oh-my-customcode 1.1.1 → 1.1.3

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 (63) hide show
  1. package/dist/cli/index.js +1 -1
  2. package/dist/index.js +1 -1
  3. package/package.json +1 -1
  4. package/templates/.claude/agents/mgr-gitnerd.md +1 -1
  5. package/templates/.claude/agents/slack-cli-expert.md +1 -1
  6. package/templates/.claude/agents/wiki-curator.md +4 -4
  7. package/templates/.claude/rules/MUST-agent-design.md +7 -2
  8. package/templates/.claude/rules/MUST-agent-teams.md +4 -0
  9. package/templates/.claude/rules/MUST-completion-verification.md +2 -0
  10. package/templates/.claude/rules/MUST-enforcement-policy.md +2 -0
  11. package/templates/.claude/rules/MUST-orchestrator-coordination.md +5 -1
  12. package/templates/.claude/rules/SHOULD-hud-statusline.md +2 -0
  13. package/templates/.claude/rules/SHOULD-verification-ladder.md +14 -0
  14. package/templates/.claude/rules/index.yaml +40 -0
  15. package/templates/.claude/skills/action-validator/SKILL.md +6 -7
  16. package/templates/.claude/skills/adaptive-harness/SKILL.md +6 -7
  17. package/templates/.claude/skills/agent-eval-framework/SKILL.md +4 -5
  18. package/templates/.claude/skills/de-lead-routing/SKILL.md +2 -2
  19. package/templates/.claude/skills/deep-plan/SKILL.md +8 -13
  20. package/templates/.claude/skills/deep-verify/SKILL.md +2 -3
  21. package/templates/.claude/skills/dev-lead-routing/SKILL.md +2 -2
  22. package/templates/.claude/skills/dev-review/SKILL.md +4 -5
  23. package/templates/.claude/skills/docker-best-practices/SKILL.md +0 -2
  24. package/templates/.claude/skills/hada-scout/SKILL.md +1 -1
  25. package/templates/.claude/skills/harness-eval/SKILL.md +3 -7
  26. package/templates/.claude/skills/harness-synthesizer/SKILL.md +3 -7
  27. package/templates/.claude/skills/help/SKILL.md +5 -8
  28. package/templates/.claude/skills/lists/SKILL.md +26 -25
  29. package/templates/.claude/skills/monitoring-setup/SKILL.md +4 -1
  30. package/templates/.claude/skills/post-release-followup/SKILL.md +2 -8
  31. package/templates/.claude/skills/professor-triage/SKILL.md +10 -14
  32. package/templates/.claude/skills/qa-lead-routing/SKILL.md +2 -2
  33. package/templates/.claude/skills/reasoning-sandwich/SKILL.md +9 -9
  34. package/templates/.claude/skills/research/SKILL.md +2 -8
  35. package/templates/.claude/skills/result-aggregation/SKILL.md +2 -8
  36. package/templates/.claude/skills/roundtable-debate/SKILL.md +6 -8
  37. package/templates/.claude/skills/sauron-watch/SKILL.md +1 -1
  38. package/templates/.claude/skills/secretary-routing/SKILL.md +2 -2
  39. package/templates/.claude/skills/skill-extractor/SKILL.md +2 -8
  40. package/templates/.claude/skills/spark-best-practices/SKILL.md +1 -1
  41. package/templates/.claude/skills/status/SKILL.md +11 -16
  42. package/templates/.claude/skills/token-efficiency-audit/SKILL.md +1 -1
  43. package/templates/.claude/skills/wiki/SKILL.md +1 -1
  44. package/templates/.claude/skills/wiki-rag/SKILL.md +1 -1
  45. package/templates/guides/airflow/README.md +8 -8
  46. package/templates/guides/alembic/README.md +1 -1
  47. package/templates/guides/cc-token-saver/README.md +14 -0
  48. package/templates/guides/claude-code/03-tools.md +1 -1
  49. package/templates/guides/claude-code/06-mcp.md +1 -1
  50. package/templates/guides/claude-code/11-sub-agents.md +4 -4
  51. package/templates/guides/claude-code/13-cli-flags.md +1 -0
  52. package/templates/guides/claude-code/15-version-compatibility.md +4 -2
  53. package/templates/guides/claude-code/index.yaml +15 -0
  54. package/templates/guides/claude-code-tracking.md +2 -2
  55. package/templates/guides/deep-plan/phases.md +7 -9
  56. package/templates/guides/external-tools/ecc-absorption-decisions.md +2 -2
  57. package/templates/guides/external-tools/graphify-integration.md +1 -1
  58. package/templates/guides/git-worktree-workflow/README.md +1 -1
  59. package/templates/guides/index.yaml +1 -1
  60. package/templates/guides/multi-model-routing/README.md +7 -2
  61. package/templates/guides/professor-triage/README.md +2 -2
  62. package/templates/guides/professor-triage/phases.md +3 -14
  63. package/templates/manifest.json +1 -1
@@ -126,19 +126,17 @@ Phase 1 research artifact is persisted by the `/research` skill.
126
126
 
