English | 한국어

vibe-sunsang

An AI mentor agent that turns your Claude Code conversation history into a growth engine.

vibe-sunsang automatically collects, converts, and analyzes every conversation you have with Claude Code — so you can become a more effective AI collaborator over time.

Quick Start • Why vibe-sunsang? • How it works • Modes • Level system • Requirements

/plugin marketplace add https://github.com/fivetaku/gptaku_plugins.git
/plugin install vibe-sunsang

Then restart Claude Code.

In any project:

/vibe-sunsang 시작

Onboarding will:

1. Create ~/vibe-sunsang/ workspace (with CLAUDE.md, .gitignore, and git init)
2. Scan your Claude Code conversation history at ~/.claude/projects/
3. Let you assign readable names to each discovered project
4. Classify each project by workspace type (Builder / Explorer / Designer / Operator)
5. Convert all JSONL logs to Markdown for the first time
6. Ask whether to jump straight into mentoring or a growth report

/vibe-sunsang 변환 ← convert this week's conversations
/vibe-sunsang 멘토링 ← get coaching on your AI usage patterns
/vibe-sunsang 성장 ← generate a growth report
/vibe-sunsang 지식 ← explore the level system and concepts

• Your conversations already hold the data — Claude Code stores every session as JSONL. vibe-sunsang reads those files so nothing new needs to be logged
• Not just "what did I build" — "how did I build it" — analysis focuses on your request quality, error recovery habits, and strategic thinking, not just output volume
• Workspace-type-aware — the level system adapts to what you are actually doing (coding, researching, planning, or automating)
• Six dimensions, not one score — DECOMP, VERIFY, ORCH, FAIL, CTX, META are measured independently so you know exactly which skill to develop next
• Longitudinal tracking — each growth report updates TIMELINE.md so you can see progress across months, not just a single session
• Non-developer friendly — plain-language coaching with analogies, no jargon wall

Claude Code conversation logs (~/.claude/projects/)
 |
 | /vibe-sunsang 변환
 v
 Readable Markdown files (~/vibe-sunsang/conversations/)
 |
 | 6-axis analysis
 | (DECOMP / VERIFY / ORCH / FAIL / CTX / META)
 v
 Mentoring session ←→ Growth report ←→ Concept learning
 |
 | Fit Score ×ばつ workspace-type weights
 v
 Level judgment: L1.0 – L7.0 (0.5-step increments)
 |
 v
 TIMELINE.md (longitudinal growth tracking)

Conversation data and plugin code live in separate directories, so plugin updates never touch your data.

Sets up the ~/vibe-sunsang/ workspace, maps project names, classifies workspace types, and runs the first full conversion.

Converts Claude Code JSONL logs to readable Markdown files organized by project.

Each converted file includes metadata frontmatter: date, token counts, model used, and tools called. An INDEX.md gives you the full overview at a glance.

Four coaching modes, each focused on different skill dimensions:

Mode D outputs a text radar chart and a three-step action plan: one thing to do right now, one this week, one within a month.

Coaching results can be saved to ~/vibe-sunsang/exports/mentor-YYYY-MM-DD.md.

Delegates analysis to a dedicated growth-analyst subagent to keep the main context lean. The agent reads your session files, scores all six dimensions, and writes a full report.

Time range options:

Report includes:

1. Basic stats — session count, message count, token usage
2. 6-axis technical dimension analysis with scores and weights
3. Text radar chart
4. Gate condition status table (requirements to reach the next level)
5. Antipattern detection (calibrated to your workspace type)
6. Longitudinal comparison against all previous reports
7. Level card with progression bar
8. Level-up message if you advanced (L4→L5 gets a special "80% wall" event)
9. TIMELINE.md auto-update

Answers questions about the vibe-sunsang framework itself:

Analysis weights differ by what you are actually doing:

Levels are scored to two decimal places internally, then rounded to 0.5 increments for display. The criterion is not "can you do this" but "do you do this consistently."

Every Friday (15 min)

1. /vibe-sunsang 변환 ← convert this week's sessions
2. 멘토링해줘 ← weekly review
3. Pick one thing to try next week

Monthly (30 min)

1. /vibe-sunsang 변환 force ← full re-convert
2. 성장 리포트 만들어줘 ← monthly growth report
3. Compare with previous reports — trends are shown automatically

All user data lives in ~/vibe-sunsang/. Plugin code lives separately.

~/vibe-sunsang/
├── CLAUDE.md ← workspace description (created by onboarding)
├── .gitignore
├── config/ ← project name map, workspace type classifications
├── conversations/ ← converted Markdown sessions
│ └── INDEX.md ← full project index
├── exports/ ← growth reports, mentor session saves
└── growth-log/
 ├── TIMELINE.md ← level and 6-axis history across all reports
 └── weekly/ ← weekly retrospective notes

• Claude Code CLI
• Python 3.8+

By default vibe-sunsang reads sessions from ~/.claude/projects/. The resolution order:

1. --projects-dir <path> flag (passed to convert_sessions.py)
2. $CLAUDE_CONFIG_DIR/projects if CLAUDE_CONFIG_DIR env var is set
3. ~/.claude/projects/ (default)
4. WSL fallback: /mnt/c/Users/$USER/.claude/projects (only if 1–3 don't resolve)

Use --projects-dir when running across environments (e.g., WSL ↔ Windows) or when your Claude config lives outside ~/.claude/:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/convert_sessions.py \
 --projects-dir /custom/path/.claude/projects \
 --output-dir "$HOME/vibe-sunsang/conversations"

MIT