oh-my-customcode 0.75.0 → 0.76.1

package/README.md

@@ -13,7 +13,7 @@
 
 **[한국어 문서 (Korean)](./README_ko.md)**
 
-46 agents. 100 skills. 21 rules. One command.
+46 agents. 101 skills. 21 rules. One command.
 
 ```bash
 npm install -g oh-my-customcode && cd your-project && omcustom init
@@ -145,7 +145,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
 
 ---
 
-### Skills (100)
+### Skills (101)
 
 | Category | Count | Includes |
 |----------|-------|----------|
@@ -285,7 +285,7 @@ your-project/
 ├── CLAUDE.md                   # Entry point
 ├── .claude/
 │   ├── agents/                 # 46 agent definitions
-│   ├── skills/                 # 100 skill modules
+│   ├── skills/                 # 101 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: "0.75.0",
+    version: "0.76.1",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -1820,7 +1820,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.75.0",
+  version: "0.76.1",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.75.0",
+  "version": "0.76.1",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/rules/MUST-parallel-execution.md

@@ -61,11 +61,23 @@ Before writing/editing multiple files:
 
 | Rule | Detail |
 |------|--------|
-| Max instances | 4 concurrent |
+| Max instances | 5 concurrent (soft default: 4) |
 | Not parallelizable | Orchestrator (must stay singleton) |
 | Instance independence | Isolated context, no shared state |
 | Large tasks (>3 min) | MUST split into parallel sub-tasks |
 
+## Stability Testing Protocol
+
+When testing 5 concurrent agents (above the soft default of 4):
+
+| Observation | Threshold | Action |
+|-------------|-----------|--------|
+| Response latency | > 2x normal | Reduce to 4 |
+| Agent failure rate | > 10% | Reduce to 4 |
+| Context errors | Any | Reduce to 4 |
+
+5-agent concurrency is supported but should be monitored during initial adoption. Fall back to 4 if instability is observed.
+
 ## Agent Tool Requirements
 
 - Use specific `subagent_type` (not "general-purpose" when specialist exists)

package/templates/.claude/skills/agora/SKILL.md

@@ -0,0 +1,194 @@
+---
+name: agora
+description: "Multi-LLM adversarial consensus loop — 3+ LLMs compete to find flaws in designs/specs until unanimous agreement is reached"
+user-invocable: true
+argument-hint: "<document-path> [--rounds N] [--severity-threshold HIGH]"
+effort: max
+scope: core
+version: 1.0.0
+source:
+  type: external
+  origin: github
+  url: https://github.com/baekenough/baekenough-skills
+  version: 1.0.0
+---
+
+# Agora: Multi-LLM Adversarial Consensus
+
+3개 이상의 LLM(Claude, Codex/GPT, Gemini)이 경쟁적으로 설계/문서의 결함을 찾고, 만장일치 합의에 도달할 때까지 반복하는 적대적 교차 검증 스킬.
