Stats
Actions
Tags
From claude-forge
Observes Claude Code sessions via hooks to create atomic instincts with confidence scoring, then evolves them into reusable skills, commands, or agents.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-forge:continuous-learning-v2The summary Claude sees in its skill listing — used to decide when to auto-load this skill
An advanced learning system that turns your Claude Code sessions into reusable knowledge through atomic "instincts" - small learned behaviors with confidence scoring.
An advanced learning system that turns your Claude Code sessions into reusable knowledge through atomic "instincts" - small learned behaviors with confidence scoring.
| 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 |
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:
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 │
└─────────────────────────────────────────┘
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"
}]
}]
}
}
mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,skills,commands}}
touch ~/.claude/homunculus/observations.jsonl
The observer can run in the background analyzing observations:
# Start background observer
~/.claude/skills/continuous-learning-v2/agents/start-observer.sh
| 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 |
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/"
}
}
~/.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
When you use the Skill Creator GitHub App, it now generates both:
Instincts from repo analysis have source: "repo-analysis" and include the source repository URL.
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:
Confidence decreases when:
"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:
v2 is fully compatible with v1:
~/.claude/skills/learned/ skills still workInstinct-based learning: teaching Claude your patterns, one observation at a time.
npx claudepluginhub sangrokjung/claude-forge --plugin claude-forgeObserves Claude Code sessions via hooks to create atomic instincts with confidence scoring, then evolves them into reusable skills, commands, or agents.
Observes Claude Code sessions to extract atomic 'instincts' (behaviors with confidence scoring), evolving them into reusable skills/commands/agents. Adds project-scoped instincts in v2.1 to prevent cross-project contamination.
Creates bite-sized, testable implementation plans from specs or requirements, with file structure and task decomposition. Activates before coding multi-step tasks.