127
127
  Phase 3 verification report path: `.claude/outputs/sessions/{YYYY-MM-DD}/deep-plan-{HHmmss}.md`
128
128
 
129
- **Sensitive-path artifact protocol**: Writing artifacts under `.claude/outputs/` MUST use the `/tmp/*.sh` bypass pattern. Direct `Write`/`Edit` and `Bash(mkdir -p)` on `.claude/` all trigger CC sensitive-path guard regardless of bypassPermissions. The `/tmp/*.sh` pattern lets the script internally write to `.claude/` sensitive-path guard inspects only direct tool target paths, not script-internal file ops.
129
+ **Artifact write protocol**: Under `mode: "bypassPermissions"`, write artifacts under `.claude/outputs/` directly with the Write tool (create the dated directory first if needed). Direct `Write`/`Edit`/`Bash` on `.claude/` is permitted since CC v2.1.121 no `/tmp/*.sh` wrapping is needed (R006/R010). Only catastrophic shell operations (`rm -rf /`) remain blocked by independent safety guards.
130
130
 
131
131
  When spawning the final synthesis agent to write this artifact, include these instructions verbatim in the agent prompt:
132
132
 
133
133
  ```
134
- **Sensitive-path artifact protocol (mandatory for this task)**
135
-
136
- Write the artifact under `.claude/outputs/` using the /tmp/*.sh bypass:
137
- 1. Build script in /tmp: cat > /tmp/deep-plan-<timestamp>.sh <<'EOF' ... EOF
138
- 2. Script content: mkdir -p .claude/outputs/sessions/<date>/ && cat > .claude/outputs/sessions/<date>/deep-plan-<HHmmss>.md <<'ARTIFACT' ... ARTIFACT
139
- 3. Execute: bash /tmp/deep-plan-<timestamp>.sh
140
- 4. Cleanup: rm /tmp/deep-plan-<timestamp>.sh
141
- DO NOT use Write/Edit directly on `.claude/outputs/` — CC sensitive-path guard triggers regardless of bypassPermissions/allow rules.
134
+ **Artifact write protocol (mandatory for this task)**
135
+
136
+ Write the artifact under `.claude/outputs/` directly with the Write tool:
137
+ 1. Ensure the dated directory exists: .claude/outputs/sessions/<date>/
138
+ 2. Write .claude/outputs/sessions/<date>/deep-plan-<HHmmss>.md with the Write tool.
139
+ This Agent tool call runs with mode: "bypassPermissions", under which direct Write/Edit/Bash on `.claude/` is permitted (CC v2.1.121+) — no /tmp/*.sh wrapping needed.
142
140
  ```
143
141
 
144
142
  Artifact metadata header:
@@ -206,7 +206,7 @@ R016 부담 없이 80% 이상의 use case를 커버합니다.
206
206
 
207
207
  DEFER 조건 모니터링을 위한 내부 KPI 메모:
208
208
 
209
- > 내부 메모: `.claude/agent-memory/sys-memory-keeper/project_ecc_kpi_internal_metrics.md`
209
+ > 내부 메모: sys-memory-keeper 프로젝트 메모리에 KPI 추적 (예정 — 파일 미생성)
210
210
 
211
211
  | KPI | 6개월 목표 | 1년 목표 |
212
212
  |-----|-----------|---------|
@@ -228,5 +228,5 @@ KPI 초과 달성 시: R016 워크플로우로 재검토 트리거.
228
228
  | sec-agentshield-wrapper | #1174 |
229
229
  | instinct-extractor | #1175 |
230
230
  | manifest-install --profile | #1177 |
231
- | 시퀀싱 메모 | `.claude/agent-memory/sys-memory-keeper/` `[[project-sequencing-alpha-beta-gamma]]` |
231
+ | 시퀀싱 메모 | sys-memory-keeper 프로젝트 메모리 (예정 — 파일 미생성) |
232
232
  | R006 compilation metaphor | `.claude/rules/MUST-agent-design.md` |
@@ -83,6 +83,6 @@ source:
83
83
 
