oh-my-opencode 4.4.0 → 4.5.1

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 (218) hide show
  1. package/.agents/command/get-unpublished-changes.md +148 -0
  2. package/.agents/command/omomomo.md +37 -0
  3. package/.agents/command/publish.md +376 -0
  4. package/.agents/command/remove-deadcode.md +221 -0
  5. package/.agents/command/security-research.md +16 -0
  6. package/.agents/skills/get-unpublished-changes/SKILL.md +24 -0
  7. package/.agents/skills/github-triage/SKILL.md +587 -0
  8. package/.agents/skills/github-triage/scripts/gh_fetch.py +398 -0
  9. package/.agents/skills/hyperplan/SKILL.md +450 -0
  10. package/.agents/skills/omomomo/SKILL.md +36 -0
  11. package/.agents/skills/pre-publish-review/SKILL.md +407 -0
  12. package/.agents/skills/publish/SKILL.md +428 -0
  13. package/.agents/skills/remove-deadcode/SKILL.md +216 -0
  14. package/.agents/skills/security-research/SKILL.md +204 -0
  15. package/.agents/skills/work-with-pr/SKILL.md +360 -0
  16. package/.agents/skills/work-with-pr-workspace/evals/evals.json +76 -0
  17. package/.agents/skills/work-with-pr-workspace/iteration-1/benchmark.json +138 -0
  18. package/.agents/skills/work-with-pr-workspace/iteration-1/benchmark.md +42 -0
  19. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/eval_metadata.json +57 -0
  20. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/grading.json +15 -0
  21. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/outputs/code-changes.md +454 -0
  22. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/outputs/execution-plan.md +136 -0
  23. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/outputs/pr-description.md +47 -0
  24. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/outputs/verification-strategy.md +163 -0
  25. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/timing.json +1 -0
  26. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/grading.json +15 -0
  27. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/outputs/code-changes.md +615 -0
  28. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/outputs/execution-plan.md +99 -0
  29. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/outputs/pr-description.md +50 -0
  30. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/outputs/verification-strategy.md +111 -0
  31. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/timing.json +1 -0
  32. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/eval_metadata.json +37 -0
  33. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/grading.json +11 -0
  34. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/outputs/code-changes.md +205 -0
  35. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/outputs/execution-plan.md +78 -0
  36. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/outputs/pr-description.md +42 -0
  37. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/outputs/verification-strategy.md +87 -0
  38. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/timing.json +1 -0
  39. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/grading.json +11 -0
  40. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/code-changes.md +334 -0
  41. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/execution-plan.md +86 -0
  42. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/pr-description.md +23 -0
  43. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/verification-strategy.md +119 -0
  44. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/timing.json +1 -0
  45. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/eval_metadata.json +32 -0
  46. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/grading.json +10 -0
  47. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/outputs/code-changes.md +221 -0
  48. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/outputs/execution-plan.md +104 -0
  49. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/outputs/pr-description.md +41 -0
  50. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/outputs/verification-strategy.md +84 -0
  51. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/timing.json +1 -0
  52. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/grading.json +10 -0
  53. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/outputs/code-changes.md +342 -0
  54. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/outputs/execution-plan.md +131 -0
  55. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/outputs/pr-description.md +39 -0
  56. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/outputs/verification-strategy.md +128 -0
  57. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/timing.json +1 -0
  58. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/eval_metadata.json +32 -0
  59. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/grading.json +10 -0
  60. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/outputs/code-changes.md +143 -0
  61. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/outputs/execution-plan.md +82 -0
  62. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/outputs/pr-description.md +51 -0
  63. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/outputs/verification-strategy.md +69 -0
  64. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/timing.json +1 -0
  65. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/grading.json +10 -0
  66. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/outputs/code-changes.md +252 -0
  67. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/outputs/execution-plan.md +83 -0
  68. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/outputs/pr-description.md +33 -0
  69. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/outputs/verification-strategy.md +101 -0
  70. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/timing.json +1 -0
