oh-my-customcode 0.48.0 → 0.48.2

package/README.md

@@ -13,7 +13,7 @@
 
 **[한국어 문서 (Korean)](./README_ko.md)**
 
-45 agents. 84 skills. 21 rules. One command.
+45 agents. 85 skills. 21 rules. One command.
 
 ```bash
 npm install -g oh-my-customcode && cd your-project && omcustom init
@@ -138,7 +138,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
 
 ---
 
-### Skills (84)
+### Skills (85)
 
 | Category | Count | Includes |
 |----------|-------|----------|
@@ -226,7 +226,7 @@ Key rules: R010 (orchestrator never writes files), R009 (parallel execution mand
 
 ---
 
-### Guides (28)
+### Guides (29)
 
 Reference documentation covering best practices, architecture decisions, and integration patterns. Located in `guides/` at project root, covering topics from agent design to CI/CD to observability.
 
@@ -272,14 +272,14 @@ your-project/
 ├── CLAUDE.md                   # Entry point
 ├── .claude/
 │   ├── agents/                 # 45 agent definitions
-│   ├── skills/                 # 84 skill modules
+│   ├── skills/                 # 85 skill modules
 │   ├── rules/                  # 21 governance rules (R000-R021)
 │   ├── hooks/                  # 15 lifecycle hook scripts
 │   ├── schemas/                # Tool input validation schemas
 │   ├── specs/                  # Extracted canonical specs
 │   ├── contexts/               # 4 shared context files
 │   └── ontology/               # Knowledge graph for RAG
-└── guides/                     # 28 reference documents
+└── guides/                     # 29 reference documents
 ```
 
 ---

package/dist/cli/index.js

@@ -9323,7 +9323,7 @@ var init_package = __esm(() => {
   package_default = {
     name: "oh-my-customcode",
     workspaces: ["packages/*"],
-    version: "0.48.0",
+    version: "0.48.2",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -1642,7 +1642,7 @@ import { join as join6 } from "node:path";
 var package_default = {
   name: "oh-my-customcode",
   workspaces: ["packages/*"],
-  version: "0.48.0",
+  version: "0.48.2",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "oh-my-customcode",
   "workspaces": ["packages/*"],
-  "version": "0.48.0",
+  "version": "0.48.2",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/skills/deep-verify/SKILL.md

@@ -2,7 +2,7 @@
 name: deep-verify
 description: Multi-angle release quality verification using parallel expert review teams
 scope: core
-version: 1.0.0
+version: 1.1.0
 user-invocable: true
 effort: high
 ---
@@ -28,13 +28,15 @@ If no argument, verifies current branch against its base (usually `develop`).
 - Run test suite, lint, and type check
 - Collect results as baseline
 
-### Round 2: Parallel Expert Review (4 agents)
-Spawn 4 parallel review agents, each with a different focus:
+### Round 2: Parallel Expert Review (6 agents)
+Spawn 6 parallel review agents, each with a different focus:
 
 1. **Correctness Reviewer** — Logic errors, edge cases, off-by-one, null handling
 2. **Security Reviewer** — Injection, auth bypass, data exposure, OWASP top 10
 3. **Performance Reviewer** — O(n^2) loops, unbounded queries, memory leaks, missing indexes
 4. **Integration Reviewer** — API contract breaks, migration safety, cross-module side effects
+5. **Philosophy Reviewer** — Project concept/metaphor alignment, separation of concerns (R006), orchestrator rules (R010), advisory-first enforcement (R021), compilation metaphor integrity
+6. **Regression & Performance Reviewer** — Feature regression risk, API contract preservation, query performance impact, index effectiveness, algorithm complexity at realistic scale
 
 Each agent receives the full diff and returns findings as structured JSON:
 ```json
@@ -67,6 +69,15 @@ Each agent receives the full diff and returns findings as structured JSON:
 - Re-run lint and type check
 - Generate summary report
 
+### Round 7: Philosophy & Regression Gate
+- Verify all changes align with project's compilation metaphor (Skills=source, Agents=artifacts, Rules=spec)
+- Check separation of concerns: no agents containing skill logic, no skills with agent definitions
+- Verify orchestrator rules: no new file writes from orchestrator context
+- Check advisory-first: no new hard-blocking hooks introduced
+- Confirm no feature regressions: existing APIs preserved, test coverage maintained
+- Performance sanity: no O(n^2) on large datasets, no missing indexes for new queries
+- If any CONCERN or VIOLATION found: report for manual review before release
+
 ## Output Format
 
