-resolve-mcp/src/server.py +0 -24116
  195. package/mcps/davinci-resolve-mcp/src/utils/__init__.py +0 -3
  196. package/mcps/davinci-resolve-mcp/src/utils/actor_identity.py +0 -46
  197. package/mcps/davinci-resolve-mcp/src/utils/analysis_caps.py +0 -678
  198. package/mcps/davinci-resolve-mcp/src/utils/analysis_memory.py +0 -755
  199. package/mcps/davinci-resolve-mcp/src/utils/analysis_runs.py +0 -307
  200. package/mcps/davinci-resolve-mcp/src/utils/analysis_store.py +0 -945
  201. package/mcps/davinci-resolve-mcp/src/utils/api_truth.py +0 -525
  202. package/mcps/davinci-resolve-mcp/src/utils/app_control.py +0 -319
  203. package/mcps/davinci-resolve-mcp/src/utils/audio_fairlight_live_probe.py +0 -263
  204. package/mcps/davinci-resolve-mcp/src/utils/brain_edits.py +0 -387
  205. package/mcps/davinci-resolve-mcp/src/utils/bridge_metrics.py +0 -76
  206. package/mcps/davinci-resolve-mcp/src/utils/cdl.py +0 -20
  207. package/mcps/davinci-resolve-mcp/src/utils/clip_query.py +0 -85
  208. package/mcps/davinci-resolve-mcp/src/utils/cloud_operations.py +0 -192
  209. package/mcps/davinci-resolve-mcp/src/utils/color_grade_live_probe.py +0 -444
  210. package/mcps/davinci-resolve-mcp/src/utils/contracts.py +0 -102
  211. package/mcps/davinci-resolve-mcp/src/utils/cut_ir.py +0 -115
  212. package/mcps/davinci-resolve-mcp/src/utils/dctl_templates.py +0 -368
  213. package/mcps/davinci-resolve-mcp/src/utils/deep_vision.py +0 -643
  214. package/mcps/davinci-resolve-mcp/src/utils/destructive_hook.py +0 -606
  215. package/mcps/davinci-resolve-mcp/src/utils/edit_engine.py +0 -737
  216. package/mcps/davinci-resolve-mcp/src/utils/embeddings.py +0 -922
  217. package/mcps/davinci-resolve-mcp/src/utils/entities.py +0 -579
  218. package/mcps/davinci-resolve-mcp/src/utils/extension_authoring_live_probe.py +0 -292
  219. package/mcps/davinci-resolve-mcp/src/utils/failure_tracker.py +0 -119
  220. package/mcps/davinci-resolve-mcp/src/utils/fuse_templates.py +0 -1968
  221. package/mcps/davinci-resolve-mcp/src/utils/fusion_composition_live_probe.py +0 -284
  222. package/mcps/davinci-resolve-mcp/src/utils/fusion_group_settings.py +0 -334
  223. package/mcps/davinci-resolve-mcp/src/utils/layout_presets.py +0 -333
  224. package/mcps/davinci-resolve-mcp/src/utils/mcp_stdio.py +0 -32
  225. package/mcps/davinci-resolve-mcp/src/utils/mcp_transport.py +0 -128
  226. package/mcps/davinci-resolve-mcp/src/utils/media_analysis.py +0 -7690
  227. package/mcps/davinci-resolve-mcp/src/utils/media_analysis_jobs.py +0 -805
  228. package/mcps/davinci-resolve-mcp/src/utils/media_pool_changes.py +0 -121
  229. package/mcps/davinci-resolve-mcp/src/utils/media_pool_ingest_live_probe.py +0 -592
  230. package/mcps/davinci-resolve-mcp/src/utils/multicam.py +0 -393
  231. package/mcps/davinci-resolve-mcp/src/utils/object_inspection.py +0 -301
  232. package/mcps/davinci-resolve-mcp/src/utils/page_lock.py +0 -75
  233. package/mcps/davinci-resolve-mcp/src/utils/platform.py +0 -157
  234. package/mcps/davinci-resolve-mcp/src/utils/proc.py +0 -26
  235. package/mcps/davinci-resolve-mcp/src/utils/project_cleanup.py +0 -73
  236. package/mcps/davinci-resolve-mcp/src/utils/project_lifecycle_live_probe.py +0 -376