  71. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/eval_metadata.json +32 -0
  72. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/grading.json +10 -0
  73. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/outputs/code-changes.md +387 -0
  74. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/outputs/execution-plan.md +112 -0
  75. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/outputs/pr-description.md +51 -0
  76. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/outputs/verification-strategy.md +75 -0
  77. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/timing.json +1 -0
  78. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/grading.json +10 -0
  79. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/outputs/code-changes.md +529 -0
  80. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/outputs/execution-plan.md +127 -0
  81. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/outputs/pr-description.md +42 -0
  82. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/outputs/verification-strategy.md +120 -0
  83. package/.agents/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/timing.json +1 -0
  84. package/.agents/skills/work-with-pr-workspace/iteration-1/review.html +1326 -0
  85. package/.opencode/command/get-unpublished-changes.md +148 -0
  86. package/.opencode/command/omomomo.md +37 -0
  87. package/.opencode/command/publish.md +376 -0
  88. package/.opencode/command/remove-deadcode.md +221 -0
  89. package/.opencode/command/security-research.md +16 -0
  90. package/.opencode/skills/github-triage/SKILL.md +587 -0
  91. package/.opencode/skills/github-triage/scripts/gh_fetch.py +398 -0
  92. package/.opencode/skills/hyperplan/SKILL.md +450 -0
  93. package/.opencode/skills/pre-publish-review/SKILL.md +407 -0
  94. package/.opencode/skills/work-with-pr/SKILL.md +360 -0
  95. package/.opencode/skills/work-with-pr-workspace/evals/evals.json +76 -0
  96. package/.opencode/skills/work-with-pr-workspace/iteration-1/benchmark.json +138 -0
  97. package/.opencode/skills/work-with-pr-workspace/iteration-1/benchmark.md +42 -0
  98. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/eval_metadata.json +57 -0
  99. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/grading.json +15 -0
  100. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/outputs/code-changes.md +454 -0
  101. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/outputs/execution-plan.md +136 -0
  102. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/outputs/pr-description.md +47 -0
  103. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/outputs/verification-strategy.md +163 -0
  104. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/with_skill/timing.json +1 -0
  105. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/grading.json +15 -0
  106. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/outputs/code-changes.md +615 -0
  107. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/outputs/execution-plan.md +99 -0
  108. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/outputs/pr-description.md +50 -0
  109. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/outputs/verification-strategy.md +111 -0
  110. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-1/without_skill/timing.json +1 -0
  111. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/eval_metadata.json +37 -0
  112. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/grading.json +11 -0
  113. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/outputs/code-changes.md +205 -0
  114. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/outputs/execution-plan.md +78 -0
  115. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/outputs/pr-description.md +42 -0
  116. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/outputs/verification-strategy.md +87 -0
  117. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/with_skill/timing.json +1 -0
  118. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/grading.json +11 -0
  119. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/code-changes.md +334 -0
  120. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/execution-plan.md +86 -0
  121. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/pr-description.md +23 -0
  122. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/outputs/verification-strategy.md +119 -0
  123. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-2/without_skill/timing.json +1 -0
  124. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/eval_metadata.json +32 -0
  125. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/grading.json +10 -0
  126. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/outputs/code-changes.md +221 -0
  127. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/outputs/execution-plan.md +104 -0
  128. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/outputs/pr-description.md +41 -0
  129. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/outputs/verification-strategy.md +84 -0
  130. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/with_skill/timing.json +1 -0
  131. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/grading.json +10 -0
  132. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/outputs/code-changes.md +342 -0
  133. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/outputs/execution-plan.md +131 -0
  134. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/outputs/pr-description.md +39 -0
  135. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/outputs/verification-strategy.md +128 -0
  136. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-3/without_skill/timing.json +1 -0
  137. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/eval_metadata.json +32 -0
  138. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/grading.json +10 -0
