oh-my-customcode 0.3.2 → 0.5.0

package/templates/guides/index.yaml

@@ -1,4 +1,4 @@
-# Baekgom Agents - Guides Index
+# Guides Index
 
 guides:
   # Internal

package/templates/index.yaml

@@ -1,4 +1,4 @@
-# Baekgom Agents - Pipeline Registry
+# Pipeline Registry
 
 description: Registry of available pipelines for sequential workflows
 

package/templates/manifest.json

@@ -1,12 +1,12 @@
 {
   "version": "0.2.0",
-  "lastUpdated": "2026-02-05T08:54:15.660Z",
+  "lastUpdated": "2026-02-06T06:06:08.847Z",
   "components": [
     {
       "name": "rules",
       "path": ".claude/rules",
       "description": "Agent behavior rules and guidelines",
-      "files": 19
+      "files": 18
     },
     {
       "name": "agents",
@@ -18,7 +18,7 @@
       "name": "skills",
       "path": ".claude/skills",
       "description": "Reusable skill modules (includes slash commands)",
-      "files": 42
+      "files": 41
     },
     {
       "name": "guides",
@@ -26,17 +26,11 @@
       "description": "Reference documentation",
       "files": 13
     },
-    {
-      "name": "pipelines",
-      "path": "pipelines",
-      "description": "Workflow pipeline definitions",
-      "files": 3
-    },
     {
       "name": "hooks",
       "path": ".claude/hooks",
       "description": "Lifecycle hook scripts",
-      "files": 8
+      "files": 1
     },
     {
       "name": "contexts",
@@ -45,5 +39,5 @@
       "files": 5
     }
   ],
-  "source": "https://github.com/baekenough/baekgom-agents"
+  "source": "https://github.com/baekenough/oh-my-customcode"
 }

package/templates/.claude/agents/tutor-go.md

@@ -1,125 +0,0 @@
----
-name: tutor-go
-description: Use when you need to teach Go language and data structures/algorithms through the learn-go curriculum, generating chapter content, exercises, and providing learning feedback
-model: sonnet
-tools:
-  - Read
-  - Write
-  - Edit
-  - Grep
-  - Glob
-  - Bash
----
-
-You are a Go language and data structures/algorithms tutor for the learn-go curriculum, teaching through structured lessons with exercises.
-
-## Target Curriculum
-
-```
-~/workspace/projects/learn-go/
-├── part1-go-basics/      (Ch01-10)
-├── part2-algorithms/     (Ch11-25)
-└── part3-backend/        (Ch26-35)
-```
-
-## Core Capabilities
-
-1. Generate chapter content (README.md with theory)
-2. Create runnable examples (examples/*.go)
-3. Create exercises with test cases (exercises/*.go, *_test.go)
-4. Review and provide feedback on solutions
-5. Track learning progress
-6. Answer questions about Go and algorithms
-
-## Commands
-
-| Command | Description |
-|---------|-------------|
-| `tutor:start <chapter>` | Generate chapter content and exercises |
-| `tutor:review` | Review current exercise solution |
-| `tutor:hint` | Get a hint for current exercise |
-| `tutor:solution` | Show solution (after attempt) |
-| `tutor:ask <question>` | Ask about Go or algorithms |
-| `tutor:progress` | Show learning progress |
-| `tutor:next` | Move to next chapter |
-
-## Teaching Principles
-
-1. **Theory first, then practice** - Explain concepts before coding
-2. **Python comparison** - Reference Python for familiar concepts
-3. **Incremental difficulty** - Start with scaffolded exercises
-4. **Test-driven** - All exercises have test cases
-5. **Korean comments** - Theory AND code comments in Korean, only identifiers in English
-
-## Language Policy
-
-| 항목 | 언어 | 예시 |
-|------|------|------|
-| README.md | 한국어 | 이론 설명, 개념 정리 |
-| 코드 주석 | 한국어 | `// 사용자 이름을 출력한다` |
-| 변수/함수명 | 영어 | `userName`, `PrintGreeting` |
-| 문자열 리터럴 | 영어 | `"Hello, World!"` |
-
-## Chapter Content Structure
-
-```
-chXX-topic/
-├── README.md           # Theory explanation (Korean)
-│   ├── Concept overview
-│   ├── Key points
-│   ├── Python comparison (where applicable)
-│   └── Common mistakes
-├── examples/
-│   └── main.go         # Runnable examples with comments
-└── exercises/
-    ├── ex01.go         # Exercise file
-    ├── ex01_test.go    # Test cases
-    └── solution/
-        └── ex01.go     # Reference solution
-```
-
-## Exercise Styles by Part
-
-| Part | Style |
-|------|-------|
-| Part 1 (Ch01-05) | Fill-in-the-blank, heavy scaffolding |
-| Part 1 (Ch06-10) | Partial scaffolding |
-| Part 2 (Ch11-18) | Problem + tests, minimal scaffold |
-| Part 2 (Ch19-25) | Full implementation (Baekjoon style) |
-| Part 3 | Project-based, guided |
-
-## Workflow
-
-```
-User: tutor:start ch01
-      │
-      ▼
-┌─────────────────────────┐
-│ 1. Create chapter folder │
-│ 2. Write README.md       │
-│ 3. Create examples/      │
-│ 4. Create exercises/     │
-│ 5. Report completion     │
-└─────────────────────────┘
-      │
-      ▼
-User: (works on exercises)
-      │
-      ▼
-User: tutor:review
-      │
-      ▼
-┌─────────────────────────┐
-│ 1. Run go test          │
-│ 2. Review code quality  │
-│ 3. Provide feedback     │
-└─────────────────────────┘
-```
-
-## Skills Referenced
-
-- go-best-practices: Core Go guidelines for idiomatic code
-
-## Guides Referenced
-
-- golang: Go reference documentation and best practices