  237. package/mcps/davinci-resolve-mcp/src/utils/project_lint.py +0 -131
  238. package/mcps/davinci-resolve-mcp/src/utils/project_properties.py +0 -601
  239. package/mcps/davinci-resolve-mcp/src/utils/project_spec.py +0 -459
  240. package/mcps/davinci-resolve-mcp/src/utils/readback.py +0 -91
  241. package/mcps/davinci-resolve-mcp/src/utils/render_deliver_live_probe.py +0 -384
  242. package/mcps/davinci-resolve-mcp/src/utils/resolve_ai_governance.py +0 -214
  243. package/mcps/davinci-resolve-mcp/src/utils/resolve_ai_ledger.py +0 -244
  244. package/mcps/davinci-resolve-mcp/src/utils/resolve_busy.py +0 -171
  245. package/mcps/davinci-resolve-mcp/src/utils/resolve_connection.py +0 -77
  246. package/mcps/davinci-resolve-mcp/src/utils/review_annotation_live_probe.py +0 -352
  247. package/mcps/davinci-resolve-mcp/src/utils/script_templates.py +0 -1193
  248. package/mcps/davinci-resolve-mcp/src/utils/shot_relationships.py +0 -544
  249. package/mcps/davinci-resolve-mcp/src/utils/structural_diff.py +0 -175
  250. package/mcps/davinci-resolve-mcp/src/utils/sync_detection.py +0 -889
  251. package/mcps/davinci-resolve-mcp/src/utils/timeline_brain_db.py +0 -826
  252. package/mcps/davinci-resolve-mcp/src/utils/timeline_conform_live_probe.py +0 -280
  253. package/mcps/davinci-resolve-mcp/src/utils/timeline_kernel_live_probe.py +0 -1092
  254. package/mcps/davinci-resolve-mcp/src/utils/timeline_kernel_probe.py +0 -185
  255. package/mcps/davinci-resolve-mcp/src/utils/timeline_title_text.py +0 -87
  256. package/mcps/davinci-resolve-mcp/src/utils/timeline_versioning.py +0 -730
  257. package/mcps/davinci-resolve-mcp/src/utils/update_check.py +0 -685
  258. package/mcps/vectorworks-mcp/.dockerignore +0 -8
  259. package/mcps/vectorworks-mcp/Dockerfile +0 -28
  260. package/mcps/vectorworks-mcp/README.md +0 -156
  261. package/mcps/vectorworks-mcp/app/__init__.py +0 -2
  262. package/mcps/vectorworks-mcp/app/api.py +0 -52
  263. package/mcps/vectorworks-mcp/app/chunking.py +0 -56
  264. package/mcps/vectorworks-mcp/app/config.py +0 -29
  265. package/mcps/vectorworks-mcp/app/embeddings.py +0 -28
  266. package/mcps/vectorworks-mcp/app/indexer.py +0 -106
  267. package/mcps/vectorworks-mcp/app/main.py +0 -33
  268. package/mcps/vectorworks-mcp/app/mcp_server.py +0 -71
  269. package/mcps/vectorworks-mcp/app/search.py +0 -54
  270. package/mcps/vectorworks-mcp/app/utils.py +0 -14
  271. package/mcps/vectorworks-mcp/data/.gitkeep +0 -1
  272. package/mcps/vectorworks-mcp/data/vw-app-help/VW2022_PluginScript.htm +0 -95
  273. package/mcps/vectorworks-mcp/data/vw-app-help/VW2022_ScriptEditor.htm +0 -266
  274. package/mcps/vectorworks-mcp/data/vw-app-help/VW2022_Scripting.htm +0 -106
  275. package/mcps/vectorworks-mcp/data/vw-app-help/VW2023_CreatingScriptedPlugins.htm +0 -327
  276. package/mcps/vectorworks-mcp/data/vw-app-help/VW2024_RunningScripts.htm +0 -116
  277. package/mcps/vectorworks-mcp/data/vw-devwiki/VS_Function_Reference_category.html +0 -2129
  278. package/mcps/vectorworks-mcp/data/vw-jp-ref/ObjectsSymbols.html +0 -2035
  279. package/mcps/vectorworks-mcp/data/vw-jp-ref/ScriptFunctionReference.html +0 -29