  139. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/outputs/code-changes.md +143 -0
  140. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/outputs/execution-plan.md +82 -0
  141. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/outputs/pr-description.md +51 -0
  142. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/outputs/verification-strategy.md +69 -0
  143. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/with_skill/timing.json +1 -0
  144. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/grading.json +10 -0
  145. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/outputs/code-changes.md +252 -0
  146. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/outputs/execution-plan.md +83 -0
  147. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/outputs/pr-description.md +33 -0
  148. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/outputs/verification-strategy.md +101 -0
  149. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-4/without_skill/timing.json +1 -0
  150. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/eval_metadata.json +32 -0
  151. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/grading.json +10 -0
  152. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/outputs/code-changes.md +387 -0
  153. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/outputs/execution-plan.md +112 -0
  154. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/outputs/pr-description.md +51 -0
  155. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/outputs/verification-strategy.md +75 -0
  156. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/with_skill/timing.json +1 -0
  157. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/grading.json +10 -0
  158. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/outputs/code-changes.md +529 -0
  159. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/outputs/execution-plan.md +127 -0
  160. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/outputs/pr-description.md +42 -0
  161. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/outputs/verification-strategy.md +120 -0
  162. package/.opencode/skills/work-with-pr-workspace/iteration-1/eval-5/without_skill/timing.json +1 -0
  163. package/.opencode/skills/work-with-pr-workspace/iteration-1/review.html +1326 -0
  164. package/README.ja.md +1 -1
  165. package/README.ko.md +1 -1
  166. package/README.md +1 -1
  167. package/README.ru.md +1 -1
  168. package/README.zh-cn.md +1 -1
  169. package/dist/agents/atlas/agent.d.ts +6 -6
  170. package/dist/agents/prometheus/gemini.d.ts +0 -11
  171. package/dist/agents/prometheus/gpt.d.ts +0 -10
  172. package/dist/agents/prometheus/system-prompt.d.ts +2 -20
  173. package/dist/agents/types.d.ts +1 -16
  174. package/dist/cli/index.js +178 -129
  175. package/dist/config/schema/agent-names.d.ts +3 -3
  176. package/dist/config/schema/agent-overrides.d.ts +208 -208
  177. package/dist/config/schema/categories.d.ts +28 -28
  178. package/dist/config/schema/fallback-models.d.ts +20 -20
  179. package/dist/config/schema/oh-my-opencode-config.d.ts +208 -208
  180. package/dist/features/background-agent/parent-wake-notifier.d.ts +8 -1
  181. package/dist/help/schema/acp.d.ts +95 -0
  182. package/dist/help/schema/doctor.d.ts +147 -0
  183. package/dist/help/schema/sandbox.d.ts +74 -0
  184. package/dist/help/schema/status.d.ts +139 -0
  185. package/dist/hooks/keyword-detector/analyze/default.d.ts +1 -1
  186. package/dist/hooks/keyword-detector/hyperplan/default.d.ts +1 -1
  187. package/dist/hooks/keyword-detector/search/default.d.ts +1 -1
  188. package/dist/hooks/keyword-detector/team/default.d.ts +2 -7
  189. package/dist/hooks/keyword-detector/ultrawork/default.d.ts +1 -9
  190. package/dist/hooks/keyword-detector/ultrawork/gemini.d.ts +1 -16
  191. package/dist/hooks/keyword-detector/ultrawork/gpt.d.ts +1 -10
  192. package/dist/hooks/keyword-detector/ultrawork/planner.d.ts +1 -5
  193. package/dist/hooks/ralph-loop/no-progress-turn-detector.d.ts +7 -0
  194. package/dist/hooks/ralph-loop/pending-verification-handler.d.ts +1 -0
  195. package/dist/hooks/ralph-loop/types.d.ts +1 -0
  196. package/dist/hooks/runtime-fallback/error-classifier.d.ts +1 -0
  197. package/dist/index.js +52205 -50528
  198. package/dist/shared/prompt-async-gate/pending-tool-turn.d.ts +1 -0
  199. package/dist/shared/prompt-async-gate/types.d.ts +4 -3
  200. package/package.json +19 -13
  201. package/dist/agents/atlas/default-prompt-sections.d.ts +0 -6
  202. package/dist/agents/atlas/default.d.ts +0 -2
  203. package/dist/agents/atlas/gemini-prompt-sections.d.ts +0 -6
  204. package/dist/agents/atlas/gemini.d.ts +0 -2
  205. package/dist/agents/atlas/gpt-prompt-sections.d.ts +0 -6
  206. package/dist/agents/atlas/gpt.d.ts +0 -2
  207. package/dist/agents/atlas/kimi-prompt-sections.d.ts +0 -6
  208. package/dist/agents/atlas/kimi.d.ts +0 -2
  209. package/dist/agents/atlas/opus-4-7-prompt-sections.d.ts +0 -6
  210. package/dist/agents/atlas/opus-4-7.d.ts +0 -2
  211. package/dist/agents/atlas/shared-prompt.d.ts +0 -9
  212. package/dist/agents/prometheus/behavioral-summary.d.ts +0 -6
  213. package/dist/agents/prometheus/high-accuracy-mode.d.ts +0 -6
  214. package/dist/agents/prometheus/identity-constraints.d.ts +0 -7
  215. package/dist/agents/prometheus/interview-mode.d.ts +0 -7
  216. package/dist/agents/prometheus/plan-generation.d.ts +0 -7
  217. package/dist/agents/prometheus/plan-template.d.ts +0 -7
  218. package/dist/agents/prometheus/spec-driven-mode.d.ts +0 -7
@@ -0,0 +1,148 @@
1
+ ---
2
+ description: Compare HEAD with the latest published npm version and list all unpublished changes
3
+ ---
4
+
5
+ <command-instruction>
6
+ IMMEDIATELY output the analysis. NO questions. NO preamble.
7
+
8
+ ## CRITICAL: DO NOT just copy commit messages!
