jeo

Installation
Summary

Unified AI agent orchestration with planning, execution, verification, and cleanup across Claude, Codex, Gemini, and OpenCode.

  • Four-phase workflow: PLAN (ralph + plannotator) → EXECUTE (team/bmad) → VERIFY (agent-browser + optional agentation) → CLEANUP (worktree management)
  • Supports Claude Code team mode for parallel multi-agent execution; falls back to BMAD for Codex, Gemini, and OpenCode
  • Persistent state tracking via .omc/state/jeo-state.json with checkpoint-based resume on restart and error recovery
  • Optional UI feedback loop with agentation when annotate keyword is used; auto-starts agentation-mcp server and injects component if needed
SKILL.md

JEO — Integrated Agent Orchestration

Keyword: jeo · annotate · UI-review · agentui (deprecated) | Platforms: Claude Code · Codex CLI · Gemini CLI · OpenCode

A unified skill providing fully automated orchestration flow: Plan (ralph+plannotator) → Execute (team/bmad) → UI Feedback (agentation/annotate) → Cleanup (worktree cleanup)

Control Layers

JEO uses one cross-platform abstraction for orchestration:

  • settings: platform/runtime configuration such as Claude hooks, Codex config.toml, Gemini settings.json, MCP registration, and prompt parameters
  • rules: policy constraints that must hold on every platform
  • hooks: event callbacks that enforce those rules on each platform

The key JEO rules are:

  • do not reopen the PLAN gate when the current plan hash already has a terminal result
Related skills

More from supercent-io/skills-template

Installs
10.4K
GitHub Stars
88
First Seen
Feb 25, 2026