package/templates/.claude/hooks/hud/index.yaml

@@ -1,27 +0,0 @@
-# HUD Statusline Hooks
-# Provides real-time status display during agent operations
-
-name: hud-statusline
-description: Real-time status display during operations
-rule: R012 (SHOULD-hud-statusline)
-
-scripts:
-  - name: update-status
-    path: ./update-status.sh
-    description: Update HUD statusline with agent/progress/parallel info
-    usage: update-status.sh <agent> [progress] [parallel_count]
-
-triggers:
-  - PreToolUse (Task)
-  - PostToolUse (Task)
-  - Agent activation
-  - Parallel spawn/complete
-
-components:
-  agent: Current agent name
-  progress: Task progress (n/total)
-  parallel: Parallel instance count
-
-installation:
-  step1: "chmod +x ~/.claude/hooks/hud/update-status.sh"
-  step2: "Hook is called automatically or manually via script"

package/templates/.claude/hooks/hud/update-status.sh

@@ -1,32 +0,0 @@
-#!/bin/bash
-# HUD Statusline Hook - Update status display
-#
-# Displays real-time status information during agent operations.
-# Output via stderr to avoid polluting tool output.
-#
-# Usage: update-status.sh <agent> [progress] [parallel_count]
-#
-# Examples:
-#   update-status.sh "creator" "1/3"
-#   update-status.sh "secretary" "0/4" "4"
-#   update-status.sh "golang-expert"
-
-AGENT="${1:-claude}"
-PROGRESS="${2:-}"
-PARALLEL="${3:-0}"
-
-# Build status line
-STATUS="[Agent] $AGENT"
-
-# Add progress if provided
-if [ -n "$PROGRESS" ]; then
-  STATUS="$STATUS | [Progress] $PROGRESS"
-fi
-
-# Add parallel count if > 0
-if [ "$PARALLEL" -gt 0 ] 2>/dev/null; then
-  STATUS="$STATUS | [Parallel] $PARALLEL"
-fi
-
-# Output to stderr to avoid polluting tool output
-echo "─── $STATUS ───" >&2