9
+
10
+ For each commit, you MUST:
11
+ 1. Read the actual diff to understand WHAT CHANGED
12
+ 2. Describe the REAL change in plain language
13
+ 3. Explain WHY it matters (if not obvious)
14
+
15
+ ## Steps:
16
+ 1. Run `git diff v{published-version}..HEAD` to see actual changes
17
+ 2. Group by type (feat/fix/refactor/docs) with REAL descriptions
18
+ 3. Note breaking changes if any
19
+ 4. Recommend version bump (major/minor/patch)
20
+
21
+ ## Output Format:
22
+ - feat: "Added X that does Y" (not just "add X feature")
23
+ - fix: "Fixed bug where X happened, now Y" (not just "fix X bug")
24
+ - refactor: "Changed X from A to B, now supports C" (not just "rename X")
25
+ </command-instruction>
26
+
27
+ <version-context>
28
+ <published-version>
29
+ !`npm view oh-my-opencode version 2>/dev/null || echo "not published"`
30
+ </published-version>
31
+ <local-version>
32
+ !`node -p "require('./package.json').version" 2>/dev/null || echo "unknown"`
33
+ </local-version>
34
+ <latest-tag>
35
+ !`git tag --sort=-v:refname | head -1 2>/dev/null || echo "no tags"`
36
+ </latest-tag>
37
+ </version-context>
38
+
39
+ <git-context>
40
+ <commits-since-release>
41
+ !`npm view oh-my-opencode version 2>/dev/null | xargs -I{} git log "v{}"..HEAD --oneline 2>/dev/null || echo "no commits since release"`
42
+ </commits-since-release>
43
+ <diff-stat>
44
+ !`npm view oh-my-opencode version 2>/dev/null | xargs -I{} git diff "v{}"..HEAD --stat 2>/dev/null || echo "no diff available"`
45
+ </diff-stat>
46
+ <files-changed-summary>
47
+ !`npm view oh-my-opencode version 2>/dev/null | xargs -I{} git diff "v{}"..HEAD --stat 2>/dev/null | tail -1 || echo ""`
48
+ </files-changed-summary>
49
+ </git-context>
50
+
51
+ <output-format>
52
+ ## Unpublished Changes (v{published} → HEAD)
53
+
54
+ ### feat
55
+ | Scope | What Changed |
56
+ |-------|--------------|
57
+ | X | Description of actual changes |
58
+
59
+ ### fix
60
+ | Scope | What Changed |
61
+ |-------|--------------|
62
+ | X | Description of actual changes |
63
+
64
+ ### refactor
65
+ | Scope | What Changed |
66
+ |-------|--------------|
67
+ | X | Description of actual changes |
68
+
69
+ ### docs
70
+ | Scope | What Changed |
71
+ |-------|--------------|
72
+ | X | Description of actual changes |
73
+
74
+ ### Breaking Changes
75
+ None or list
76
+
77
+ ### Files Changed
78
+ {diff-stat}
79
+
80
+ ### Suggested Version Bump
81
+ - **Recommendation**: patch|minor|major
82
+ - **Reason**: Reason for recommendation
83
+ </output-format>
84
+
85
+ <oracle-safety-review>
86
+ ## Oracle Deployment Safety Review (Only when user explicitly requests)
87
+
88
+ **Trigger keywords**: "safe to deploy", "can I deploy", "is it safe", "review", "check", "oracle"
89
+
90
+ When user includes any of the above keywords in their request:
91
+
92
+ ### 1. Pre-validation
93
+ ```bash
94
+ bun run typecheck
95
+ bun test
96
+ ```
97
+ - On failure → Report "❌ Cannot deploy" immediately without invoking Oracle
98
+
99
+ ### 2. Oracle Invocation Prompt
100
+
101
+ Collect the following information and pass to Oracle:
102
+
103
+ ```
104
+ ## Deployment Safety Review Request
105
+
106
+ ### Changes Summary
107
+ {Changes table analyzed above}
108
+
109
+ ### Key diffs (organized by feature)
110
+ {Core code changes for each feat/fix/refactor - only key parts, not full diff}
111
+
112
+ ### Validation Results
113
+ - Typecheck: ✅/❌
114
+ - Tests: {pass}/{total} (✅/❌)
115
+
116
+ ### Review Items
117
+ 1. **Regression Risk**: Are there changes that could affect existing functionality?
118
+ 2. **Side Effects**: Are there areas where unexpected side effects could occur?
119
+ 3. **Breaking Changes**: Are there changes that affect external users?
120
+ 4. **Edge Cases**: Are there missed edge cases?
121
+ 5. **Deployment Recommendation**: SAFE / CAUTION / UNSAFE
122
+
123
+ ### Request
124
+ Please analyze the above changes deeply and provide your judgment on deployment safety.
125
+ If there are risks, explain with specific scenarios.
126
+ Suggest keywords to monitor after deployment if any.
127
+ ```
128
+
129
+ ### 3. Output Format After Oracle Response
130
+
131
+ ## 🔍 Oracle Deployment Safety Review Result
132
+
133
+ ### Verdict: ✅ SAFE / ⚠️ CAUTION / ❌ UNSAFE
134
+
135
+ ### Risk Analysis
136
+ | Area | Risk Level | Description |
137
+ |------|------------|-------------|
138
+ | ... | 🟢/🟡/🔴 | ... |
139
+
140
+ ### Recommendations
141
+ - ...
142
+
143
+ ### Post-deployment Monitoring Keywords
144
+ - ...