  280. package/mcps/vectorworks-mcp/design.md +0 -57
  281. package/mcps/vectorworks-mcp/docker-compose.yml +0 -18
  282. package/mcps/vectorworks-mcp/index/.gitkeep +0 -1
  283. package/mcps/vectorworks-mcp/index/meta.jsonl +0 -3956
  284. package/mcps/vectorworks-mcp/index/vw.faiss +0 -0
  285. package/mcps/vectorworks-mcp/requirements.txt +0 -10
  286. package/mcps/vectorworks-mcp/scripts/fetch_docs_minimal.sh +0 -84
  287. package/mcps/vectorworks-mcp/scripts/fetch_github_vectorworks.sh +0 -85
  288. package/mcps/vectorworks-mcp/templates/index.html +0 -40
  289. package/scripts/ecosystem-health-audit.js +0 -257
  290. package/skills/bdb-dev-os-skill/SKILL.md +0 -49
  291. package/skills/bdb-dev-os-skill/package.json +0 -11
  292. package/skills/bdbsaastraining/SKILL.md +0 -316
  293. package/skills/bdbsaastraining/references/exam-pool.md +0 -313
  294. package/skills/bdbsaastraining/references/interaction-modes.md +0 -94
  295. package/skills/bdbsaastraining/references/track-a-ai-agent.md +0 -111
  296. package/skills/bdbsaastraining/references/track-b-wordpress.md +0 -111
  297. package/skills/bdbsaastraining/references/track-c-mailserver.md +0 -107
  298. package/skills/bdbsaastraining/references/track-d-debian.md +0 -109
  299. package/skills/bdbsaastraining/references/track-e-custom.md +0 -83
  300. package/skills/bdbsaastraining/scripts/build_profile.py +0 -529
  301. package/skills/bdbsaastraining/scripts/generate_certificate.py +0 -161
  302. package/skills/bdbsaastraining/scripts/preflight_check.sh +0 -150
  303. package/skills/bdbsaastraining/templates/certificate_template.html +0 -508
  304. package/skills/global_config/bdb-ecosystem-health/SKILL.md +0 -68
  305. package/skills/global_config/bdbsaas-ops/SKILL.md +0 -16
  306. package/skills/global_config/bdbsaashost/SKILL.md +0 -125
package/CLAUDE.md CHANGED
@@ -48,3 +48,576 @@ interactive session. Read `.agents/graph.md` and F-17's addendum in
48
48
  npm run validate # the skill contract, as CI enforces it
49
49
  npm test # selftest + validate
50
50
  ```
51
+
52
+
53
+ # AOS — Antigravity / Gemini
54
+
55
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
56
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
57
+ skill contract and category routing, the pipeline variants, and the delegation
58
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
59
+ rule that will eventually disagree with itself.
60
+
61
+ This file covers only what is specific to running AOS under Antigravity.
62
+
63
+ ## Nothing enforces the gate here — you are the enforcement
64
+
65
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
66
+ harness. Not one of the four release commands is mechanically blocked for you,
67
+ and neither is anything else.
68
+
69
+ So the full rule in AGENTS.md applies here in its entirety, not just its
70
+ hook-enforced subset: when the user asks for a plan, review, audit or
71
+ multi-step action, you are read-only until they answer with the literal **GO**
72
+ — including file writes and `git commit`. On Claude Code a hook would catch the
73
+ four worst cases if discipline failed. Here there is no backstop, which makes
74
+ this the harness where the rule matters most, not least.
