Yeachan-Heo

Full autonomous execution from idea to working code

N coordinated agents on shared task list using Claude Code implicit agent teams

Diagnose and fix oh-my-claudecode installation issues

Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow

Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery

Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state

Carry an approved task through to working, verified code

Configure HUD display options (layout, presets, display elements)

Diagnose and fix oh-my-codex installation issues

Setup and configure oh-my-codex using current CLI behavior

N coordinated agents on shared task list using tmux-based orchestration

Consensus planning stage for Planner -> Architect -> Critic handoff to $ultragoal

[OMX] Canonical autonomous orchestrator: $deep-interview -> $ralplan -> $ultragoal

Socratic deep interview with mathematical ambiguity gating before execution

Run an anti-slop cleanup/refactor/deslop workflow

Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference boundaries. Use when a user says 'analyze', 'investigate', 'why does', 'what's causing', or needs grounded…

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

Goal-directed research missions that interleave web research with data experimentation and end on a structured best-effort verdict

Consensus planning entrypoint that auto-gates vague ultragoal requests before execution

Create and execute durable repo-native multi-goal plans over GJC goal mode artifacts.

Delegate planning and execution workflows to gajae-code via the coordinator MCP server.

Author trusted-local TypeScript and Python scripts that operate GJC sessions through the broker-bound CLI.

Operate trusted local GJC sessions through a reviewed broker-bound CLI allowlist with single-use human approval.

Index of trusted GJC SDK reference guides (broker, session CLI, embedding, app development). Advisory only: read these documents for background; there is no guide to execute and no workflow skill to run.

Patterns for data loading, exploration, and statistical analysis

Best practices for designing reproducible experiments

Enforces baseline comparisons, cross-validation, interpretation, and leakage prevention for ML pipelines

Patterns for data loading, exploration, and statistical analysis

Best practices for designing reproducible experiments

Enforces baseline comparisons, cross-validation, interpretation, and leakage prevention for ML pipelines