package/templates/.claude/hooks/index.yaml

@@ -1,46 +0,0 @@
-# Claude Code Hooks Configuration
-# Source: https://github.com/affaan-m/everything-claude-code
-
-hooks:
-  PreToolUse:
-    - dev-server-tmux-guard
-    - long-running-tmux-reminder
-    - git-push-review-pause
-    - md-file-creation-block
-    - strategic-compact-suggester
-    - hud-statusline (Task)
-
-  PreCompact:
-    - memory-persistence/pre-compact
-
-  SessionStart:
-    - memory-persistence/session-start
-
-  PostToolUse:
-    - pr-creation-logger
-    - prettier-auto-format (js/ts)
-    - typescript-checker
-    - console-log-warner
-    - gofmt-auto-format (go)
-    - ruff-format-and-lint (python)
-    - ty-type-check (python)
-
-  Stop:
-    - console-log-final-audit
-    - memory-persistence/session-end
-
-scripts:
-  memory-persistence:
-    - pre-compact.sh
-    - session-start.sh
-    - session-end.sh
-  strategic-compact:
-    - suggest-compact.sh
-  hud:
-    - update-status.sh
-
-installation:
-  step1: "Copy hooks.json content to ~/.claude/settings.json"
-  step2: "Copy scripts to ~/.claude/hooks/"
-  step3: "chmod +x ~/.claude/hooks/**/*.sh"
-  step4: "Create ~/.claude/sessions/ and ~/.claude/skills/learned/"

package/templates/.claude/hooks/memory-persistence/pre-compact.sh

@@ -1,37 +0,0 @@
-#!/bin/bash
-# PreCompact Hook - Save state before context compaction
-#
-# Runs before Claude compacts context. Logs the event and marks
-# active session files so you know when compaction occurred.
-#
-# Hook config (in ~/.claude/settings.json):
-# {
-#   "hooks": {
-#     "PreCompact": [{
-#       "matcher": "*",
-#       "hooks": [{
-#         "type": "command",
-#         "command": "~/.claude/hooks/memory-persistence/pre-compact.sh"
-#       }]
-#     }]
-#   }
-# }
-
-SESSIONS_DIR="${HOME}/.claude/sessions"
-LOG_FILE="${SESSIONS_DIR}/compaction-log.txt"
-
-mkdir -p "$SESSIONS_DIR"
-
-# Log the compaction event
-echo "[$(date '+%Y-%m-%d %H:%M:%S')] Context compaction triggered" >> "$LOG_FILE"
-
-# Find and mark active session file
-ACTIVE_SESSION=$(find "$SESSIONS_DIR" -name "*.tmp" -mmin -60 2>/dev/null | head -1)
-if [ -n "$ACTIVE_SESSION" ] && [ -f "$ACTIVE_SESSION" ]; then
-  echo "" >> "$ACTIVE_SESSION"
-  echo "---" >> "$ACTIVE_SESSION"
-  echo "**[COMPACTION]** Context compacted at $(date '+%H:%M')" >> "$ACTIVE_SESSION"
-  echo "---" >> "$ACTIVE_SESSION"
-fi
-
-echo "[PreCompact] State preserved before compaction" >&2

package/templates/.claude/hooks/memory-persistence/session-end.sh

@@ -1,64 +0,0 @@
-#!/bin/bash
-# Stop Hook (Session End) - Persist learnings when session ends
-#
-# Runs when Claude session ends. Creates/updates session log file
-# with timestamp for continuity tracking.
-#
-# Hook config (in ~/.claude/settings.json):
-# {
-#   "hooks": {
-#     "Stop": [{
-#       "matcher": "*",
-#       "hooks": [{
-#         "type": "command",
-#         "command": "~/.claude/hooks/memory-persistence/session-end.sh"
-#       }]
-#     }]
-#   }
-# }
-
-SESSIONS_DIR="${HOME}/.claude/sessions"
-TODAY=$(date '+%Y-%m-%d')
-SESSION_FILE="${SESSIONS_DIR}/${TODAY}-session.tmp"
-
-mkdir -p "$SESSIONS_DIR"
-
-# If session file exists for today, update the end time
-if [ -f "$SESSION_FILE" ]; then
-  # Update Last Updated timestamp (macOS and Linux compatible)
-  if [[ "$OSTYPE" == "darwin"* ]]; then
-    sed -i '' "s/\*\*Last Updated:\*\*.*/\*\*Last Updated:\*\* $(date '+%H:%M')/" "$SESSION_FILE" 2>/dev/null
-  else
-    sed -i "s/\*\*Last Updated:\*\*.*/\*\*Last Updated:\*\* $(date '+%H:%M')/" "$SESSION_FILE" 2>/dev/null
-  fi
-  echo "[SessionEnd] Updated session file: $SESSION_FILE" >&2
-else
-  # Create new session file with template
-  cat > "$SESSION_FILE" << EOF
-# Session: $(date '+%Y-%m-%d')
-**Date:** $TODAY
-**Started:** $(date '+%H:%M')
-**Last Updated:** $(date '+%H:%M')
-
----
-
-## Current State
-
-[Session context goes here]
-
-### Completed
-- [ ]
-
-### In Progress
-- [ ]
-
-### Notes for Next Session
--
-
-### Context to Load
-\`\`\`
-[relevant files]
-\`\`\`
-EOF
-  echo "[SessionEnd] Created session file: $SESSION_FILE" >&2
-fi

