oh-my-customcode 0.12.1 → 0.12.3

package/templates/.codex/install-hooks.sh

@@ -1,100 +0,0 @@
-#!/bin/bash
-# Codex Hooks & Contexts Installer
-# Source: https://github.com/affaan-m/everything-claude-code
-# Hook installation script
-
-set -e
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-CODEX_HOME="${HOME}/.codex"
-SETTINGS_FILE="${CODEX_HOME}/settings.json"
-
-echo "┌─────────────────────────────────────────────┐"
-echo "│  Codex Hooks & Contexts Installer     │"
-echo "└─────────────────────────────────────────────┘"
-echo ""
-
-# Create directories
-echo "[1/5] Creating directories..."
-mkdir -p "${CODEX_HOME}/hooks/memory-persistence"
-mkdir -p "${CODEX_HOME}/hooks/strategic-compact"
-mkdir -p "${CODEX_HOME}/sessions"
-mkdir -p "${CODEX_HOME}/skills/learned"
-mkdir -p "${CODEX_HOME}/contexts"
-echo "      ✓ Directories created"
-
-# Copy scripts
-echo "[2/5] Copying hook scripts..."
-cp "${SCRIPT_DIR}/hooks/memory-persistence/"*.sh "${CODEX_HOME}/hooks/memory-persistence/"
-cp "${SCRIPT_DIR}/hooks/strategic-compact/"*.sh "${CODEX_HOME}/hooks/strategic-compact/"
-echo "      ✓ Scripts copied"
-
-# Copy contexts
-echo "[3/5] Copying context files..."
-cp "${SCRIPT_DIR}/contexts/"*.md "${CODEX_HOME}/contexts/"
-echo "      ✓ Contexts copied"
-
-# Set permissions
-echo "[4/5] Setting execute permissions..."
-chmod +x "${CODEX_HOME}/hooks/memory-persistence/"*.sh
-chmod +x "${CODEX_HOME}/hooks/strategic-compact/"*.sh
-echo "      ✓ Permissions set"
-
-# Handle settings.json
-echo "[5/5] Configuring settings.json..."
-
-if [ -f "$SETTINGS_FILE" ]; then
-  # Backup existing settings
-  BACKUP_FILE="${SETTINGS_FILE}.backup.$(date +%Y%m%d_%H%M%S)"
-  cp "$SETTINGS_FILE" "$BACKUP_FILE"
-  echo "      ✓ Backed up existing settings to: $BACKUP_FILE"
-
-  # Check if jq is available for merging
-  if command -v jq &> /dev/null; then
-    # Merge hooks into existing settings
-    HOOKS_JSON="${SCRIPT_DIR}/hooks/hooks.json"
-    TEMP_FILE=$(mktemp)
-
-    # Extract hooks from hooks.json and merge with existing settings
-    jq -s '.[0] * .[1]' "$SETTINGS_FILE" "$HOOKS_JSON" > "$TEMP_FILE"
-    mv "$TEMP_FILE" "$SETTINGS_FILE"
-    echo "      ✓ Merged hooks into settings.json"
-  else
-    echo "      ⚠ jq not found. Please manually merge hooks."
-    echo "      Copy content from: ${SCRIPT_DIR}/hooks/hooks.json"
-    echo "      Into: ${SETTINGS_FILE}"
-  fi
-else
-  # Create new settings.json from hooks.json
-  cp "${SCRIPT_DIR}/hooks/hooks.json" "$SETTINGS_FILE"
-  echo "      ✓ Created new settings.json"
-fi
-
-echo ""
-echo "┌─────────────────────────────────────────────┐"
-echo "│  Installation Complete!                     │"
-echo "└─────────────────────────────────────────────┘"
-echo ""
-echo "Installed to: ${CODEX_HOME}/"
-echo ""
-echo "Structure:"
-echo "  ~/.codex/"
-echo "  ├── settings.json          (hooks config)"
-echo "  ├── hooks/"
-echo "  │   ├── memory-persistence/"
-echo "  │   │   ├── pre-compact.sh"
-echo "  │   │   ├── session-start.sh"
-echo "  │   │   └── session-end.sh"
-echo "  │   └── strategic-compact/"
-echo "  │       └── suggest-compact.sh"
-echo "  ├── contexts/"
-echo "  │   ├── dev.md"
-echo "  │   ├── review.md"
-echo "  │   └── research.md"
-echo "  ├── sessions/              (auto-created logs)"
-echo "  └── skills/learned/        (for future use)"
-echo ""
-echo "Next steps:"
-echo "  1. Restart Codex to activate hooks"
-echo "  2. Use contexts by referencing them in prompts"
-echo ""