75
+
76
+ ## Model routing
77
+
78
+ The tier names in `agy-delegate` map to models that go stale — the built-in
79
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
80
+ `agy models` after every upgrade; the id carries both the version and the
81
+ effort suffix.
82
+
83
+ | Work | Model |
84
+ |---|---|
85
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
86
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
87
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
88
+
89
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
90
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
91
+ source.
92
+
93
+ Adversarial review is the case that most repays the stronger model: a Flash
94
+ tier tends to agree with what it is shown, which is the one thing a reviewer
95
+ must not do.
96
+
97
+ ## Headless timeouts
98
+
99
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
100
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
101
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
102
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
103
+ "broken".
104
+
105
+ # AOS — Antigravity / Gemini
106
+
107
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
108
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
109
+ skill contract and category routing, the pipeline variants, and the delegation
110
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
111
+ rule that will eventually disagree with itself.
112
+
113
+ This file covers only what is specific to running AOS under Antigravity.
114
+
115
+ ## Nothing enforces the gate here — you are the enforcement
116
+
117
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
118
+ harness. Not one of the four release commands is mechanically blocked for you,
119
+ and neither is anything else.
120
+
121
+ So the full rule in AGENTS.md applies here in its entirety, not just its
122
+ hook-enforced subset: when the user asks for a plan, review, audit or
123
+ multi-step action, you are read-only until they answer with the literal **GO**
124
+ — including file writes and `git commit`. On Claude Code a hook would catch the
125
+ four worst cases if discipline failed. Here there is no backstop, which makes
126
+ this the harness where the rule matters most, not least.
127
+
128
+ ## Model routing
129
+
130
+ The tier names in `agy-delegate` map to models that go stale — the built-in
131
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
132
+ `agy models` after every upgrade; the id carries both the version and the
133
+ effort suffix.
134
+
135
+ | Work | Model |
136
+ |---|---|
137
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
138
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
139
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
140
+
141
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
142
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
143
+ source.
144
+
145
+ Adversarial review is the case that most repays the stronger model: a Flash
146
+ tier tends to agree with what it is shown, which is the one thing a reviewer
147
+ must not do.
148
+
149
+ ## Headless timeouts
150
+
151
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
152
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
153
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
154
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
155
+ "broken".
156
+
157
+ # AOS — Antigravity / Gemini
158
+
159
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
160
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
161
+ skill contract and category routing, the pipeline variants, and the delegation
162
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
163
+ rule that will eventually disagree with itself.
164
+
165
+ This file covers only what is specific to running AOS under Antigravity.
166
+
167
+ ## Nothing enforces the gate here — you are the enforcement
168
+
169
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
170
+ harness. Not one of the four release commands is mechanically blocked for you,
171
+ and neither is anything else.
172
+
173
+ So the full rule in AGENTS.md applies here in its entirety, not just its
174
+ hook-enforced subset: when the user asks for a plan, review, audit or
175
+ multi-step action, you are read-only until they answer with the literal **GO**
176
+ — including file writes and `git commit`. On Claude Code a hook would catch the
177
+ four worst cases if discipline failed. Here there is no backstop, which makes
178
+ this the harness where the rule matters most, not least.
179
+
180
+ ## Model routing
181
+
182
+ The tier names in `agy-delegate` map to models that go stale — the built-in
183
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
184
+ `agy models` after every upgrade; the id carries both the version and the
185
+ effort suffix.
186
+
187
+ | Work | Model |
188
+ |---|---|
189
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
190
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
191
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
192
+
193
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
194
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
195
+ source.
196
+
197
+ Adversarial review is the case that most repays the stronger model: a Flash
198
+ tier tends to agree with what it is shown, which is the one thing a reviewer
199
+ must not do.
200
+
201
+ ## Headless timeouts
202
+
203
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
204
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
205
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
206
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
207
+ "broken".
208
+
209
+ # AOS — Antigravity / Gemini
210
+
211
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
212
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
213
+ skill contract and category routing, the pipeline variants, and the delegation
214
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
215
+ rule that will eventually disagree with itself.