package/templates/.claude/hooks/memory-persistence/session-start.sh

@@ -1,41 +0,0 @@
-#!/bin/bash
-# SessionStart Hook - Load previous context on new session
-#
-# Runs when a new Claude session starts. Checks for recent session
-# files and learned skills to provide continuity hints.
-#
-# Hook config (in ~/.claude/settings.json):
-# {
-#   "hooks": {
-#     "SessionStart": [{
-#       "matcher": "*",
-#       "hooks": [{
-#         "type": "command",
-#         "command": "~/.claude/hooks/memory-persistence/session-start.sh"
-#       }]
-#     }]
-#   }
-# }
-
-SESSIONS_DIR="${HOME}/.claude/sessions"
-SKILLS_DIR="${HOME}/.claude/skills/learned"
-
-# Check for recent session files (last 7 days)
-if [ -d "$SESSIONS_DIR" ]; then
-  RECENT_SESSIONS=$(find "$SESSIONS_DIR" -name "*.tmp" -mtime -7 2>/dev/null | wc -l | tr -d ' ')
-  if [ "$RECENT_SESSIONS" -gt 0 ]; then
-    echo "[SessionStart] Found $RECENT_SESSIONS recent session(s)" >&2
-    LATEST=$(find "$SESSIONS_DIR" -name "*.tmp" -mtime -7 2>/dev/null | sort -r | head -1)
-    if [ -n "$LATEST" ]; then
-      echo "[SessionStart] Latest: $LATEST" >&2
-    fi
-  fi
-fi
-
-# Check for learned skills
-if [ -d "$SKILLS_DIR" ]; then
-  SKILLS_COUNT=$(find "$SKILLS_DIR" -name "*.md" 2>/dev/null | wc -l | tr -d ' ')
-  if [ "$SKILLS_COUNT" -gt 0 ]; then
-    echo "[SessionStart] $SKILLS_COUNT learned skill(s) available" >&2
-  fi
-fi

package/templates/.claude/hooks/strategic-compact/suggest-compact.sh

@@ -1,50 +0,0 @@
-#!/bin/bash
-# Strategic Compact Suggester - Suggest manual compaction at logical intervals
-#
-# Tracks tool usage and suggests compaction at strategic points.
-# Manual compaction preserves context through logical phases.
-#
-# Best times to compact:
-# - After completing an exploration phase, before starting execution
-# - After reaching a milestone (feature complete, tests passing)
-# - When context feels cluttered but before it auto-compacts
-#
-# Hook config (in ~/.claude/settings.json):
-# {
-#   "hooks": {
-#     "PreToolUse": [{
-#       "matcher": "tool == \"Edit\" || tool == \"Write\"",
-#       "hooks": [{
-#         "type": "command",
-#         "command": "~/.claude/hooks/strategic-compact/suggest-compact.sh"
-#       }]
-#     }]
-#   }
-# }
-
-COUNTER_FILE="/tmp/claude-tool-count-$$"
-THRESHOLD=${COMPACT_THRESHOLD:-50}
-
-# Initialize or increment counter
-if [ -f "$COUNTER_FILE" ]; then
-  COUNT=$(cat "$COUNTER_FILE")
-  COUNT=$((COUNT + 1))
-else
-  COUNT=1
-fi
-echo "$COUNT" > "$COUNTER_FILE"
-
-# Suggest compaction at threshold
-if [ "$COUNT" -eq "$THRESHOLD" ]; then
-  echo "[StrategicCompact] Reached $THRESHOLD tool calls" >&2
-  echo "[StrategicCompact] Consider running /compact if at a logical breakpoint" >&2
-  echo "[StrategicCompact] Good times: after exploration, before implementation" >&2
-fi
-
-# Reminder every 25 calls after threshold
-if [ "$COUNT" -gt "$THRESHOLD" ] && [ $(((COUNT - THRESHOLD) % 25)) -eq 0 ]; then
-  echo "[StrategicCompact] $COUNT tool calls - /compact reminder" >&2
-fi
-
-# Pass through input
-cat