+
+## Prerequisites
+
+- `codex-exec` skill (Codex/GPT 호출)
+- `gemini-exec` skill (Gemini 호출)
+- Agent Teams enabled (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`) or Agent tool available
+
+## Usage
+
+```
+/agora docs/design.md                          # Default: 3 LLMs, unlimited rounds
+/agora docs/design.md --rounds 10              # Max 10 rounds
+/agora docs/design.md --severity-threshold HIGH # Exit when no HIGH+ findings
+/agora docs/design.md --models claude,codex     # 2 LLMs only
+```
+
+## Workflow
+
+### Phase 1: Setup
+1. Read the target document
+2. Create Agent Team: `TeamCreate("agora-review")`
+3. Create review tasks per focus area
+
+### Phase 2: Spawn Reviewers (parallel)
+Spawn 3 reviewers as Agent Team members:
+
+```
+Agent(name: "claude-critic", model: opus, effort: max)
+  → 20-point deep adversarial review
+  
+Agent(name: "codex-critic", model: opus)
+  → Invoke Skill(codex-exec) for GPT perspective + independent Claude analysis
+  
+Agent(name: "gemini-critic", model: opus)  
+  → Invoke Skill(gemini-exec) for Gemini perspective + independent Claude analysis
+```
+
+### Phase 3: Independent Review
+Each reviewer performs adversarial review with this template:
+
+```
+For EACH review point:
+### Round N: [Topic]
+**Severity**: CRITICAL / HIGH / MEDIUM / LOW
+**Flaw**: [Specific, concrete problem description]
+**Evidence**: [Why this is real, not theoretical]
+**Impact**: [What happens if not addressed]
+**Counter-argument**: [Best case FOR the current design]
+**Verdict**: KEEP / MODIFY / REJECT
+```
+
+Review areas (adapt to document type):
+- Architecture fundamentals
+- Component/service design
+- Data architecture
+- Security & resilience
+- Feasibility & deployment
+- Testing strategy
+- Operational complexity
+
+### Phase 4: Cross-Review (Peer-to-Peer)
+Each reviewer sends findings to the other two via `SendMessage`.
+
+Counter-review template:
+1. Which findings do you **AGREE** with? (and why)
+2. Which findings do you **DISAGREE** with? (evidence-based rebuttal)
+3. What did they **MISS** that you caught?
+4. What did they catch that you **MISSED**?
+5. **SEVERITY** adjustments — upgrade or downgrade with justification
+
+### Phase 5: Synthesis
+Team lead aggregates all findings:
+
+```
+UNANIMOUS CRITICAL: [findings all 3 agreed on]
+STRONG AGREEMENT:   [findings 2/3 agreed on]
+SPLIT DECISIONS:    [findings with disagreement + resolution]
+```
+
+Determine verdict:
+- **BUILD**: No CRITICAL, no unresolved HIGH
+- **BUILD WITH CHANGES**: No CRITICAL, HIGH findings have accepted mitigations
+- **REDESIGN**: Any unresolved CRITICAL findings
+- **ABANDON**: Fundamental concept is flawed
+
+### Phase 6: Loop (if REDESIGN)
+1. Team lead produces/delegates redesign addressing ALL critical findings
+2. New version sent to ALL reviewers: `SendMessage(to: "*")`
+3. Reviewers re-review → GOTO Phase 4
+4. Repeat until EXIT criteria met
+
+### Phase 7: Exit (consensus reached)
+When ALL reviewers agree BUILD or BUILD WITH CHANGES:
+1. Produce final consensus report
+2. Write to `.claude/outputs/sessions/{date}/agora-{topic}-{time}.md`
+3. Shut down team: `SendMessage(to: "*", message: {type: "shutdown_request"})`
+
+## Reviewer Principles
+
+1. **NEUTRAL** — no reviewer has home team advantage
+2. **COMPETITIVE** — find flaws others missed
+3. **CRITICAL** — "fewer than 5 CRITICAL flaws = not looking hard enough"
+4. **EVIDENCE-BASED** — every finding cites specific evidence
+5. **CONSTRUCTIVE** — every flaw includes recommended fix
+6. **CONVERGENT** — goal is consensus, not endless disagreement
+
+## Consensus Criteria
+
+| Condition | Required |
+|-----------|----------|
+| CRITICAL findings resolved | ALL |
+| HIGH findings resolved or accepted | ALL |
+| All reviewers rate BUILD or BUILD WITH CHANGES | YES |
+| Cross-review disagreements resolved | ALL |
+
+## Output Format
+
+```markdown
+# Agora Consensus Report
+
+## Document: [path]
+## Rounds: [N]
+## Reviewers: [list with LLM models used]
+
+## Verdict: [BUILD / BUILD WITH CHANGES / REDESIGN]
+
+## Unanimous Findings
+| # | Finding | Severity | All 3 Agree |
+|---|---------|----------|-------------|
+
+## Required Changes Before Build
+1. [change with source reviewer]
+2. ...