 ```
@@ -80,11 +91,13 @@ Each agent receives the full diff and returns findings as structured JSON:
 ║  Findings:                                           ║
 ║    HIGH:   {n} ({confirmed} confirmed, {fp} FP)      ║
 ║    MEDIUM: {n} ({confirmed} confirmed, {fp} FP)      ║
-║    LOW:    {n}                                        ║
+║    LOW:    {n}                                       ║
 ╠══════════════════════════════════════════════════════╣
 ║  Fixes Applied: {n}                                  ║
 ║  Tests: {pass}/{total} passing                       ║
 ║  Verdict: READY / NEEDS REVIEW / BLOCKED             ║
+║  Philosophy: ALIGNED / {n} CONCERNS                  ║
+║  Regression: CLEAN / {n} RISKS                       ║
 ╚══════════════════════════════════════════════════════╝
 ```
 
@@ -94,3 +107,5 @@ Each agent receives the full diff and returns findings as structured JSON:
 - Round 3 verification agents use `model: opus` for reasoning depth
 - FALSE POSITIVE filtering is critical — previous releases showed 80%+ FP rate on automated review
 - This skill replaces ad-hoc cross-verification with a repeatable process
+- Round 7 philosophy check references CLAUDE.md architecture section and R006/R010/R021 rules
+- Regression check compares function signatures, export lists, and test counts against develop baseline

package/templates/.claude/skills/professor-triage/SKILL.md

@@ -0,0 +1,205 @@
+---
+name: professor-triage
+description: Cross-analyze GitHub issues with omc_issue_analyzer comments, verify against codebase, and perform automated triage
+scope: harness
+version: 1.0.0
+user-invocable: true
+effort: high
+context: fork
+argument-hint: "[issue-numbers...] [--label <label>] [--state <state>] [--since <date>]"
+---
+
+# /professor-triage — Cross-Analysis Issue Triage
+
+## Purpose
+
+Cross-analyzes GitHub issues containing `omc_issue_analyzer` comments (Architect, Colleague, Professor analyses). Verifies claims against the current codebase, produces a cross-analysis report, and performs automated triage actions.
+
+## Usage
+
+```
+/professor-triage                          # Default: --label professor --state open
+/professor-triage 587 589 590 591 592      # Direct issue numbers
+/professor-triage --label codex-release    # Custom label filter
+/professor-triage --since 2026-03-20       # Date filter
+```
+
+## Workflow
+
+### Phase 1: Gather
+
+1. Parse arguments to determine target issues:
+   - If issue numbers provided: use those directly
+   - If `--label` provided: `gh issue list --label <label> --state <state> --json number`
+   - Default: `gh issue list --label professor --state open --json number`
+   - If `--since` provided: add `--search "created:>YYYY-MM-DD"` filter
+
+2. For each issue, fetch full details:
+```bash
+gh issue view NNN --json number,title,body,comments,labels,createdAt
+```
+
+3. For batches >20 issues, prefer `gh api graphql` for batch fetching to respect GitHub API rate limits (5000/hour authenticated).
+
+4. If `--label` returns 0 results, check label existence via `gh label list`. Report if label missing.
+
+### Phase 2: Parse
+
+Extract structured data from omc_issue_analyzer comments by matching these headers:
+
+| Header | Section |
+|--------|---------|
+| `## 🏛️ Senior Architect Analysis` | Architecture impact, code-level analysis, strategy, risk assessment |
+| `## 🤝 Project Colleague Review` | Implementation ideas, blind spots, next steps |
+| `## 🎓 Professor Synthesis` | Verification results, consensus, disagreements, priority matrix, missed perspectives, roadmap |
+
+For each issue, extract:
+- **File paths and line references** mentioned in any analysis (regex: backtick-wrapped paths, `(L\d+)`, `(lines \d+-\d+)`, `:\d+` suffixes)
+- **Priority/size assessments** from Professor synthesis
+- **Recommended actions** from all three analyses
+- **Risk levels** and breaking change assessments
+- **Consensus points** where all 3 analyses agree
+- **Disagreement points** where analyses differ
+
+If an issue has no omc_issue_analyzer comments (no matching headers), skip with warning and include in report as "no analysis available".
+
+### Phase 3: Verify
+
+Verify ALL file paths and line references extracted in Phase 2 against the current codebase.
+
+**Verification levels:**
+
+| Level | Check | Tool |
+|-------|-------|------|
+| Existence | File currently exists | Glob |
+| Content | Referenced line contains expected code | Read |
+| Freshness | Changed since comment was written | `git log --since=<comment_date> -- <file>` |
+
+**Result classification:**
+
+| Status | Meaning | Marker |
+|--------|---------|--------|
+| `verified` | File exists + content matches | ✅ |
+| `stale-still-valid` | File changed but recommendation still applies | ⚠️ |
+| `stale-invalidated` | File changed and recommendation is moot | ⚠️❌ |
+| `missing` | File/path not found | ❌ |
+| `unchecked` | No specific path to verify | ➖ |
+