package/templates/.claude/rules/SHOULD-pipeline-mode.md

@@ -1,165 +0,0 @@
-# [SHOULD] Pipeline Mode Rules
-
-> **Priority**: SHOULD - Recommended for sequential workflows
-> **ID**: R014
-
-## Purpose
-
-Enable declarative, sequential multi-step workflows with variable passing between steps.
-
-## Pipeline Definition Format
-
-```yaml
-name: pipeline-name
-description: What this pipeline does
-
-inputs:
-  - name: input_name
-    required: true
-    description: Input description
-
-steps:
-  - id: step_1
-    agent: agent-name
-    action: action_name
-    input: { key: "${input_name}" }
-    output: result_variable
-
-  - id: step_2
-    agent: another-agent
-    action: action_name
-    input: { data: "${result_variable}" }
-    output: final_result
-```
-
-## Variable Syntax
-
-- `${variable}`: Reference input or previous step output
-- `${step_id.field}`: Reference specific field from step output
-- `${inputs.name}`: Explicit input reference
-
-## Execution Rules
-
-### Sequential by Default
-
-Steps execute in order. Each step waits for previous step completion.
-
-```
-Step 1 → complete → Step 2 → complete → Step 3
-```
-
-### Output Passing
-
-Output from step N is available to step N+1 and beyond.
-
-```yaml
-steps:
-  - id: analyze
-    output: analysis    # Creates ${analysis}
-
-  - id: review
-    input: { data: "${analysis}" }  # Uses ${analysis}
-```
-
-### Error Handling
-
-```yaml
-error_handling:
-  default: stop              # stop | continue | retry
-
-steps:
-  - id: risky_step
-    on_error: continue       # Override for this step
-    retry:
-      max_attempts: 3
-      delay: 1000
-```
-
-## Pipeline Commands
-
-| Command | Description |
-|---------|-------------|
-| `pipeline:run <name>` | Execute a pipeline |
-| `pipeline:list` | List available pipelines |
-| `pipeline:status` | Show running pipeline status |
-
-## Pipeline Locations
-
-```
-pipelines/
-├── index.yaml              # Pipeline registry
-├── templates/              # Pipeline templates
-│   └── pipeline-template.yaml
-└── examples/               # Example pipelines
-    └── code-review.yaml
-```
-
-## Example Pipeline
-
-### code-review.yaml
-
-```yaml
-name: code-review
-description: Full code review workflow
-
-inputs:
-  - name: file_path
-    required: true
-
-steps:
-  - id: detect_language
-    agent: secretary
-    action: detect_language
-    input: { file: "${file_path}" }
-    output: language
-
-  - id: analyze
-    agent: "${language}-expert"
-    action: analyze
-    input: { file: "${file_path}" }
-    output: analysis
-
-  - id: security_check
-    agent: qa-lead
-    action: security_review
-    input: { findings: "${analysis}" }
-    output: security
-
-  - id: report
-    agent: arch-documenter
-    action: summarize
-    input:
-      analysis: "${analysis}"
-      security: "${security}"
-    output: report
-```
-
-## Execution Output
-
-```
-[Pipeline] code-review
-├── [1/4] detect_language: ✓ Go detected
-├── [2/4] analyze: ✓ 5 issues found
-├── [3/4] security_check: ✓ No vulnerabilities
-└── [4/4] report: ✓ Summary generated
-
-[Complete] Pipeline finished successfully
-Output: ${report}
-```
-
-## Secretary Integration
-
-Secretary can:
-1. Load and validate pipeline definitions
-2. Execute pipelines step-by-step
-3. Pass variables between steps
-4. Report progress and results
-5. Handle errors according to policy
-
-## Benefits
-
-1. **Reproducibility**: Same workflow, consistent results
-2. **Composability**: Build complex workflows from simple steps
-3. **Visibility**: Clear step-by-step progress
-4. **Error Recovery**: Defined error handling per step
-5. **Reusability**: Save and reuse common workflows