145
+
146
+ ### Conclusion
147
+ {Oracle's final judgment}
148
+ </oracle-safety-review>
@@ -0,0 +1,37 @@
1
+ ---
2
+ description: Easter egg command - about oh-my-opencode
3
+ ---
4
+
5
+ <command-instruction>
6
+ You found an easter egg! 🥚✨
7
+
8
+ Print the following message to the user EXACTLY as written (in a friendly, celebratory tone):
9
+
10
+ ---
11
+
12
+ # 🎉 oMoMoMoMoMo···
13
+
14
+ **You found the easter egg!** 🥚✨
15
+
16
+ ## What is Oh My OpenCode?
17
+
18
+ **Oh My OpenCode** is a powerful OpenCode plugin that transforms your AI agent into a full development team:
19
+
20
+ - 🤖 **Multi-Agent Orchestration**: Oracle (GPT-5.2), Librarian (Claude), Explore (Grok), Frontend Engineer (Gemini), and more
21
+ - 🔧 **LSP Tools**: Full IDE capabilities for your agents - hover, goto definition, find references, rename, code actions
22
+ - 🔍 **AST-Grep**: Structural code search and replace across 25 languages
23
+ - 📚 **Built-in MCPs**: Context7 for docs, Exa for web search, grep.app for GitHub code search
24
+ - 🔄 **Background Agents**: Run multiple agents in parallel like a real dev team
25
+ - 🎯 **Claude Code Compatibility**: Your existing Claude Code config just works
26
+
27
+ ## Who Made This?
28
+
29
+ Created with ❤️ by **[code-yeongyu](https://github.com/code-yeongyu)**
30
+
31
+ 🔗 **GitHub**: https://github.com/code-yeongyu/oh-my-opencode
32
+
33
+ ---
34
+
35
+ *Enjoy coding on steroids!* 🚀
36
+
37
+ </command-instruction>
@@ -0,0 +1,376 @@
1
+ ---
2
+ description: Publish oh-my-opencode to npm via GitHub Actions workflow
3
+ argument-hint: <patch|minor|major>
4
+ ---
5
+
6
+ <command-instruction>
7
+ You are the release manager for oh-my-opencode. Execute the FULL publish workflow from start to finish.
8
+
9
+ ## CRITICAL: ARGUMENT REQUIREMENT
10
+
11
+ **You MUST receive a version bump type from the user.** Valid options:
12
+ - `patch`: Bug fixes, backward-compatible (1.1.7 → 1.1.8)
13
+ - `minor`: New features, backward-compatible (1.1.7 → 1.2.0)
14
+ - `major`: Breaking changes (1.1.7 → 2.0.0)
15
+
16
+ **If the user did not provide a bump type argument, STOP IMMEDIATELY and ask:**
17
+ > "To proceed with deployment, please specify a version bump type: `patch`, `minor`, or `major`"
18
+
19
+ **DO NOT PROCEED without explicit user confirmation of bump type.**
20
+
21
+ ---
22
+
23
+ ## STEP 0: REGISTER TODO LIST (MANDATORY FIRST ACTION)
24
+
25
+ **Before doing ANYTHING else**, create a detailed todo list using TodoWrite:
26
+
27
+ ```
28
+ [
29
+ { "id": "confirm-bump", "content": "Confirm version bump type with user (patch/minor/major)", "status": "in_progress", "priority": "high" },
30
+ { "id": "check-uncommitted", "content": "Check for uncommitted changes and commit if needed", "status": "pending", "priority": "high" },
31
+ { "id": "sync-remote", "content": "Sync with remote (pull --rebase && push if unpushed commits)", "status": "pending", "priority": "high" },
32
+ { "id": "run-workflow", "content": "Trigger GitHub Actions publish workflow", "status": "pending", "priority": "high" },
33
+ { "id": "wait-workflow", "content": "Wait for workflow completion (poll every 30s)", "status": "pending", "priority": "high" },
34
+ { "id": "verify-and-preview", "content": "Verify release created + preview auto-generated changelog & contributor thanks", "status": "pending", "priority": "high" },
35
+ { "id": "draft-summary", "content": "Draft enhanced release summary (mandatory for minor/major, optional for patch — ask user)", "status": "pending", "priority": "high" },
36
+ { "id": "apply-summary", "content": "Prepend enhanced summary to release (if user opted in)", "status": "pending", "priority": "high" },
37
+ { "id": "verify-npm", "content": "Verify npm package published successfully", "status": "pending", "priority": "high" },
38
+ { "id": "wait-platform-workflow", "content": "Wait for publish-platform workflow completion", "status": "pending", "priority": "high" },
39
+ { "id": "verify-platform-binaries", "content": "Verify all 7 platform binary packages published", "status": "pending", "priority": "high" },
40
+ { "id": "final-confirmation", "content": "Final confirmation to user with links", "status": "pending", "priority": "low" }
41
+ ]
42
+ ```
43
+
44
+ **Mark each todo as `in_progress` when starting, `completed` when done. ONE AT A TIME.**
45
+
46
+ ---
47
+
48
+ ## STEP 1: CONFIRM BUMP TYPE
49
+
50
+ If bump type provided as argument, confirm with user:
51
+ > "Version bump type: `{bump}`. Proceed? (y/n)"
52
+
53
+ Wait for user confirmation before proceeding.