+**No limits**: All mentioned file paths are verified exhaustively. Quality over token cost.
+
+**Shared verification**: If the same file is mentioned across multiple issues, verify once and share the result.
+
+**Parallelization (R009/R018):**
+- ≤20 unique file references → single Explore agent
+- 21-80 file references → 2-4 parallel Explore agents (R009)
+- 80+ file references or 3+ verification agents needed → Agent Teams per R018
+
+**Delegation**: Delegate verification to Explore agent(s). Orchestrator collects results.
+
+### Phase 4: Cross-Analyze
+
+**R010 note**: This is a read-only analytical step — no file writes. Per R010 exception, the orchestrator may perform this directly. For batches >15 issues, delegate to a dedicated cross-analysis agent with model: opus.
+
+Perform deep cross-analysis with full context from all issues:
+
+1. **Common patterns** — Identify findings that appear across multiple issues (e.g., same file referenced, same recommendation theme)
+2. **Duplicate/merge candidates** — Detect issues tracking the same underlying change:
+   - Same release series (e.g., alpha.3/5/6)
+   - Same upstream dependency
+   - Same affected component
+3. **Conflicting recommendations** — Where analyses disagree across issues, resolve based on:
+   - Codebase verification evidence (Phase 3 results)
+   - Specificity (concrete code-level analysis > abstract strategy)
+   - Recency (newer analyses > older ones)
+4. **Priority matrix** — Unified priority ranking:
+   - P1: Breaking changes, security issues, blocking bugs
+   - P2: Documentation gaps, compatibility updates, medium-risk items
+   - P3: Nice-to-have improvements, future considerations
+5. **Action determination** — Per-issue decision:
+   - `Close (Not Applicable)`: Issue is irrelevant (internal dependency tag, no impact)
+   - `Close (Duplicate of #NNN)`: Superseded by another issue in the batch
+   - `Open — action required`: Real work needed
+   - `Open — monitoring`: Waiting for external trigger (e.g., stable release)
+   - `New issue needed`: Cross-analysis discovered issue not yet tracked
+
+### Phase 5: Output
+
+**5A: Artifact report** — Delegate to arch-documenter to write:
+
+Path: `.claude/outputs/sessions/YYYY-MM-DD/professor-triage-HHmmss.md`
+
+Timestamps use local machine time (consistent with other artifact skills).
+
+Template:
+```
+# Professor Triage Report — YYYY-MM-DD
+
+## Analysis Target
+| # | Title | Labels | Analysis Comments |
+|---|-------|--------|-------------------|
+
+## Per-Issue Summary
+### #NNN — title
+- Core conclusion:
+- Verification status: N✅ N⚠️ N❌
+- Recommended action:
+
+## Cross-Analysis
+### Common Patterns
+### Duplicate/Merge Candidates
+### Conflicting Recommendations Resolution
+### Priority Matrix
+
+## Executed Actions
+| Issue | Action | Status |
+
+## Pending Actions (Confirmation Required)
+```
+
+**5B: Issue comments** — Delegate to mgr-gitnerd to post on each analyzed issue:
+
+```
+## 🔬 Professor Triage — Cross-Analysis Result
+
+**Decision**: {Close (Not Applicable) | Close (Duplicate of #NNN) | Open — action required}
+**Rationale**: {1-2 line summary}
+**Verification**: {N}✅ {N}⚠️ {N}❌
+**Full report**: {artifact path}
+
+---
+_Cross-analyzed by `/professor-triage` with {N} related issues_
+```
+
+### Phase 6: Act
+
+Delegate ALL GitHub operations to mgr-gitnerd.
+
+**Automatic (low-risk, reversible):**
+
+| Condition | Action |
+|-----------|--------|
+| Professor synthesis concludes "Not Applicable" / "no action needed" | `gh issue close --reason "not planned"` |
+| Cross-analysis detects same-series duplicates | Keep latest, close others + `duplicate` label |
+| All analysis complete | Add `verify-done` label |
+| Professor synthesis assigns priority | Add `P1`/`P2`/`P3` label |
+
+**Confirmation required (high-risk):**
+
+Present to user and wait for approval before executing:
+
+| Condition | Action | Reason |
+|-----------|--------|--------|
+| Reopen a closed issue | Propose reopen | Unintended notifications |
+| New issue creation needed | Present draft title/body | Noise prevention |
+| Epic/milestone linking | Propose link | Project structure change |
+| Issue body modification | Present edit draft | Respect original author intent |
+
+**Ensure `verify-done` label exists**: If not, create with `gh label create "verify-done" --color "0E8A16"`.
+
+## Notes
+
+- Phase 2 agents: not needed (orchestrator parses text directly)
+- Phase 3 agents: `Explore` with `model: haiku` for file verification
+- Phase 4: orchestrator directly (read-only, R010 exception)
+- Phase 5: `arch-documenter` for artifact, `mgr-gitnerd` for comments
+- Phase 6: `mgr-gitnerd` for all GitHub ops

package/templates/CLAUDE.md

@@ -139,7 +139,7 @@ project/
 |   +-- rules/                   # 전역 규칙 (R000-R021)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)
-+-- guides/                      # 레퍼런스 문서 (28 토픽)
++-- guides/                      # 레퍼런스 문서 (29 토픽)
 ```
 