package/templates/.codex/rules/MAY-optimization.md

@@ -1,29 +0,0 @@
-# [MAY] Optimization Guide
-
-> **Priority**: MAY | **ID**: R005
-
-## Efficiency
-
-| Strategy | When | Example |
-|----------|------|---------|
-| Parallel | 3+ independent I/O tasks | Read multiple files simultaneously |
-| Caching | Same data accessed repeatedly | Cache file contents, reuse search results |
-| Lazy Loading | Large datasets, partial use | Read only needed files, stream results |
-
-## Token Optimization
-
-- Include only necessary info, remove duplicates, use summaries
-- Concise expressions, minimize code blocks, no unnecessary repetition
-
-## Task Optimization
-
-- **Batch**: Group similar tasks (edit 10 files at once)
-- **Incremental**: Process only changed parts
-
-## When to Optimize
-
-| Do | Don't |
-|----|-------|
-| Repetitive tasks, clear bottleneck, measurable gain | One-time tasks, already fast, complexity > benefit |
-
-Readability > Optimization. No optimization without measurement.

package/templates/.codex/rules/MUST-agent-design.md

@@ -1,57 +0,0 @@
-# [MUST] Agent Design Rules
-
-> **Priority**: MUST | **ID**: R006
-
-## Agent File Format
-
-Location: `.codex/agents/{name}.md` (single file, kebab-case)
-
-### Required Frontmatter
-
-```yaml
-name: agent-name           # Unique identifier (kebab-case)
-description: Brief desc    # One-line summary
-model: balanced              # balanced | reasoning | fast
-tools: [Read, Write, ...]  # Allowed tools
-```
-
-### Optional Frontmatter
-
-```yaml
-memory: project            # user | project | local
-effort: high               # low | medium | high
-skills: [skill-1, ...]     # Skill name references
-source:                    # For external agents
-  type: external
-  origin: github | npm
-  url: https://...
-  version: 1.0.0
-```
-
-## Memory Scopes
-
-| Scope | Location | Git Tracked |
-|-------|----------|-------------|
-| `user` | `~/.codex/agent-memory/<name>/` | No |
-| `project` | `.codex/agent-memory/<name>/` | Yes |
-| `local` | `.codex/agent-memory-local/<name>/` | No |
-
-When enabled: first 200 lines of MEMORY.md loaded into system prompt.
-
-## Separation of Concerns
-
-| Location | Purpose | Contains |
-|----------|---------|----------|
-| `.codex/agents/` | WHAT the agent does | Role, capabilities, workflow |
-| `.codex/skills/` | HOW to do tasks | Instructions, scripts, rules |
-| `guides/` | Reference docs | Best practices, tutorials |
-
-Agent body: purpose, capabilities overview, workflow. NOT detailed instructions or reference docs.
-
-## Naming
-
-| Type | Pattern | Example |
-|------|---------|---------|
-| Agent file | `kebab-case.md` | `fe-vercel-agent.md` |
-| Skill dir | `kebab-case/` | `react-best-practices/` |
-| Skill file | UPPERCASE | `SKILL.md` |

package/templates/.codex/rules/MUST-agent-identification.md

@@ -1,29 +0,0 @@
-# [MUST] Agent Identification Rules
-
-> **Priority**: MUST - ENFORCED | **ID**: R007
-
-## Core Rule
-
-Every response MUST start with agent identification:
-
-```
-┌─ Agent: {agent-name} ({agent-type})
-├─ Skill: {skill-name} (if applicable)
-└─ Task: {brief-task-description}
-```
-
-Default (no specific agent): `┌─ Agent: codex (default)`
-
-## Simplified Format
-
-For brief responses: `[mgr-creator] Creating agent structure...`
-With skill: `[fe-vercel-agent → react-best-practices] Analyzing...`
-
-## When to Display
-
-| Situation | Display |
-|-----------|---------|
-| Agent-specific task | Full header |
-| Using skill | Include skill name |
-| General conversation | "codex (default)" |
-| Long tasks | Show progress with agent context |