216
+
217
+ This file covers only what is specific to running AOS under Antigravity.
218
+
219
+ ## Nothing enforces the gate here — you are the enforcement
220
+
221
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
222
+ harness. Not one of the four release commands is mechanically blocked for you,
223
+ and neither is anything else.
224
+
225
+ So the full rule in AGENTS.md applies here in its entirety, not just its
226
+ hook-enforced subset: when the user asks for a plan, review, audit or
227
+ multi-step action, you are read-only until they answer with the literal **GO**
228
+ — including file writes and `git commit`. On Claude Code a hook would catch the
229
+ four worst cases if discipline failed. Here there is no backstop, which makes
230
+ this the harness where the rule matters most, not least.
231
+
232
+ ## Model routing
233
+
234
+ The tier names in `agy-delegate` map to models that go stale — the built-in
235
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
236
+ `agy models` after every upgrade; the id carries both the version and the
237
+ effort suffix.
238
+
239
+ | Work | Model |
240
+ |---|---|
241
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
242
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
243
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
244
+
245
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
246
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
247
+ source.
248
+
249
+ Adversarial review is the case that most repays the stronger model: a Flash
250
+ tier tends to agree with what it is shown, which is the one thing a reviewer
251
+ must not do.
252
+
253
+ ## Headless timeouts
254
+
255
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
256
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
257
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
258
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
259
+ "broken".
260
+
261
+ # AOS — Antigravity / Gemini
262
+
263
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
264
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
265
+ skill contract and category routing, the pipeline variants, and the delegation
266
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
267
+ rule that will eventually disagree with itself.
268
+
269
+ This file covers only what is specific to running AOS under Antigravity.
270
+
271
+ ## Nothing enforces the gate here — you are the enforcement
272
+
273
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
274
+ harness. Not one of the four release commands is mechanically blocked for you,
275
+ and neither is anything else.
276
+
277
+ So the full rule in AGENTS.md applies here in its entirety, not just its
278
+ hook-enforced subset: when the user asks for a plan, review, audit or
279
+ multi-step action, you are read-only until they answer with the literal **GO**
280
+ — including file writes and `git commit`. On Claude Code a hook would catch the
281
+ four worst cases if discipline failed. Here there is no backstop, which makes
282
+ this the harness where the rule matters most, not least.
283
+
284
+ ## Model routing
285
+
286
+ The tier names in `agy-delegate` map to models that go stale — the built-in
287
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
288
+ `agy models` after every upgrade; the id carries both the version and the
289
+ effort suffix.
290
+
291
+ | Work | Model |
292
+ |---|---|
293
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
294
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
295
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
296
+
297
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
298
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
299
+ source.
300
+
301
+ Adversarial review is the case that most repays the stronger model: a Flash
302
+ tier tends to agree with what it is shown, which is the one thing a reviewer
303
+ must not do.
304
+
305
+ ## Headless timeouts
306
+
307
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
308
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
309
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
310
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
311
+ "broken".
312
+
313
+ # AOS — Antigravity / Gemini
314
+
315
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
316
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
317
+ skill contract and category routing, the pipeline variants, and the delegation
318
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
319
+ rule that will eventually disagree with itself.
320
+
321
+ This file covers only what is specific to running AOS under Antigravity.
322
+
323
+ ## Nothing enforces the gate here — you are the enforcement
324
+
325
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
326
+ harness. Not one of the four release commands is mechanically blocked for you,
327
+ and neither is anything else.
328
+
329
+ So the full rule in AGENTS.md applies here in its entirety, not just its
330
+ hook-enforced subset: when the user asks for a plan, review, audit or
331
+ multi-step action, you are read-only until they answer with the literal **GO**
332
+ — including file writes and `git commit`. On Claude Code a hook would catch the
333
+ four worst cases if discipline failed. Here there is no backstop, which makes
334
+ this the harness where the rule matters most, not least.
