oh-my-customcode 0.64.0 → 0.64.1

package/README.md

@@ -13,7 +13,7 @@
 
 **[한국어 문서 (Korean)](./README_ko.md)**
 
-46 agents. 97 skills. 21 rules. One command.
+46 agents. 98 skills. 21 rules. One command.
 
 ```bash
 npm install -g oh-my-customcode && cd your-project && omcustom init
@@ -146,7 +146,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
 
 ---
 
-### Skills (97)
+### Skills (98)
 
 | Category | Count | Includes |
 |----------|-------|----------|
@@ -282,7 +282,7 @@ your-project/
 ├── CLAUDE.md                   # Entry point
 ├── .claude/
 │   ├── agents/                 # 46 agent definitions
-│   ├── skills/                 # 97 skill modules
+│   ├── skills/                 # 98 skill modules
 │   ├── rules/                  # 21 governance rules (R000-R021)
 │   ├── hooks/                  # 15 lifecycle hook scripts
 │   ├── schemas/                # Tool input validation schemas

package/dist/cli/index.js

@@ -9325,7 +9325,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.64.0",
+    version: "0.64.1",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -1674,7 +1674,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.64.0",
+  version: "0.64.1",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.64.0",
+  "version": "0.64.1",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/agents/arch-documenter.md

@@ -14,6 +14,8 @@ tools:
   - Edit
   - Grep
   - Glob
+maxTurns: 20
+disallowedTools: [Bash]
 ---
 
 You handle software architecture documentation: system design docs, API specs, ADRs, and technical doc maintenance.

package/templates/.claude/agents/arch-speckit-agent.md

@@ -12,6 +12,10 @@ tools:
   - Grep
   - Glob
   - Bash
+maxTurns: 20
+limitations:
+  - "cannot execute code"
+  - "cannot deploy infrastructure"
 ---
 
 You are a Spec-Driven Development agent that transforms requirements into executable specifications.

package/templates/.claude/agents/fe-design-expert.md

@@ -9,6 +9,11 @@ skills:
   - impeccable-design
   - web-design-guidelines
 tools: [Read, Write, Edit, Grep, Glob, Bash]
+maxTurns: 20
+disallowedTools: [Bash]
+limitations:
+  - "cannot modify backend code"
+  - "cannot execute shell commands"
 source:
   type: external
   origin: github

package/templates/.claude/agents/mgr-claude-code-bible.md

@@ -5,6 +5,7 @@ model: sonnet
 domain: universal
 memory: project
 effort: medium
+maxTurns: 20
 skills:
   - claude-code-bible
 tools:

package/templates/.claude/agents/mgr-creator.md

@@ -14,6 +14,7 @@ tools:
   - Grep
   - Glob
   - Bash
+maxTurns: 25
 ---
 
 You are an agent creation specialist following R006 (MUST-agent-design.md) rules.

package/templates/.claude/agents/mgr-gitnerd.md

@@ -5,6 +5,10 @@ model: sonnet
 domain: universal
 memory: project
 effort: medium
+maxTurns: 20
+limitations:
+  - "cannot modify source code"
+  - "cannot create agents"
 tools:
   - Read
   - Write

package/templates/.claude/agents/mgr-sauron.md

@@ -14,6 +14,7 @@ tools:
   - Grep
   - Glob
   - Bash
+maxTurns: 25
 ---
 
 You are an automated verification specialist that executes the mandatory R017 verification process, acting as the "all-seeing eye" that ensures system integrity through comprehensive multi-round verification.