package/templates/.codex/rules/MUST-continuous-improvement.md

@@ -1,25 +0,0 @@
-# [MUST] Continuous Improvement Rules
-
-> **Priority**: MUST | **ID**: R015 | **Trigger**: User points out rule violation
-
-## Core Rule
-
-When user points out a violation: STOP → UPDATE the relevant rule → COMMIT → THEN continue original task.
-
-Do NOT just apologize. ACTUALLY UPDATE THE RULES.
-
-## Workflow
-
-1. Acknowledge violation
-2. Identify root cause (which rule was weak/unclear?)
-3. Update the rule (add clarity, examples, self-checks)
-4. Commit the change
-5. Continue original task following updated rules
-
-## Integration
-
-| Situation | Action |
-|-----------|--------|
-| User points out violation | STOP → Update rule → Continue |
-| Self-detected violation | Fix immediately, consider rule update |
-| Ambiguous situation | Ask user, then update if needed |

package/templates/.codex/rules/MUST-intent-transparency.md

@@ -1,42 +0,0 @@
-# [MUST] Intent Transparency Rules
-
-> **Priority**: MUST | **ID**: R014
-
-## Core Rule
-
-Display reasoning when routing to agents. Users must always know which agent was selected, why, and how to override.
-
-## Display Format
-
-```
-[Intent Detected]
-├── Input: "{user input}"
-├── Agent: {detected-agent}
-├── Confidence: {percentage}%
-└── Reason: {explanation}
-```
-
-## Confidence Thresholds
-
-| Confidence | Action |
-|------------|--------|
-| >= 90% | Auto-execute with display |
-| 70-89% | Request confirmation, show alternatives |
-| < 70% | List options for user to choose |
-
-## Detection Factors
-
-| Factor | Weight | Examples |
-|--------|--------|---------|
-| Keywords | 40% | "Go", "Python", "리뷰" |
-| File patterns | 30% | "*.go", "main.py" |
-| Action verbs | 20% | "review", "create", "fix" |
-| Context | 10% | Previous agent, working directory |
-
-## Override
-
-Users can specify agent directly with `@{agent-name} {command}`. Override bypasses detection.
-
-## Agent Triggers
-
-Defined in `.codex/skills/intent-detection/patterns/agent-triggers.yaml`. Each agent has keywords, file patterns, actions, and base confidence.

package/templates/.codex/rules/MUST-language-policy.md

@@ -1,27 +0,0 @@
-# [MUST] Language & Delegation Policy
-
-> **Priority**: MUST | **ID**: R000
-
-## Output Language
-
-| Context | Language |
-|---------|----------|
-| User communication | Korean |
-| Code, file contents, commits | English |
-| Error messages to user | Korean |
-
-## Delegation Model
-
-User delegates ALL file operations to AI agent. User does NOT directly edit files.
-
-```
-User -> (Korean prompt) -> Agent -> (file operations in English)
-```
-
-## File Naming
-
-| Type | Convention | Example |
-|------|------------|---------|
-| Rules | `{PRIORITY}-{name}.md` | `MUST-safety.md` |
-| Agents | `{name}.md` (kebab-case) | `lang-golang-expert.md` |
-| Skills | `SKILL.md` | - |