54
+
55
+ ---
56
+
57
+ ## STEP 2: CHECK UNCOMMITTED CHANGES
58
+
59
+ Run: `git status --porcelain`
60
+
61
+ - If there are uncommitted changes, warn user and ask if they want to commit first
62
+ - If clean, proceed
63
+
64
+ ---
65
+
66
+ ## STEP 2.5: SYNC WITH REMOTE (MANDATORY)
67
+
68
+ Check if there are unpushed commits:
69
+ ```bash
70
+ git log origin/master..HEAD --oneline
71
+ ```
72
+
73
+ **If there are unpushed commits, you MUST sync before triggering workflow:**
74
+ ```bash
75
+ git pull --rebase && git push
76
+ ```
77
+
78
+ This ensures the GitHub Actions workflow runs on the latest code including all local commits.
79
+
80
+ ---
81
+
82
+ ## STEP 3: TRIGGER GITHUB ACTIONS WORKFLOW
83
+
84
+ Run the publish workflow:
85
+ ```bash
86
+ gh workflow run publish -f bump={bump_type}
87
+ ```
88
+
89
+ Wait 3 seconds, then get the run ID:
90
+ ```bash
91
+ gh run list --workflow=publish --limit=1 --json databaseId,status --jq '.[0]'
92
+ ```
93
+
94
+ ---
95
+
96
+ ## STEP 4: WAIT FOR WORKFLOW COMPLETION
97
+
98
+ Poll workflow status every 30 seconds until completion:
99
+ ```bash
100
+ gh run view {run_id} --json status,conclusion --jq '{status: .status, conclusion: .conclusion}'
101
+ ```
102
+
103
+ Status flow: `queued` → `in_progress` → `completed`
104
+
105
+ **IMPORTANT: Use polling loop, NOT sleep commands.**
106
+
107
+ If conclusion is `failure`, show error and stop:
108
+ ```bash
109
+ gh run view {run_id} --log-failed
110
+ ```
111
+
112
+ ---
113
+
114
+ ## STEP 5: VERIFY RELEASE & PREVIEW AUTO-GENERATED CONTENT
115
+
116
+ Two goals: confirm the release exists, then show the user what the workflow already generated.
117
+
118
+ ```bash
119
+ # Pull latest (workflow committed version bump)
120
+ git pull --rebase
121
+ NEW_VERSION=$(node -p "require('./package.json').version")
122
+
123
+ # Verify release exists on GitHub
124
+ gh release view "v${NEW_VERSION}" --json tagName,url --jq '{tag: .tagName, url: .url}'
125
+ ```
126
+
127
+ **After verifying, generate a local preview of the auto-generated content:**
128
+
129
+ ```bash
130
+ bun run script/generate-changelog.ts
131
+ ```
132
+
133
+ <agent-instruction>
134
+ After running the preview, present the output to the user and say:
135
+
136
+ > **The following content is ALREADY included in the release automatically:**
137
+ > - Commit changelog (grouped by feat/fix/refactor)
138
+ > - Contributor thank-you messages (for non-team contributors)
139
+ >
140
+ > You do NOT need to write any of this. It's handled.
141
+ >
142
+ > **For a patch release**, this is usually sufficient on its own. However, if there are notable bug fixes or changes worth highlighting, an enhanced summary can be added.
143
+ > **For a minor/major release**, an enhanced summary is **required** — I'll draft one in the next step.
144
+
145
+ Wait for the user to acknowledge before proceeding.
146
+ </agent-instruction>
147
+
148
+ ---
149
+
150
+ ## STEP 6: DRAFT ENHANCED RELEASE SUMMARY
151
+
152
+ <decision-gate>
153
+
154
+ | Release Type | Action |
155
+ |-------------|--------|
156
+ | **patch** | ASK the user: "Would you like me to draft an enhanced summary highlighting the key bug fixes / changes? Or is the auto-generated changelog sufficient?" If user declines → skip to Step 8. If user accepts → draft a concise bug-fix / change summary below. |
157
+ | **minor** | MANDATORY. Draft a concise feature summary. Do NOT proceed without one. |
158
+ | **major** | MANDATORY. Draft a full release narrative with migration notes if applicable. Do NOT proceed without one. |
159
+
160
+ </decision-gate>
161
+
162
+ ### What You're Writing (and What You're NOT)
163
+
164
+ You are writing the **headline layer** — a product announcement that sits ABOVE the auto-generated commit log. Think "release blog post", not "git log".
