Continuous Learning - Instinct-Based Architecture

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

Features project-scoped instincts — React patterns stay in your React project, Python conventions stay in your Python project, and universal patterns (like "always validate input") are shared globally.

When to Activate

Setting up automatic learning from Codex sessions
Configuring instinct-based behavior extraction via hooks
Tuning confidence thresholds for learned behaviors
Reviewing, exporting, or importing instinct libraries
Evolving instincts into full skills, commands, or agents
Managing project-scoped vs global instincts
Promoting instincts from project to global scope

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"
scope: project
project_id: "a1b2c3d4e5f6"
project_name: "my-react-app"
---

# 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
Scope-aware -- project (default) or global

How It Works

Session Activity (in a git repo)
      |
      | Hooks capture prompts + tool use (100% reliable)
      | + detect project context (git remote / repo path)
      v
+---------------------------------------------+
|  projects/<project-hash>/observations.jsonl |
|   (prompts, tool calls, outcomes, project)  |
+---------------------------------------------+
      |
      | Observer agent reads (background)
      v
+---------------------------------------------+
|          PATTERN DETECTION                  |
|   * User corrections -> instinct            |
|   * Error resolutions -> instinct           |
|   * Repeated workflows -> instinct          |
|   * Scope decision: project or global?      |
+---------------------------------------------+
      |
      | Creates/updates
      v
+---------------------------------------------+
|  projects/<project-hash>/instincts/personal/|
|   * prefer-functional.yaml (0.7) [project]  |
|   * use-react-hooks.yaml (0.9) [project]    |
+---------------------------------------------+
|  instincts/personal/  (GLOBAL)              |
|   * always-validate-input.yaml (0.85)[global|
|   * grep-before-edit.yaml (0.6) [global]    |
+---------------------------------------------+
      |
      | /evolve clusters + /promote
      v
+---------------------------------------------+
|  projects/<hash>/evolved/ (project-scoped)  |
|  evolved/ (global)                          |
|   * commands/new-feature.md                 |
|   * skills/testing-workflow.md              |
|   * agents/refactor-specialist.md           |
+---------------------------------------------+

Project Detection

The system automatically detects your current project:

CODEX_PLUGIN_PROJECT_DIR env var (highest priority)
git remote get-url origin -- hashed to create a portable project ID (same repo on different machines gets the same ID)
git rev-parse --show-toplevel -- fallback using repo path (machine-specific)
Global fallback -- if no project is detected, instincts go to global scope

Each project gets a 12-character hash ID (e.g., a1b2c3d4e5f6). A registry file at ~/.codex/codex-plugin/continuous-learning/projects.json maps IDs to human-readable names.

Quick Start

1. Enable Observation Hooks

The continuous learning observation hooks are bundled as part of the plugin in the hooks/hooks.json file. When the plugin is installed and trusted, Codex can run them on PreToolUse and PostToolUse.

2. Initialize Directory Structure

The system creates directories automatically on first use, but you can also create them manually:

# Global directories
mkdir -p ~/.codex/codex-plugin/continuous-learning/{instincts/{personal,inherited},evolved/{agents,skills,commands},projects}

# Project directories are auto-created when the hook first runs in a git repo

3. Use the Instinct Commands

python3 scripts/instinct-cli.py status     # Show learned instincts (project + global)
python3 scripts/instinct-cli.py evolve     # Cluster related instincts into skills/commands
python3 scripts/instinct-cli.py export     # Export instincts to file
python3 scripts/instinct-cli.py import     # Import instincts from others
python3 scripts/instinct-cli.py promote    # Promote project instincts to global scope
python3 scripts/instinct-cli.py projects   # List all known projects and their instinct counts

Configuration

Configuration is managed with environment variables and Codex plugin settings. Use CODEX_PLUGIN_OBSERVER_ENABLED=true to enable observation.

Setting	Default	Description
Observer Enabled	`false`	Enable the background observer agent
Run Interval	`5`	How often the observer analyzes observations (in minutes)
Min Observations	`20`	Minimum observations before analysis runs

Other behavior (observation capture, instinct thresholds, project scoping, promotion criteria) is configured via code defaults in scripts/instinct-cli.py and hooks/observe.sh.

File Structure

~/.codex/codex-plugin/continuous-learning/
+-- identity.json           # Your profile, technical level
+-- projects.json           # Registry: project hash -> name/path/remote
+-- observations.jsonl      # Global observations (fallback)
+-- instincts/
|   +-- personal/           # Global auto-learned instincts
|   +-- inherited/          # Global imported instincts
+-- evolved/
|   +-- agents/             # Global generated agents
|   +-- skills/             # Global generated skills
|   +-- commands/           # Global generated commands
+-- projects/
    +-- a1b2c3d4e5f6/       # Project hash (from git remote URL)
    |   +-- project.json    # Per-project metadata mirror (id/name/root/remote)
    |   +-- observations.jsonl
    |   +-- observations.archive/
    |   +-- instincts/
    |   |   +-- personal/   # Project-specific auto-learned
    |   |   +-- inherited/  # Project-specific imported
    |   +-- evolved/
    |       +-- skills/
    |       +-- commands/
    |       +-- agents/
    +-- f6e5d4c3b2a1/       # Another project
        +-- ...

Scope Decision Guide

Pattern Type	Scope	Examples
Language/framework conventions	project	"Use React hooks", "Follow Django REST patterns"
File structure preferences	project	"Tests in `__tests__`/", "Components in src/components/"
Code style	project	"Use functional style", "Prefer dataclasses"
Error handling strategies	project	"Use Result type for errors"
Security practices	global	"Validate user input", "Sanitize SQL"
General best practices	global	"Write tests first", "Always handle errors"
Tool workflow preferences	global	"Grep before Edit", "Read before Write"
Git practices	global	"Conventional commits", "Small focused commits"

Instinct Promotion (Project -> Global)

When the same instinct appears in multiple projects with high confidence, it's a candidate for promotion to global scope.

Auto-promotion criteria:

Same instinct ID in 2+ projects
Average confidence >= 0.8

How to promote:

# Promote a specific instinct
python3 scripts/instinct-cli.py promote prefer-explicit-errors

# Auto-promote all qualifying instincts
python3 scripts/instinct-cli.py promote

# Preview without changes
python3 scripts/instinct-cli.py promote --dry-run

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 for Observation?

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

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

Privacy

Observations stay local on your machine
Project-scoped instincts are isolated per project
Only instincts (patterns) can be exported — not raw observations
No actual code or conversation content is shared
You control what gets exported and promoted

Instinct-based learning: teaching Codex your patterns, one project at a time.

continuous-learning

SKILL.mdskills/continuous-learning/SKILL.md