Py Code Agent OMO
Oh My OpenCode plugin collection for Py Code Agent. Brings multi-model orchestration, parallel sub-agents, intent classification, and discipline enforcement.
Features
| Plugin | Capability |
|---|---|
| Intent Gate | Classifies user intent (research/implementation/fix/investigation/open-ended) before execution |
| Category Router | Maps task categories to optimal models (Gemini for visual, GPT for logic, Claude for deep) |
| Sub-Agent | Parallel background agent execution with category-based model routing |
| Discipline | Ralph Loop + Todo Enforcer — prevents agent from quitting with pending work |
| Comment Checker | Prevents AI-generated excessive comments in code |
| Think Mode | Structured thinking tool for complex problems |
Installation
pip install py-code-agent-omo
Plugins are auto-discovered via entry points. No additional configuration needed.
Configuration
Create ~/.config/py-code-agent/omo.yaml to customize model assignments:
category_router:
categories:
visual-engineering:
model: "google/gemini-3.1-pro"
variant: "high"
ultrabrain:
model: "openai/gpt-5.4"
variant: "xhigh"
quick:
model: "openai/gpt-5.4-mini"
See omo.yaml.example for the full configuration reference.
Tools Provided
| Tool | Plugin | Description |
|---|---|---|
classify_intent |
Intent Gate | Classify task intent |
route_task |
Category Router | Resolve category → model |
list_categories |
Category Router | List available categories |
set_category_model |
Category Router | Override category model |
task |
Sub-Agent | Delegate to background agent |
background_output |
Sub-Agent | Get background task output |
background_cancel |
Sub-Agent | Cancel running task |
background_list |
Sub-Agent | List all background tasks |
check_todos |
Discipline | Check pending todo count |
enforce_continuation |
Discipline | Force continuation |
check_comment_ratio |
Comment Checker | Scan file comment ratio |
ultrathink |
Think Mode | Structured problem analysis |
Usage
# Delegate to a visual engineering sub-agent
task(category="visual-engineering", description="Redesign sidebar", prompt="...", run_in_background=True)
# Run a quick fix synchronously
task(category="quick", description="Fix typo in auth.py", prompt="...", run_in_background=False)
# Collect results
background_output(task_id="bg_abc123")
# Structured thinking for complex decisions
ultrathink(problem="Should we migrate from SQLite to Postgres?")
Requirements
- Python 3.10+
- Py Code Agent 0.1.0+
- PyYAML 6.0+
- Pydantic 2.0+
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for py-code-agent-omo 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| py_code_agent_omo-0.1.0.tar.gz | 14.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| py_code_agent_omo-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 34.8 kB
Release files / py_code_agent_omo-0.1.0.tar.gz
| Download URL | py_code_agent_omo-0.1.0.tar.gz |
|---|---|
| Size | 14.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bf1bccde43bf6fe3ed6be5e7ce4995fcbb02c5b0a87d46052ab7a9644e5e8f50
|
|
BLAKE2b-256 checksum How to use checksums |
b78243de233b8f1825655670eba044c52b817ac9c477efc66be17e2ab196b1ac
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.5
|
Release files / py_code_agent_omo-0.1.0-py3-none-any.whl
| Download URL | py_code_agent_omo-0.1.0-py3-none-any.whl |
|---|---|
| Size | 20.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
59ab599e04e8381c6d7cdad6535c7271b4738b0b98d08258387a5254fc910da5
|
|
BLAKE2b-256 checksum How to use checksums |
07286fec64a2d42ce9ecc19a241e80485eb1888cd1e4995e818bc57235a16e92
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.5
|