165
+
166
+ <rules>
167
+ - NEVER duplicate commit messages. The auto-generated section already lists every commit.
168
+ - NEVER write generic filler like "Various bug fixes and improvements" or "Several enhancements".
169
+ - ALWAYS focus on USER IMPACT: what can users DO now that they couldn't before?
170
+ - ALWAYS group by THEME or CAPABILITY, not by commit type (feat/fix/refactor).
171
+ - ALWAYS use concrete language: "You can now do X" not "Added X feature".
172
+ </rules>
173
+
174
+ <examples>
175
+ <bad title="Commit regurgitation — DO NOT do this">
176
+ ## What's New
177
+ - feat(auth): add JWT refresh token rotation
178
+ - fix(auth): handle expired token edge case
179
+ - refactor(auth): extract middleware
180
+ </bad>
181
+
182
+ <good title="User-impact narrative — DO this">
183
+ ## 🔐 Smarter Authentication
184
+
185
+ Token refresh is now automatic and seamless. Sessions no longer expire mid-task — the system silently rotates credentials in the background. If you've been frustrated by random logouts, this release fixes that.
186
+ </good>
187
+
188
+ <bad title="Vague filler — DO NOT do this">
189
+ ## Improvements
190
+ - Various performance improvements
191
+ - Bug fixes and stability enhancements
192
+ </bad>
193
+
194
+ <good title="Specific and measurable — DO this">
195
+ ## ⚡ 3x Faster Rule Parsing
196
+
197
+ Rules are now cached by file modification time. If your project has 50+ rule files, you'll notice startup is noticeably faster — we measured a 3x improvement in our test suite.
198
+ </good>
199
+ </examples>
200
+
201
+ ### Drafting Process
202
+
203
+ 1. **Analyze** the commit list from Step 5's preview. Identify 2-5 themes that matter to users.
204
+ 2. **Write** the summary to `/tmp/release-summary-v${NEW_VERSION}.md`.
205
+ 3. **Present** the draft to the user for review and approval before applying.
206
+
207
+ ```bash
208
+ # Write your draft here
209
+ cat > /tmp/release-summary-v${NEW_VERSION}.md << 'SUMMARY_EOF'
210
+ {your_enhanced_summary}
211
+ SUMMARY_EOF
212
+
213
+ cat /tmp/release-summary-v${NEW_VERSION}.md
214
+ ```
215
+
216
+ <agent-instruction>
217
+ After drafting, ask the user:
218
+ > "Here's the release summary I drafted. This will appear AT THE TOP of the release notes, above the auto-generated commit changelog and contributor thanks. Want me to adjust anything before applying?"
219
+
220
+ Do NOT proceed to Step 7 without user confirmation.
221
+ </agent-instruction>
222
+
223
+ ---
224
+
225
+ ## STEP 7: APPLY ENHANCED SUMMARY TO RELEASE
226
+
227
+ **Skip this step ONLY if the user opted out of the enhanced summary in Step 6** — proceed directly to Step 8.
228
+
229
+ <architecture>
230
+ The final release note structure:
231
+
232
+ ```
233
+ ┌─────────────────────────────────────┐
234
+ │ Enhanced Summary (from Step 6) │ ← You wrote this
235
+ │ - Theme-based, user-impact focused │
236
+ ├─────────────────────────────────────┤
237
+ │ --- (separator) │
238
+ ├─────────────────────────────────────┤
239
+ │ Auto-generated Commit Changelog │ ← Workflow wrote this
240
+ │ - feat/fix/refactor grouped │
241
+ │ - Contributor thank-you messages │
242
+ └─────────────────────────────────────┘
243
+ ```
244
+ </architecture>
245
+
246
+ <zero-content-loss-policy>
247
+ - Fetch the existing release body FIRST
248
+ - PREPEND your summary above it
249
+ - The existing auto-generated content must remain 100% INTACT
250
+ - NOT A SINGLE CHARACTER of existing content may be removed or modified
251
+ </zero-content-loss-policy>
252
+
253
+ ```bash
254
+ # 1. Fetch existing auto-generated body
255
+ EXISTING_BODY=$(gh release view "v${NEW_VERSION}" --json body --jq '.body')
256
+
257
+ # 2. Combine: enhanced summary on top, auto-generated below
258
+ {
259
+ cat /tmp/release-summary-v${NEW_VERSION}.md
260
+ echo ""
261
+ echo "---"
262
+ echo ""
263
+ echo "$EXISTING_BODY"
264
+ } > /tmp/final-release-v${NEW_VERSION}.md
265
+
266
+ # 3. Update the release (additive only)
267
+ gh release edit "v${NEW_VERSION}" --notes-file /tmp/final-release-v${NEW_VERSION}.md
268
+
269
+ # 4. Confirm
270
+ echo "✅ Release v${NEW_VERSION} updated with enhanced summary."
