sangrokjung/continuous-learning-v2

Continuous Learning v2 - Instinct-Based Architecture

An advanced learning system that turns your Claude Code sessions into reusable knowledge through atomic "instincts" - small learned behaviors with confidence scoring.

What's New in v2

| Feature | v1 | v2 | |---------|----|----| | Observation | Stop hook (session end) | PreToolUse/PostToolUse (100% reliable) | | Analysis | Main context | Background agent (Haiku) | | Granularity | Full skills | Atomic "instincts" | | Confidence | None | 0.3-0.9 weighted | | Evolution | Direct to skill | Instincts → cluster → skill/command/agent | | Sharing | None | Export/import instincts |

The Instinct Model

An instinct is a small learned behavior:

---
id: prefer-functional-style
trigger: "when writing new functions"
confidence: 0.7
domain: "code-style"
source: "session-observation"
---

# Prefer Functional Style

## Action
Use functional patterns over classes when appropriate.

## Evidence
- Observed 5 instances of functional pattern preference
- User corrected class-based approach to functional on 2025-01-15

Properties:

• Atomic — one trigger, one action
• Confidence-weighted — 0.3 = tentative, 0.9 = near certain
• Domain-tagged — code-style, testing, git, debugging, workflow, etc.
• Evidence-backed — tracks what observations created it

How It Works

Session Activity
      │
      │ Hooks capture prompts + tool use (100% reliable)
      ▼
┌─────────────────────────────────────────┐
│         observations.jsonl              │
│   (prompts, tool calls, outcomes)       │
└─────────────────────────────────────────┘
      │
      │ Observer agent reads (background, Haiku)
      ▼
┌─────────────────────────────────────────┐
│          PATTERN DETECTION              │
│   • User corrections → instinct         │
│   • Error resolutions → instinct        │
│   • Repeated workflows → instinct       │
└─────────────────────────────────────────┘
      │
      │ Creates/updates
      ▼
┌─────────────────────────────────────────┐
│         instincts/personal/             │
│   • prefer-functional.md (0.7)          │
│   • always-test-first.md (0.9)          │
│   • use-zod-validation.md (0.6)         │
└─────────────────────────────────────────┘
      │
      │ /evolve clusters
      ▼
┌─────────────────────────────────────────┐
│              evolved/                   │
│   • commands/new-feature.md             │
│   • skills/testing-workflow.md          │
│   • agents/refactor-specialist.md       │
└─────────────────────────────────────────┘

Quick Start

1. Enable Observation Hooks

Add to your ~/.claude/settings.json:

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh pre"
      }]
    }],
    "PostToolUse": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh post"
      }]
    }]
  }
}

2. Initialize Directory Structure

mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,skills,commands}}
touch ~/.claude/homunculus/observations.jsonl

3. Run the Observer Agent (Optional)

The observer can run in the background analyzing observations:

# Start background observer
~/.claude/skills/continuous-learning-v2/agents/start-observer.sh

Commands

| Command | Description | |---------|-------------| | /instinct-status | Show all learned instincts with confidence | | /evolve | Cluster related instincts into skills/commands | | /instinct-export | Export instincts for sharing | | /instinct-import <file> | Import instincts from others |

Configuration

Edit config.json:

{
  "version": "2.0",
  "observation": {
    "enabled": true,
    "store_path": "~/.claude/homunculus/observations.jsonl",
    "max_file_size_mb": 10,
    "archive_after_days": 7
  },
  "instincts": {
    "personal_path": "~/.claude/homunculus/instincts/personal/",
    "inherited_path": "~/.claude/homunculus/instincts/inherited/",
    "min_confidence": 0.3,
    "auto_approve_threshold": 0.7,
    "confidence_decay_rate": 0.05
  },
  "observer": {
    "enabled": true,
    "model": "haiku",
    "run_interval_minutes": 5,
    "patterns_to_detect": [
      "user_corrections",
      "error_resolutions",
      "repeated_workflows",
      "tool_preferences"
    ]
  },
  "evolution": {
    "cluster_threshold": 3,
    "evolved_path": "~/.claude/homunculus/evolved/"
  }
}

File Structure

~/.claude/homunculus/
├── identity.json           # Your profile, technical level
├── observations.jsonl      # Current session observations
├── observations.archive/   # Processed observations
├── instincts/
│   ├── personal/           # Auto-learned instincts
│   └── inherited/          # Imported from others
└── evolved/
    ├── agents/             # Generated specialist agents
    ├── skills/             # Generated skills
    └── commands/           # Generated commands

Integration with Skill Creator

When you use the Skill Creator GitHub App, it now generates both:

• Traditional SKILL.md files (for backward compatibility)
• Instinct collections (for v2 learning system)

Instincts from repo analysis have source: "repo-analysis" and include the source repository URL.

Confidence Scoring

Confidence evolves over time:

| Score | Meaning | Behavior | |-------|---------|----------| | 0.3 | Tentative | Suggested but not enforced | | 0.5 | Moderate | Applied when relevant | | 0.7 | Strong | Auto-approved for application | | 0.9 | Near-certain | Core behavior |

Confidence increases when:

• Pattern is repeatedly observed
• User doesn't correct the suggested behavior
• Similar instincts from other sources agree

Confidence decreases when:

• User explicitly corrects the behavior
• Pattern isn't observed for extended periods
• Contradicting evidence appears

Why Hooks vs Skills for Observation?

"v1 relied on skills to observe. Skills are probabilistic—they fire ~50-80% of the time based on Claude's judgment."

Hooks fire 100% of the time, deterministically. This means:

• Every tool call is observed
• No patterns are missed
• Learning is comprehensive

Backward Compatibility

v2 is fully compatible with v1:

• Existing ~/.claude/skills/learned/ skills still work
• Stop hook still runs (but now also feeds into v2)
• Gradual migration path: run both in parallel

Privacy

• Observations stay local on your machine
• Only instincts (patterns) can be exported
• No actual code or conversation content is shared
• You control what gets exported

Agent Memory Integration

continuous-learning-v2의 instinct 시스템은 에이전트의 Self-Evolution Protocol과 상호보완적으로 동작한다.

관계도

Continuous Learning v2 (세션 관찰 기반)
  └─ observations.jsonl → instincts/personal/ → evolved/
        ↕ 상호 참조
Agent Self-Evolution (작업 완료 기반)
  └─ 에이전트 작업 결과 → ~/.claude/agent-memory/{agent-name}/

차이점

| 차원 | Continuous Learning v2 | Agent Self-Evolution | |------|----------------------|---------------------| | 트리거 | 세션 관찰 (hooks) | 에이전트 작업 완료 | | 저장소 | ~/.claude/homunculus/instincts/ | ~/.claude/agent-memory/ | | 형태 | 원자적 instinct (trigger + action) | Learnings 리스트 (발견/개선) | | 대상 | 전체 (범용) | 개별 에이전트 | | 자동화 | Hook → Observer → Instinct (자동) | 에이전트 작업 완료 후 자체 기록 |

통합 사용 시나리오

1. 세션 중: continuous-learning-v2 hooks가 관찰 데이터 수집
2. 에이전트 작업 후: 에이전트가 Self-Evolution으로 자체 memory 업데이트
3. 세션 종료: /session-wrap이 양쪽 데이터를 종합하여 정리
4. 다음 세션 시작: /sync로 프로젝트 문서 동기화

Related

• Skill Creator - Generate instincts from repo history
• Homunculus - Inspiration for v2 architecture
• The Longform Guide - Continuous learning section

---

Instinct-based learning: teaching Claude your patterns, one observation at a time.