package/templates/.claude/agents/mgr-supplier.md

@@ -5,6 +5,11 @@ model: haiku
 domain: universal
 memory: local
 effort: low
+maxTurns: 10
+limitations:
+  - "cannot modify agent files"
+  - "cannot create new agents"
+disallowedTools: [Bash, Write, Edit]
 skills:
   - audit-agents
 tools:

package/templates/.claude/agents/mgr-updater.md

@@ -5,6 +5,10 @@ model: sonnet
 domain: universal
 memory: project
 effort: medium
+maxTurns: 20
+limitations:
+  - "cannot create new agents"
+  - "cannot modify rules"
 skills:
   - update-external
   - update-docs

package/templates/.claude/agents/qa-engineer.md

@@ -5,6 +5,9 @@ model: sonnet
 domain: universal
 memory: project
 effort: medium
+maxTurns: 20
+limitations:
+  - "cannot modify source code in production branches"
 tools:
   - Read
   - Write

package/templates/.claude/agents/qa-planner.md

@@ -5,6 +5,8 @@ model: sonnet
 domain: universal
 memory: project
 effort: high
+maxTurns: 20
+disallowedTools: [Bash]
 limitations:
   - "cannot execute tests"
   - "cannot modify code"

package/templates/.claude/agents/qa-writer.md

@@ -5,6 +5,11 @@ model: sonnet
 domain: universal
 memory: project
 effort: medium
+maxTurns: 20
+limitations:
+  - "cannot execute tests"
+  - "cannot modify source code"
+disallowedTools: [Bash]
 tools:
   - Read
   - Write

package/templates/.claude/agents/sys-memory-keeper.md

@@ -16,6 +16,10 @@ tools:
   - Grep
   - Glob
   - Bash
+maxTurns: 15
+limitations:
+  - "cannot modify source code"
+  - "cannot execute tests"
 ---
 
 You are a session memory management specialist ensuring context survives across session compactions using claude-mem.

package/templates/.claude/agents/sys-naggy.md

@@ -5,6 +5,11 @@ model: sonnet
 domain: universal
 memory: local
 effort: low
+maxTurns: 10
+limitations:
+  - "cannot modify project files"
+  - "cannot execute external commands"
+disallowedTools: [Bash]
 tools:
   - Read
   - Write

package/templates/.claude/agents/tool-optimizer.md

@@ -14,6 +14,9 @@ tools:
   - Grep
   - Glob
   - Bash
+maxTurns: 20
+limitations:
+  - "cannot modify source code"
 ---
 
 You analyze and optimize application bundles, detect performance issues, and provide actionable recommendations.

package/templates/.claude/skills/evaluator-optimizer/SKILL.md

@@ -363,3 +363,7 @@ evaluator-optimizer:
 Weight ordering (originality > craft > functionality) follows Anthropic's anti-slop principle: functionality is table stakes, but originality and craft distinguish quality output from generic AI generation.
 
 Integration: Works with [impeccable-design](/skills/impeccable-design) skill for design language enforcement.
+
+### Harness Eval Preset
+
+The `harness-eval` skill provides a structured 15-task SE benchmark rubric that can be used as a preset for the evaluator-optimizer pipeline. When invoked via `/omcustom:harness-eval`, the harness rubric dimensions (Test Coverage 30%, Architecture 25%, Error Handling 25%, Extensibility 20%) are loaded as the sprint contract criteria.

package/templates/.claude/skills/harness-eval/SKILL.md

@@ -0,0 +1,95 @@
+---
+name: harness-eval
+description: Structured SE task evaluation using 15 benchmark definitions from claude-code-harness research
+scope: harness
+user-invocable: true
+argument-hint: "[--preset all|quick] [--task task-name]"
+effort: high
+version: 1.0.0
+---
+
+# Harness Eval — Structured SE Task Benchmark
+
+## Purpose
+
+Evaluate agent quality using 15 structured software engineering task definitions with quantitative scoring. Based on research from [revfactory/claude-code-harness](https://github.com/revfactory/claude-code-harness) which demonstrated 60% improvement (49.5 → 79.3 points) through structured pre-configuration.