271
+ gh release view "v${NEW_VERSION}" --json url --jq '.url'
272
+ ```
273
+
274
+ ---
275
+
276
+ ## STEP 8: VERIFY NPM PUBLICATION
277
+
278
+ Poll npm registry until the new version appears:
279
+ ```bash
280
+ npm view oh-my-opencode version
281
+ ```
282
+
283
+ Compare with expected version. If not matching after 2 minutes, warn user about npm propagation delay.
284
+
285
+ ---
286
+
287
+ ## STEP 8.5: WAIT FOR PLATFORM WORKFLOW COMPLETION
288
+
289
+ The main publish workflow triggers a separate `publish-platform` workflow for platform-specific binaries.
290
+
291
+ 1. Find the publish-platform workflow run triggered by the main workflow:
292
+ ```bash
293
+ gh run list --workflow=publish-platform --limit=1 --json databaseId,status,conclusion --jq '.[0]'
294
+ ```
295
+
296
+ 2. Poll workflow status every 30 seconds until completion:
297
+ ```bash
298
+ gh run view {platform_run_id} --json status,conclusion --jq '{status: .status, conclusion: .conclusion}'
299
+ ```
300
+
301
+ **IMPORTANT: Use polling loop, NOT sleep commands.**
302
+
303
+ If conclusion is `failure`, show error logs:
304
+ ```bash
305
+ gh run view {platform_run_id} --log-failed
306
+ ```
307
+
308
+ ---
309
+
310
+ ## STEP 8.6: VERIFY PLATFORM BINARY PACKAGES
311
+
312
+ After publish-platform workflow completes, verify all 7 platform packages are published:
313
+
314
+ ```bash
315
+ PLATFORMS="darwin-arm64 darwin-x64 linux-x64 linux-arm64 linux-x64-musl linux-arm64-musl windows-x64"
316
+ for PLATFORM in $PLATFORMS; do
317
+ npm view "oh-my-opencode-${PLATFORM}" version
318
+ done
319
+ ```
320
+
321
+ All 7 packages should show the same version as the main package (`${NEW_VERSION}`).
322
+
323
+ **Expected packages:**
324
+ | Package | Description |
325
+ |---------|-------------|
326
+ | `oh-my-opencode-darwin-arm64` | macOS Apple Silicon |
327
+ | `oh-my-opencode-darwin-x64` | macOS Intel |
328
+ | `oh-my-opencode-linux-x64` | Linux x64 (glibc) |
329
+ | `oh-my-opencode-linux-arm64` | Linux ARM64 (glibc) |
330
+ | `oh-my-opencode-linux-x64-musl` | Linux x64 (musl/Alpine) |
331
+ | `oh-my-opencode-linux-arm64-musl` | Linux ARM64 (musl/Alpine) |
332
+ | `oh-my-opencode-windows-x64` | Windows x64 |
333
+
334
+ If any platform package version doesn't match, warn the user and suggest checking the publish-platform workflow logs.
335
+
336
+ ---
337
+
338
+ ## STEP 9: FINAL CONFIRMATION
339
+
340
+ Report success to user with:
341
+ - New version number
342
+ - GitHub release URL: https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v{version}
343
+ - npm package URL: https://www.npmjs.com/package/oh-my-opencode
344
+ - Platform packages status: List all 7 platform packages with their versions
345
+
346
+ ---
347
+
348
+ ## ERROR HANDLING
349
+
350
+ - **Workflow fails**: Show failed logs, suggest checking Actions tab
351
+ - **Release not found**: Wait and retry, may be propagation delay
352
+ - **npm not updated**: npm can take 1-5 minutes to propagate, inform user
353
+ - **Permission denied**: User may need to re-authenticate with `gh auth login`
354
+ - **Platform workflow fails**: Show logs from publish-platform workflow, check which platform failed
355
+ - **Platform package missing**: Some platforms may fail due to cross-compilation issues, suggest re-running publish-platform workflow manually
356
+
357
+ ## LANGUAGE
358
+
359
+ Respond to user in English.
360
+
361
+ </command-instruction>
362
+
363
+ <current-context>
364
+ <published-version>
365
+ !`npm view oh-my-opencode version 2>/dev/null || echo "not published"`
366
+ </published-version>
367
+ <local-version>
368
+ !`node -p "require('./package.json').version" 2>/dev/null || echo "unknown"`
369
+ </local-version>
370
+ <git-status>
371
+ !`git status --porcelain`
372
+ </git-status>
373
+ <recent-commits>
374
+ !`npm view oh-my-opencode version 2>/dev/null | xargs -I{} git log "v{}"..HEAD --oneline 2>/dev/null | head -15 || echo "no commits"`
375
+ </recent-commits>
376
+ </current-context>