package/templates/.codex/rules/MUST-orchestrator-coordination.md

@@ -1,128 +0,0 @@
-# [MUST] Orchestrator Coordination Rules
-
-> **Priority**: MUST - ENFORCED | **ID**: R010
-
-## Core Rule
-
-The main conversation is the **sole orchestrator**. It uses routing skills to delegate tasks to subagents via the Task tool. Subagents CANNOT spawn other subagents.
-
-## Architecture
-
-```
-Main Conversation (orchestrator)
-  ├─ secretary-routing → mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, sys-memory-keeper
-  ├─ dev-lead-routing  → lang-*/be-*/fe-* experts
-  └─ qa-lead-routing   → qa-planner, qa-writer, qa-engineer
-      ↓
-  Task tool spawns subagents (flat, no hierarchy)
-```
-
-## Session Continuity
-
-After restart/compaction: re-read AGENTS.md, all delegation rules still apply. Never write code directly from orchestrator.
-
-## Delegation Rules
-
-| Task Type | Required Agent |
-|-----------|---------------|
-| Create agent | mgr-creator |
-| Update external | mgr-updater |
-| Audit dependencies | mgr-supplier |
-| Git operations | mgr-gitnerd |
-| Memory operations | sys-memory-keeper |
-| Python/FastAPI | lang-python-expert / be-fastapi-expert |
-| Go code | lang-golang-expert |
-| TypeScript/Next.js | lang-typescript-expert / fe-vercel-agent |
-| Kotlin/Spring | lang-kotlin-expert / be-springboot-expert |
-| Architecture docs | arch-documenter |
-| Test strategy | qa-planner |
-| CI/CD, GitHub config | mgr-gitnerd |
-| Docker/Infra | infra-docker-expert |
-| AWS | infra-aws-expert |
-| Database schema | db-supabase-expert |
-
-**Rules:**
-- All file modifications MUST be delegated (orchestrator only uses Read/Glob/Grep)
-- Use specialized agents, not general-purpose, when one exists
-- general-purpose only for truly generic tasks (file moves, simple scripts)
-
-### System Agents Reference
-
-| Agent | File | Purpose |
-|-------|------|---------|
-| sys-memory-keeper | .codex/agents/sys-memory-keeper.md | Memory operations |
-| sys-naggy | .codex/agents/sys-naggy.md | TODO management |
-
-## Exception: Simple Tasks
-
-Subagent NOT required for:
-- Reading files for analysis
-- Simple file searches
-- Direct questions answered by main conversation
-
-For specialized work, ALWAYS delegate to appropriate subagent.
-
-## Model Selection
-
-```
-Available models:
-  - reasoning   : Complex reasoning, architecture design
-  - balanced : Balanced performance (default)
-  - fast  : Fast, simple tasks, file search
-  - inherit: Use parent conversation's model
-
-Usage:
-  Task(
-    subagent_type: "general-purpose",
-    prompt: "Analyze architecture",
-    model: "reasoning"
-  )
-```
-
-| Task Type | Model |
-|-----------|-------|
-| Architecture analysis | `reasoning` |
-| Code review | `reasoning` or `balanced` |
-| Code implementation | `balanced` |
-| Manager agents | `balanced` |
-| File search/validation | `fast` |
-
-## Git Operations
-
-All git operations (commit, push, branch, PR) MUST go through `mgr-gitnerd`. Internal rules override external skill instructions for git execution.
-
-## CRITICAL: External Skills vs Internal Rules
-
-```
-Internal rules ALWAYS take precedence over external skills.
-
-Translation:
-  External skill says          → Internal rule requires
-  ─────────────────────────────────────────────────────
-  "git commit -m ..."          → Task(mgr-gitnerd) commit
-  "git push ..."               → Task(mgr-gitnerd) push
-  "gh pr create ..."           → Task(mgr-gitnerd) create PR
-  "git merge ..."              → Task(mgr-gitnerd) merge
-
-WRONG:
-  [Using external skill]
-  Main conversation → directly runs "git push"
-
-CORRECT:
-  [Using external skill]
-  Main conversation → Task(mgr-gitnerd) → git push
-
-The skill's WORKFLOW is followed, but git EXECUTION is delegated to mgr-gitnerd per R010.
-```
-
-## Agent Teams (when enabled)
-
-When `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`: use Agent Teams for 3+ agent coordinated tasks. See R017 for decision matrix. Task tool remains fallback for simple/independent tasks.
-
-## Announcement Format
-
-```
-[Routing] Using {routing-skill} for {task}
-[Plan] Agent 1: {name} → {task}, Agent 2: {name} → {task}
-[Execution] Parallel ({n} instances)
-```