84
84
  - `.claude/skills/wiki/SKILL.md` — 위키 생성/유지 스킬 (Karpathy LLM Wiki 패턴)
85
85
  - `.claude/skills/wiki-rag/SKILL.md` — wiki/index.yaml 기반 RAG 조회 스킬
86
- - `.claude/skills/ontology-rag/SKILL.md` ontology-rag MCP 기반 라우팅 enrichment
86
+ - ontology-rag MCP 서버 (R019 참조) 라우팅 enrichment Layer-1 (`.claude/rules/SHOULD-ontology-rag-routing.md`)
87
87
  - `.claude/rules/SHOULD-ontology-rag-routing.md` — R019 dual-layer enrichment 규칙
88
88
  - 내재화 배경: issue #977
@@ -72,7 +72,7 @@ Claude Code provides `EnterWorktree` and `ExitWorktree` tools for session-scoped
72
72
 
73
73
  ```
74
74
  EnterWorktree(name: "feature-x")
75
- # Creates .claude/worktrees/feature-x with a new branch based on HEAD
75
+ # Creates .claude/worktrees/feature-x with a new branch; base ref governed by the worktree.baseRef setting (fresh = origin/<default-branch>, the default; head = branch from current HEAD, opt-in)
76
76
  # Session working directory switches to the worktree
77
77
 
78
78
  EnterWorktree(path: "/absolute/path/to/existing-worktree")
@@ -55,7 +55,7 @@ guides:
55
55
  source:
56
56
  type: external
57
57
  origin: docs.oracle.com
58
- url: https://docs.oracle.com/en/java/javase/21/
58
+ url: https://docs.oracle.com/en/java/javase/25/
59
59
 
60
60
  - name: python
61
61
  description: Python reference from PEP 8 and PEP 20
@@ -9,11 +9,16 @@ Role-based model selection strategy for AI agent workflows. Consolidates model r
9
9
  | Alias | Full ID | Cost | Speed | Use Case |
10
10
  |-------|---------|------|-------|----------|
11
11
  | `haiku` | claude-haiku-4-5 | $ | Fast | Search, simple edits, file discovery |
12
- | `sonnet` | claude-sonnet-4-6 | $$ | Moderate | Code generation, general tasks (default) |
12
+ | `sonnet` | claude-sonnet-4-6 | $$ | Moderate | Code generation, general tasks (project base alias — pinned to 4-6 for stability) |
13
+ | `sonnet5` | claude-sonnet-5 | $$ | Moderate | CC platform default (v2.1.197+); native 1M context |
13
14
  | `opus` | claude-opus-4-6 | $$$ | Slower | Complex reasoning, architecture, planning |
15
+ | `opus48` | claude-opus-4-8 | $$$ | Slower | Latest Opus (GA); highest capability below Fable 5 |
16
+ | `fable` | claude-fable-5 | $$$$ | Slower | Mythos-class; tier above Opus, highest GA capability |
14
17
  | `opusplan` | claude-opus-4-6 + plan mode | $$$ | Slower | Architecture with approval gates |
15
18
 
16
- Extended context: `[1m]` suffix enables 1M token context (e.g., `claude-opus-4-6[1m]`).
19
+ Extended context: `[1m]` suffix enables 1M token context (e.g., `claude-opus-4-6[1m]`). Fable 5 and Sonnet 5 include 1M context by default — no `[1m]` suffix needed.
20
+
21
+ > **Base alias pin (design intent)**: The base `sonnet` alias stays pinned to `claude-sonnet-4-6` for stability — existing agents specifying `model: sonnet` remain unchanged. Claude Sonnet 5 (`claude-sonnet-5`) is the CC platform default as of v2.1.197 and is opt-in via the explicit `sonnet5` alias.
17
22
 
18
23
  ## Role-Based Routing Table
19
24
 
@@ -37,6 +37,6 @@ The SKILL.md is intentionally thin — it carries only the workflow contract and
37
37
 
38
38
  ## Key Design Decisions
39
39
 
40
- - **Phase 4 uses `general-purpose` (NOT `arch-documenter`)**: `arch-documenter` has `disallowedTools: [Bash]` — cannot execute `/tmp/*.sh` bypass falls back to Write triggers sensitive-path guard. `general-purpose` has Bash access. See #1043.