 ## 오케스트레이션

package/templates/guides/index.yaml

@@ -34,6 +34,14 @@ guides:
       origin: go.dev
       url: https://go.dev/doc/effective_go
 
+  - name: java21
+    description: Java 21 language reference and modern feature documentation
+    path: ./java21/
+    source:
+      type: external
+      origin: docs.oracle.com
+      url: https://docs.oracle.com/en/java/javase/21/
+
   - name: python
     description: Python reference from PEP 8 and PEP 20
     path: ./python/
@@ -67,6 +75,14 @@ guides:
       url: https://www.typescriptlang.org/docs/handbook/
 
   # Backend
+  - name: django-best-practices
+    description: Django patterns for production-ready Python web applications
+    path: ./django-best-practices/
+    source:
+      type: external
+      origin: djangoproject.com
+      url: https://docs.djangoproject.com/en/6.0/
+
   - name: fastapi
     description: FastAPI framework reference
     path: ./fastapi/
@@ -158,6 +174,14 @@ guides:
       url: https://iceberg.apache.org/docs/latest/
 
   # Database
+  - name: alembic
+    description: Alembic database migration framework for SQLAlchemy
+    path: ./alembic/
+    source:
+      type: external
+      origin: alembic.sqlalchemy.org
+      url: https://alembic.sqlalchemy.org/en/latest/
+
   - name: supabase-postgres
     description: Supabase and PostgreSQL best practices reference
     path: ./supabase-postgres/
@@ -182,6 +206,20 @@ guides:
       origin: redis.io
       url: https://redis.io/docs/
 
+  # Git
+  - name: git-worktree-workflow
+    description: Git worktree workflow for parallel branch development
+    path: ./git-worktree-workflow/
+    source:
+      type: internal
+
+  # Architecture
+  - name: skill-bundle-design
+    description: Domain skill bundle design patterns for Author/Test/Troubleshoot tri-pattern
+    path: ./skill-bundle-design/
+    source:
+      type: internal
+
   # Writing
   - name: elements-of-style
     description: The Elements of Style writing clarity guidelines
@@ -190,3 +228,10 @@ guides:
       type: external
       origin: public-domain
       url: https://www.gutenberg.org/ebooks/37134
+
+  # Web Scraping
+  - name: web-scraping
+    description: BeautifulSoup and Playwright patterns for reliable web scraping and government site parsing
+    path: ./web-scraping/
+    source:
+      type: internal