# Continuous Learning V2

Instinct-based learning system that observes sessions via hooks, creates atomic...

- Repository: https://github.com/sangrokjung/claude-forge (868 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-09-03
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add sangrokjung/claude-forge --skill continuous-learning-v2 -g -a claude-code -y`
Codex: `npx skills add sangrokjung/claude-forge --skill continuous-learning-v2 -g -a codex -y`
Cursor: `npx skills add sangrokjung/claude-forge --skill continuous-learning-v2 -g -a cursor -y`
Gemini CLI: `npx skills add sangrokjung/claude-forge --skill continuous-learning-v2 -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add sangrokjung/claude-forge`

## Description

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# 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:

```yaml
---
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

The rest: https://github.com/sangrokjung/claude-forge/blob/HEAD/skills/continuous-learning-v2/SKILL.md