41
- - **Sensitive-path protocol**: All `.claude/outputs/` writes must use `/tmp/*.sh` bypass. See phases.md Phase 4E.
40
+ - **Phase 4 uses `general-purpose` (NOT `arch-documenter`)**: `arch-documenter` has `disallowedTools: [Bash]` — cannot run `gh` (comment posting) or shell scripts these phases require. `general-purpose` has Bash access. See #1043 and R010 Known Limitations.
41
+ - **Artifact write**: `.claude/outputs/` writes use the Write tool directly under `mode: "bypassPermissions"` — direct Write/Edit/Bash on `.claude/` is permitted since CC v2.1.121 (R006/R010); no `/tmp/*.sh` wrapping needed. See phases.md Phase 4E.
42
42
  - **Parallelization**: Phase 4A + 4B parallel; Phase 4C after both; Phase 4D + 4E parallel; Phase 4F verification gate.
@@ -111,7 +111,7 @@ Generate multi-perspective analysis comments and artifacts for each analyzed iss
111
111
 
112
112
  Phases 4A, 4B, 4C, 4E use `general-purpose` (NOT `arch-documenter`).
113
113
 
114
- `arch-documenter` has `disallowedTools: [Bash]` → cannot execute `/tmp/*.sh` bypass pattern falls back to Write tool triggers CC sensitive-path guard on `.claude/outputs/`. `general-purpose` has Bash access and can use the `/tmp/*.sh` bypass. See #1043.
114
+ `arch-documenter` has `disallowedTools: [Bash]` → cannot run `gh` (GitHub comment posting) or shell scripts that these phases require. `general-purpose` has Bash access and can execute the `gh` calls and artifact writes. See #1043 and R010 "Agent Capability Pre-Check → Known Limitations".
115
115
 
116
116
  ### 4A: Senior Architect Analysis
117
117
 
@@ -229,23 +229,12 @@ _`/professor-triage` v2.3.0에 의해 현재 코드베이스 대비 분석됨
229
229
 
230
230
  Delegate to general-purpose. Path: `.claude/outputs/sessions/YYYY-MM-DD/professor-triage-HHmmss.md`
231
231
 
232
- **Sensitive-path protocol**: Use `/tmp/*.sh` bypass direct Write/Edit/Bash on `.claude/outputs/` triggers CC sensitive-path guard.
233
-
234
- ```bash
235
- cat > /tmp/professor-triage-$(date +%H%M%S).sh << 'ARTIFACT_SCRIPT'
236
- mkdir -p .claude/outputs/sessions/YYYY-MM-DD
237
- cat > .claude/outputs/sessions/YYYY-MM-DD/professor-triage-HHmmss.md << 'ARTIFACT_CONTENT'
238
- {artifact content here}
239
- ARTIFACT_CONTENT
240
- ARTIFACT_SCRIPT
241
- bash /tmp/professor-triage-HHmmss.sh
242
- rm /tmp/professor-triage-HHmmss.sh
243
- ```
232
+ **Artifact write**: Under `mode: "bypassPermissions"`, write the artifact directly with the Write tool (create the dated directory first if needed). Direct Write/Edit/Bash on `.claude/outputs/` is permitted since CC v2.1.121 — no `/tmp/*.sh` wrapping is needed (R006/R010). Only catastrophic shell operations (`rm -rf /`) remain blocked by independent safety guards.
244
233
 
245
234
  Artifact template:
246
235
 
247
236
  ```
248
- # Professor Triage リポート — YYYY-MM-DD
237
+ # Professor Triage 리포트 — YYYY-MM-DD
249
238
 
250
239
  ## 분석 대상
251
240
  | # | 제목 | 라벨 | 생성일 |
@@ -1,5 +1,5 @@
1
1
  {
2
- "version": "1.1.1",
2
+ "version": "1.1.3",
3
3
  "lastUpdated": "2026-07-01T00:00:00.000Z",
4
4
  "omcustomMinClaudeCode": "2.1.121",
5
5
  "omcustomMinClaudeCodeReason": "Sensitive-path direct Write/Edit on .claude/** under bypassPermissions (R010 deprecation, #1101)",