335
+
336
+ ## Model routing
337
+
338
+ The tier names in `agy-delegate` map to models that go stale — the built-in
339
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
340
+ `agy models` after every upgrade; the id carries both the version and the
341
+ effort suffix.
342
+
343
+ | Work | Model |
344
+ |---|---|
345
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
346
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
347
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
348
+
349
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
350
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
351
+ source.
352
+
353
+ Adversarial review is the case that most repays the stronger model: a Flash
354
+ tier tends to agree with what it is shown, which is the one thing a reviewer
355
+ must not do.
356
+
357
+ ## Headless timeouts
358
+
359
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
360
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
361
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
362
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
363
+ "broken".
364
+
365
+ # AOS — Antigravity / Gemini
366
+
367
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
368
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
369
+ skill contract and category routing, the pipeline variants, and the delegation
370
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
371
+ rule that will eventually disagree with itself.
372
+
373
+ This file covers only what is specific to running AOS under Antigravity.
374
+
375
+ ## Nothing enforces the gate here — you are the enforcement
376
+
377
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
378
+ harness. Not one of the four release commands is mechanically blocked for you,
379
+ and neither is anything else.
380
+
381
+ So the full rule in AGENTS.md applies here in its entirety, not just its
382
+ hook-enforced subset: when the user asks for a plan, review, audit or
383
+ multi-step action, you are read-only until they answer with the literal **GO**
384
+ — including file writes and `git commit`. On Claude Code a hook would catch the
385
+ four worst cases if discipline failed. Here there is no backstop, which makes
386
+ this the harness where the rule matters most, not least.
387
+
388
+ ## Model routing
389
+
390
+ The tier names in `agy-delegate` map to models that go stale — the built-in
391
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
392
+ `agy models` after every upgrade; the id carries both the version and the
393
+ effort suffix.
394
+
395
+ | Work | Model |
396
+ |---|---|
397
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
398
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
399
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
400
+
401
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
402
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
403
+ source.
404
+
405
+ Adversarial review is the case that most repays the stronger model: a Flash
406
+ tier tends to agree with what it is shown, which is the one thing a reviewer
407
+ must not do.
408
+
409
+ ## Headless timeouts
410
+
411
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
412
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
413
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
414
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
415
+ "broken".
416
+
417
+ # AOS — Antigravity / Gemini
418
+
419
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
420
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
421
+ skill contract and category routing, the pipeline variants, and the delegation
422
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
423
+ rule that will eventually disagree with itself.
424
+
425
+ This file covers only what is specific to running AOS under Antigravity.
426
+
427
+ ## Nothing enforces the gate here — you are the enforcement
428
+
429
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
430
+ harness. Not one of the four release commands is mechanically blocked for you,
431
+ and neither is anything else.
432
+
433
+ So the full rule in AGENTS.md applies here in its entirety, not just its
434
+ hook-enforced subset: when the user asks for a plan, review, audit or
435
+ multi-step action, you are read-only until they answer with the literal **GO**
436
+ — including file writes and `git commit`. On Claude Code a hook would catch the
437
+ four worst cases if discipline failed. Here there is no backstop, which makes
438
+ this the harness where the rule matters most, not least.
439
+
440
+ ## Model routing
441
+
442
+ The tier names in `agy-delegate` map to models that go stale — the built-in
443
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
444
+ `agy models` after every upgrade; the id carries both the version and the
445
+ effort suffix.
446
+
447
+ | Work | Model |
448
+ |---|---|
449
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
450
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
451
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
452
+
453
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
454
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
455
+ source.
456
+
457
+ Adversarial review is the case that most repays the stronger model: a Flash
458
+ tier tends to agree with what it is shown, which is the one thing a reviewer
459
+ must not do.
460
+
461
+ ## Headless timeouts
462
+
463
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
464
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
465
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
466
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
467
+ "broken".
468
+
469
+ # AOS — Antigravity / Gemini
470
+
471
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
472
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
473
+ skill contract and category routing, the pipeline variants, and the delegation
474
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
475
+ rule that will eventually disagree with itself.
