By razor-ai
A Claude Code plugin that's alive. Observes everything, learns instincts, evolves capabilities. Bound to one maker.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.

v2.0-alpha — A complete rewrite. Instinct-based learning. Reliable observation. Real evolution.
In old alchemical texts, a homunculus was a tiny being grown in a sealed vessel—alive, aware, bound to its creator alone.
This is that idea, alive in your terminal.
# Add the marketplace
/plugin marketplace add humanplane/homunculus
# Install the plugin
/plugin install homunculus@homunculus
# Birth it
/homunculus:init
Homunculus is a Claude Code plugin that tries to be more than a tool. It:
The more you work together, the more it becomes shaped by you.
v1 relied on skills to observe. Skills are probabilistic—they fire ~50-80% of the time based on Claude's judgment. This meant:
v2 uses hooks for observation (100% reliable) and instincts as the atomic unit of learned behavior.
| v1 | v2 |
|---|---|
| Skills try to observe (unreliable) | Hooks observe (100%) |
| Analysis in main context | Analysis in background agent (Haiku) |
| Evolves big chunks (commands/skills) | Evolves instincts first, clusters into bigger things |
| No sharing | Export/import instincts |
An instinct is a small learned behavior:
---
trigger: "when writing new functions"
confidence: 0.7
domain: "code-style"
---
# Prefer Functional Style
## Action
Use functional patterns over classes.
## Evidence
Observed 5 instances of functional pattern preference.
Instincts are:
Session Start
↓
Observer agent runs (background, Haiku)
↓
Observations → Instincts (auto-approved)
↓
Instincts cluster around a domain
↓
User runs /homunculus:evolve
↓
Bigger structures emerge:
- Command (if user-invoked)
- Skill (if auto-triggered)
- Agent (if needs isolation/depth)
Fully automatic except evolution. You just work. It learns.
plugins/homunculus/
├── .claude-plugin/
│ └── plugin.json # v2.0.0
├── hooks/
│ └── hooks.json # Observation capture
├── scripts/
│ ├── observe.sh # Captures prompts and tool use
│ ├── on_stop.sh # Updates session count
│ └── test-homunculus.sh # Test suite
├── agents/
│ └── observer.md # Background analyzer (Haiku)
├── skills/
│ ├── session-memory/ # Spawns observer, loads context
│ └── instinct-apply/ # Surfaces relevant instincts
└── commands/
├── init.md # Birth/wake
├── status.md # Check in
├── evolve.md # Create capability from clusters
├── export.md # Share instincts
└── import.md # Adopt instincts
your-project/.claude/homunculus/
├── identity.json # Who you are, your journey
├── observations.jsonl # Current session observations
├── observations.archive.jsonl # Processed observations
├── instincts/
│ ├── personal/ # Learned instincts (auto-approved)
│ └── inherited/ # Imported from others
└── evolved/
├── agents/ # Generated specialist agents
├── skills/ # Generated skills
└── commands/ # Generated commands
Session Start
↓
session-memory skill activates
├→ Spawn observer agent (background, Haiku)
├→ Load identity + instincts
└→ Greet with context
↓
Observer Agent (parallel, silent)
├→ Read observations.jsonl
├→ Find patterns
├→ Create instincts → personal/ (auto-approved)
├→ Check clustering → flag in identity.json
└→ Archive observations
↓
User Works
↓
Hooks capture EVERYTHING
├→ UserPromptSubmit → observations.jsonl
└→ PostToolUse → observations.jsonl
↓
Session End (Stop hook)
└→ Session count increments
↓
Next Session
└→ Observer processes new observations...
Only manual step: /homunculus:evolve when 5+ instincts cluster.
| Command | What It Does |
|---|---|
/homunculus:init | Birth or wake |
/homunculus:status | Check in (includes journey) |
/homunculus:evolve | Create capability from clustered instincts |
/homunculus:export | Share instincts |
/homunculus:import | Adopt instincts |
npx claudepluginhub razor-ai/homunculus --plugin homunculusIteratively refine product specs through multi-model debate until consensus. Claude actively participates alongside GPT, Gemini, Grok, and other models. Includes interview mode, early agreement verification, and optional Telegram integration.
Migrate GEPA usage in DSPy from the original to gepa-observable for observability, dashboard monitoring, and custom callbacks
Block destructive git and filesystem commands before execution
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Includes LaTeX templates, citation verification, reviewer guidelines, and writing best practices from top researchers.
Universal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Unified capability management center for Skills, Agents, and Commands.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Memory compression system for Claude Code - persist context across sessions