+
+## Accepted Risks
+- [finding accepted with justification]
+
+## Unique Contributions Per Reviewer
+| Reviewer | Findings Others Missed |
+|----------|----------------------|
+
+## Process Metrics
+- Rounds: N
+- Total findings: N
+- Cross-adopted: N
+- Severity upgrades: N
+- Severity downgrades: N
+- Disagreements raised: N
+- Disagreements resolved: N/N
+```
+
+## Configuration
+
+```yaml
+# Default settings
+agora:
+  max_rounds: unlimited       # Set --rounds to limit
+  severity_threshold: HIGH    # EXIT when no findings >= threshold
+  models:
+    - claude (opus, max effort)
+    - codex (via codex-exec skill)
+    - gemini (via gemini-exec skill)
+  review_points: 20           # Per reviewer
+  cross_review: true          # Peer-to-peer sharing
+  auto_redesign: true         # Auto-produce redesign on REDESIGN verdict
+```
+
+## Anti-Patterns
+
+| Anti-Pattern | Why Wrong | Correct |
+|-------------|-----------|---------|
+| Single LLM review | Misses blind spots | 3+ LLMs find complementary flaws |
+| No cross-review | Reviewers don't challenge each other | Peer-to-peer sharing surfaces disagreements |
+| Accepting first BUILD | May miss edge cases | Loop until ALL agree |
+| Ignoring split decisions | Unresolved disagreements fester | Resolve every split with evidence |
+| Push for consensus too fast | Premature agreement | Let reviewers challenge freely |

package/templates/.claude/skills/pipeline-guards/SKILL.md

@@ -18,7 +18,7 @@ Defines mandatory safety constraints for all pipeline, workflow, and iterative e
 |-------|---------|----------|------------|
 | Max iterations | 3 | 5 | worker-reviewer-pipeline |
 | Max DAG nodes | 20 | 30 | dag-orchestration |
-| Max parallel agents | 4 | 4 | R009 (all pipelines) |
+| Max parallel agents | 4 | 5 | R009 (all pipelines) |
 | Timeout per node | 300s | 600s | dag-orchestration nodes |
 | Timeout per pipeline | 900s | 1800s | worker-reviewer-pipeline |
 | Max retry count | 2 | 3 | Failure retry strategies |
@@ -148,7 +148,7 @@ Guard warnings appear inline:
 
 | Rule/Skill | Integration |
 |------------|-------------|
-| R009 | Max parallel agents enforced (hard cap: 4) |
+| R009 | Max parallel agents enforced (hard cap: 5, soft default: 4) |
 | R010 | Guards run in orchestrator only |
 | R015 | Guard warnings displayed transparently |
 | dag-orchestration | Node count and timeout limits |

package/templates/CLAUDE.md

@@ -108,6 +108,7 @@ oh-my-customcode로 구동됩니다.
 | `/omcustom:improve-report` | eval-core 기반 개선 현황 리포트 |
 | `/omcustom-takeover` | 기존 에이전트/스킬에서 canonical spec 추출 |
 | `/adversarial-review` | 공격자 관점 보안 코드 리뷰 |
+| `/omcustom:agora` | Multi-LLM 적대적 합의 루프 (설계/스펙 교차 검증) |
 | `/ambiguity-gate` | 요청 모호성 분석 및 명확화 질문 (ouroboros 패턴) |
 | `/dev-review` | 코드 베스트 프랙티스 리뷰 |
 | `/dev-refactor` | 코드 리팩토링 |
@@ -151,7 +152,7 @@ project/
 +-- CLAUDE.md                    # 진입점
 +-- .claude/
 |   +-- agents/                  # 서브에이전트 정의 (46 파일)
-|   +-- skills/                  # 스킬 (99 디렉토리)
+|   +-- skills/                  # 스킬 (100 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": "0.75.0",
+  "version": "0.76.1",
   "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": 100
+      "files": 101
     },
     {
       "name": "guides",