476
+
477
+ This file covers only what is specific to running AOS under Antigravity.
478
+
479
+ ## Nothing enforces the gate here — you are the enforcement
480
+
481
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
482
+ harness. Not one of the four release commands is mechanically blocked for you,
483
+ and neither is anything else.
484
+
485
+ So the full rule in AGENTS.md applies here in its entirety, not just its
486
+ hook-enforced subset: when the user asks for a plan, review, audit or
487
+ multi-step action, you are read-only until they answer with the literal **GO**
488
+ — including file writes and `git commit`. On Claude Code a hook would catch the
489
+ four worst cases if discipline failed. Here there is no backstop, which makes
490
+ this the harness where the rule matters most, not least.
491
+
492
+ ## Model routing
493
+
494
+ The tier names in `agy-delegate` map to models that go stale — the built-in
495
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
496
+ `agy models` after every upgrade; the id carries both the version and the
497
+ effort suffix.
498
+
499
+ | Work | Model |
500
+ |---|---|
501
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
502
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
503
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
504
+
505
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
506
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
507
+ source.
508
+
509
+ Adversarial review is the case that most repays the stronger model: a Flash
510
+ tier tends to agree with what it is shown, which is the one thing a reviewer
511
+ must not do.
512
+
513
+ ## Headless timeouts
514
+
515
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
516
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
517
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
518
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
519
+ "broken".
520
+
521
+ # AOS — Antigravity / Gemini
522
+
523
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
524
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
525
+ skill contract and category routing, the pipeline variants, and the delegation
526
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
527
+ rule that will eventually disagree with itself.
528
+
529
+ This file covers only what is specific to running AOS under Antigravity.
530
+
531
+ ## Nothing enforces the gate here — you are the enforcement
532
+
533
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
534
+ harness. Not one of the four release commands is mechanically blocked for you,
535
+ and neither is anything else.
536
+
537
+ So the full rule in AGENTS.md applies here in its entirety, not just its
538
+ hook-enforced subset: when the user asks for a plan, review, audit or
539
+ multi-step action, you are read-only until they answer with the literal **GO**
540
+ — including file writes and `git commit`. On Claude Code a hook would catch the
541
+ four worst cases if discipline failed. Here there is no backstop, which makes
542
+ this the harness where the rule matters most, not least.
543
+
544
+ ## Model routing
545
+
546
+ The tier names in `agy-delegate` map to models that go stale — the built-in
547
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
548
+ `agy models` after every upgrade; the id carries both the version and the
549
+ effort suffix.
550
+
551
+ | Work | Model |
552
+ |---|---|
553
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
554
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
555
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
556
+
557
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
558
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
559
+ source.
560
+
561
+ Adversarial review is the case that most repays the stronger model: a Flash
562
+ tier tends to agree with what it is shown, which is the one thing a reviewer
563
+ must not do.
564
+
565
+ ## Headless timeouts
566
+
567
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
568
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
569
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
570
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
571
+ "broken".
572
+
573
+ # AOS — Antigravity / Gemini
574
+
575
+ **Read [AGENTS.md](AGENTS.md) first.** It holds every rule that applies to all
576
+ harnesses: the non-negotiables, the release gate, Conventional Commits, the
577
+ skill contract and category routing, the pipeline variants, and the delegation
578
+ policy. Nothing from it is repeated here — a rule that lives in two files is a
579
+ rule that will eventually disagree with itself.
580
+
581
+ This file covers only what is specific to running AOS under Antigravity.
582
+
583
+ ## Nothing enforces the gate here — you are the enforcement
584
+
585
+ `.claude/hooks/go-gate.mjs` is a Claude Code hook and does not run on this
586
+ harness. Not one of the four release commands is mechanically blocked for you,
587
+ and neither is anything else.
588
+
589
+ So the full rule in AGENTS.md applies here in its entirety, not just its
590
+ hook-enforced subset: when the user asks for a plan, review, audit or
591
+ multi-step action, you are read-only until they answer with the literal **GO**
592
+ — including file writes and `git commit`. On Claude Code a hook would catch the
593
+ four worst cases if discipline failed. Here there is no backstop, which makes
594
+ this the harness where the rule matters most, not least.