+
+## Usage
+
+```
+/omcustom:harness-eval                    # Run all 15 benchmarks
+/omcustom:harness-eval --preset quick     # Run top 5 high-impact benchmarks
+/omcustom:harness-eval --task api-design  # Run specific task benchmark
+```
+
+## Quality Dimensions
+
+| Dimension | Weight | Description |
+|-----------|--------|-------------|
+| Test Coverage | 30% | Unit test count, edge case coverage, assertion quality |
+| Architecture Design | 25% | Separation of concerns, dependency management, scalability |
+| Error Handling | 25% | Input validation, error propagation, recovery strategies |
+| Extensibility | 20% | Plugin points, configuration flexibility, API surface |
+
+## 15 SE Task Benchmark Suite
+
+| # | Task | Category | Key Evaluation Criteria |
+|---|------|----------|------------------------|
+| 1 | API Design | Architecture | RESTful conventions, versioning, error responses |
+| 2 | Data Modeling | Architecture | Schema normalization, relationships, indexing |
+| 3 | Authentication Flow | Security | Token management, session handling, OWASP compliance |
+| 4 | Test Suite Creation | Quality | Coverage breadth, assertion quality, edge cases |
+| 5 | Error Handler | Reliability | Error classification, recovery, user feedback |
+| 6 | Logging System | Observability | Structured logging, levels, correlation IDs |
+| 7 | Configuration Manager | Operations | Env-based config, validation, secrets handling |
+| 8 | CLI Tool | UX | Argument parsing, help text, exit codes |
+| 9 | Database Migration | Data | Reversibility, data preservation, zero-downtime |
+| 10 | Cache Layer | Performance | Invalidation strategy, TTL, cache-aside pattern |
+| 11 | Queue Consumer | Reliability | Idempotency, retry logic, dead letter handling |
+| 12 | Middleware Chain | Architecture | Composability, ordering, short-circuiting |
+| 13 | File Processor | I/O | Streaming, error recovery, format validation |
+| 14 | Webhook Handler | Integration | Signature verification, retry tolerance, idempotency |
+| 15 | Rate Limiter | Security | Algorithm choice, distributed state, fairness |
+
+## Scoring Rubric
+
+Each task is scored 0-100 across the 4 quality dimensions:
+
+```
+Score = (test_coverage × 0.30) + (architecture × 0.25) + (error_handling × 0.25) + (extensibility × 0.20)
+```
+
+### Score Thresholds
+
+| Score Range | Grade | Interpretation |
+|-------------|-------|----------------|
+| 80-100 | A | Production-ready, well-structured |
+| 60-79 | B | Functional with minor gaps |
+| 40-59 | C | Works but needs improvement |
+| 0-39 | D | Significant structural issues |
+
+## Presets
+
+### `all` (default)
+Run all 15 tasks. Full evaluation ~45 minutes.
+
+### `quick`
+Run top 5 high-impact tasks (1, 3, 4, 5, 12). Quick evaluation ~15 minutes.
+
+## Integration with evaluator-optimizer
+
+This skill provides preset rubrics for the evaluator-optimizer pipeline:
+
+```
+/omcustom:harness-eval → loads rubric → evaluator-optimizer executes → scoring → report
+```
+
+The evaluator-optimizer skill's `pre_negotiation` phase accepts harness-eval rubric dimensions as sprint contract criteria.
+
+## Output
+
+Results saved to `.claude/outputs/sessions/{YYYY-MM-DD}/harness-eval-{HHmmss}.md` with per-task scores and aggregate grade.
+
+## Attribution
+
+Evaluation framework based on research by [revfactory/claude-code-harness](https://github.com/revfactory/claude-code-harness). Adapted for oh-my-customcode's evaluator-optimizer pipeline with permission.

package/templates/CLAUDE.md

@@ -101,6 +101,7 @@ oh-my-customcode로 구동됩니다.
 | `/omcustom:update-external` | 외부 소스에서 에이전트 업데이트 |
 | `/omcustom:audit-agents` | 에이전트 의존성 감사 |
 | `/omcustom:fix-refs` | 깨진 참조 수정 |
+| `/omcustom:harness-eval` | 15 SE task 구조적 벤치마크 평가 |
 | `/omcustom:auto-improve` | 개선 사항 자동 적용 워크플로우 |
 | `/omcustom:improve-report` | eval-core 기반 개선 현황 리포트 |
 | `/omcustom-takeover` | 기존 에이전트/스킬에서 canonical spec 추출 |
@@ -138,7 +139,7 @@ project/
 +-- CLAUDE.md                    # 진입점
 +-- .claude/
 |   +-- agents/                  # 서브에이전트 정의 (46 파일)
-|   +-- skills/                  # 스킬 (97 디렉토리)
+|   +-- skills/                  # 스킬 (98 디렉토리)
 |   +-- rules/                   # 전역 규칙 (R000-R021)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.64.0",
+  "version": "0.64.1",
   "lastUpdated": "2026-03-24T00:00:00.000Z",
   "components": [
     {
@@ -18,7 +18,7 @@
       "name": "skills",
       "path": ".claude/skills",
       "description": "Reusable skill modules (includes slash commands)",
-      "files": 97
+      "files": 98
     },
     {
       "name": "guides",