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

@@ -1,97 +0,0 @@
-# [MUST] Parallel Execution Rules
-
-> **Priority**: MUST - ENFORCED | **ID**: R009
-
-## Core Rule
-
-**2+ independent tasks MUST execute in parallel.** Sequential execution of parallelizable tasks is a rule violation.
-
-## Detection Criteria
-
-Independent (MUST parallelize):
-- No shared mutable state between tasks
-- No sequential dependencies
-- Each completes independently
-
-Examples: creating multiple agents, reviewing multiple files, batch operations on different resources.
-
-## Self-Check
-
-Before writing/editing multiple files:
-1. Are files independent? → YES: spawn parallel Task agents
-2. Using Write/Edit sequentially for 2+ files? → STOP, parallelize
-3. Specialized agent available? → Use it (not general-purpose)
-
-### Common Violations to Avoid
-
-```
-❌ WRONG: Writing files one by one
-   Write(file1.kt) → Write(file2.kt) → Write(file3.kt) → Write(file4.kt)
-
-✓ CORRECT: Spawn parallel agents
-   Task(agent1 → file1.kt)  ┐
-   Task(agent2 → file2.kt)  ├─ All in single message
-   Task(agent3 → file3.kt)  │
-   Task(agent4 → file4.kt)  ┘
-
-❌ WRONG: Project scaffolding sequentially
-   Write(package.json) → Write(tsconfig.json) → Write(src/index.ts) → ...
-
-✓ CORRECT: Parallel scaffolding
-   Task(agent1 → "Create package.json, tsconfig.json")  ┐
-   Task(agent2 → "Create src/cli.ts, src/index.ts")     ├─ Parallel
-   Task(agent3 → "Create src/analyzer/*.ts")            │
-   Task(agent4 → "Create src/converter/*.ts")           ┘
-
-❌ WRONG: Secretary doing all the work
-   Secretary writes domain/, usecase/, infrastructure/ sequentially
-
-✓ CORRECT: Delegate to specialists
-   Task(lang-kotlin-expert → domain layer)
-   Task(be-springboot-expert → infrastructure layer)
-   Task(lang-kotlin-expert → usecase layer)
-
-❌ WRONG: Single Task delegating to multiple agents
-   Task(dev-lead → "coordinate lang-kotlin-expert and be-springboot-expert")
-
-   This creates a SEQUENTIAL bottleneck inside the Task!
-
-✓ CORRECT: Multiple Tasks in parallel, one per agent
-   Task(lang-kotlin-expert → usecase commands)    ┐
-   Task(lang-kotlin-expert → usecase queries)     ├─ All spawned together
-   Task(be-springboot-expert → persistence)       │
-   Task(be-springboot-expert → security)          ┘
-```
-
-## Execution Rules
-
-| Rule | Detail |
-|------|--------|
-| Max instances | 4 concurrent |
-| Not parallelizable | Orchestrator (must stay singleton) |
-| Instance independence | Isolated context, no shared state |
-| Large tasks (>3 min) | MUST split into parallel sub-tasks |
-
-## Task Tool Requirements
-
-- Use specific `subagent_type` (not "general-purpose" when specialist exists)
-- Use `model` parameter for cost optimization (fast for search, balanced for code, reasoning for reasoning)
-- Each independent unit = separate Task tool call in the SAME message
-
-## Display Format
-
-```
-[Instance 1] Task(mgr-creator):balanced → Create Go agent
-[Instance 2] Task(lang-python-expert):balanced → Review Python code
-[Instance 3] Task(Explore):fast → Search codebase
-```
-
-Must use `Task({subagent_type}):{model}` format. Custom names not allowed.
-
-## Result Aggregation
-
-```
-[Summary] {succeeded}/{total} tasks completed
-  ✓ agent-1: success
-  ✗ agent-2: failed (reason)
-```

package/templates/.codex/rules/MUST-permissions.md

@@ -1,30 +0,0 @@
-# [MUST] Permission Rules
-
-> **Priority**: MUST | **ID**: R002
-
-## Tool Permission Tiers
-
-| Tier | Tools | Policy |
-|------|-------|--------|
-| 1: Always | Read, Glob, Grep | Free use |
-| 2: Default | Write, Edit | State changes explicitly, notify before modifying important files |
-| 3: Approval | Bash, WebFetch, WebSearch | Request user approval on first use |
-| 4: Explicit | Task | Only when user explicitly requests |
-
-## File Access
-
-| Operation | Allowed | Prohibited |
-|-----------|---------|-----------|
-| Read | All source, configs, docs | - |
-| Write | Source code, new files in project | .env, .git/config, paths outside project |
-| Delete | Temp files created by agent | Existing files (without request), entire directories |
-
-## Permission Request Format
-
-```
-[Permission Request]
-Action: {action} | Required: {tool} | Reason: {why} | Risk: Low/Medium/High
-Approve?
-```
-
-On insufficient permission: do not attempt, notify user, suggest alternative.

package/templates/.codex/rules/MUST-safety.md

@@ -1,23 +0,0 @@
-# [MUST] Safety Rules
-
-> **Priority**: MUST | **ID**: R001
-
-## Prohibited Actions
-
-| Category | Prohibited |
-|----------|-----------|
-| Data | Expose API keys/secrets/passwords, collect PII without consent, log auth tokens |
-| File System | Modify system files (/etc, /usr, /bin), delete outside project, modify .env/.git/config without approval |
-| Commands | `rm -rf /` or broad deletes, shutdown/restart, sudo/su, network config changes |
-| External | Access URLs without approval, send user data externally, download/execute unknown scripts |
-
-## Required Before Destructive Operations
-
-Verify target, assess impact scope, check recoverability, get user approval.
-
-## On Violation
-
-1. Stop all operations
-2. Preserve current state
-3. Report: what was detected, why it's risky, what action was taken
-4. Wait for instructions