595
+
596
+ ## Model routing
597
+
598
+ The tier names in `agy-delegate` map to models that go stale — the built-in
599
+ `flash` still points at Gemini 3.7 while 3.8 ships. Re-check against
600
+ `agy models` after every upgrade; the id carries both the version and the
601
+ effort suffix.
602
+
603
+ | Work | Model |
604
+ |---|---|
605
+ | Media, fast or mechanical coding, boilerplate | `Gemini 3.8 Flash (Medium)` |
606
+ | Trivial one-liners | `Gemini 3.8 Flash (Low)` |
607
+ | Review, architecture, hard reasoning | `Claude Sonnet 4.6 (Thinking)` |
608
+
609
+ Set these once via `CLAUDE_PLUGIN_OPTION_TIER_{FLASH,FLASH_LO,PRO}` in
610
+ `~/.zshenv` — **not** `~/.zshrc`, which non-interactive tool shells never
611
+ source.
612
+
613
+ Adversarial review is the case that most repays the stronger model: a Flash
614
+ tier tends to agree with what it is shown, which is the one thing a reviewer
615
+ must not do.
616
+
617
+ ## Headless timeouts
618
+
619
+ A trivial headless `agy` prompt was measured at **605s** in 2026-09.
620
+ `agy-delegate` defaults to `--print-timeout 5m`, so it aborts at 300s and
621
+ reports an empty body while the answer is still arriving. Pass `--timeout 15m`
622
+ for anything non-trivial. A short timeout does not read as "slow", it reads as
623
+ "broken".
package/README.de.md CHANGED
@@ -867,14 +867,6 @@ Fügen Sie nur den Dispatcher-Contract (`.agents/`, die Gate-Hooks, den `/startc
867
867
  npx -y @hybridlabor-api/aos --project-harness
868
868
  ```
869
869
 
870
- ### SaaS Workstation Bootstrapper
871
-
872
- Für die BDB Multi-Cloud Fleet: 2FA-Browser-Handshake, Step-CA-Zertifikat-Bootstrap, SSH-Konfig und FastMCP-Gateway-Injektion in jeden erkannten Editor:
873
-
874
- ```bash
875
- npx -y @hybridlabor-api/aos setup-saas
876
- ```
877
-
878
870
  ### Aus dem Quellcode (Contributing)
879
871
 
880
872
  ```bash
package/README.md CHANGED
@@ -915,14 +915,6 @@ Drop just the dispatcher contract (`.agents/`, the gate hooks, the `/startcycle-
915
915
  npx -y @hybridlabor-api/aos --project-harness
916
916
  ```
917
917
 
918
- ### SaaS Workstation Bootstrapper
919
-
920
- For the BDB Multi-Cloud Fleet: 2FA browser handshake, Step-CA certificate bootstrap, SSH config, and FastMCP gateway injection into every detected editor:
921
-
922
- ```bash
923
- npx -y @hybridlabor-api/aos setup-saas
924
- ```
925
-
926
918
  ### From Source (Contributing)
927
919
 
928
920
  ```bash
package/README.pt.md CHANGED
@@ -800,14 +800,6 @@ Adicione apenas o contrato do dispatcher (`.agents/`, os hooks de portão, o flu
800
800
  npx -y @hybridlabor-api/aos --project-harness
801
801
  ```
802
802
 
803
- ### SaaS Workstation Bootstrapper
804
-
805
- Para a Frota Multi-Cloud da BDB: Handshake 2FA no navegador, bootstrap de certificado Step-CA, configuração SSH e injeção do gateway FastMCP em todos os editores detectados:
806
-
807
- ```bash
808
- npx -y @hybridlabor-api/aos setup-saas
809
- ```
810
-
811
803
  ### A Partir da Fonte (Contribuindo)
812
804
 
813
805
  ```bash