tjl8787/mycodex-skills / skills/multi-codex-orchestration
multi-codex-orchestration
VerifiedUse when the user explicitly wants multiple Codex agents or a virtual team, the work can be decomposed into safe parallel roles, and tgtool should coordinate a Ruflo-backed orchestration path.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.8 KB |
| scripts/bootstrap_ruflo_backend.pyexecutable | script | 3.4 KB |
| scripts/build_claude_flow_payload.pyexecutable | script | 1.4 KB |
| scripts/ensure_ruflo_init.pyexecutable | script | 2.7 KB |
| scripts/launch_explicit_tmux.pyexecutable | script | 3.6 KB |
| scripts/normalize_claude_flow_result.pyexecutable | script | 1.1 KB |
| scripts/probe_ruflo_execution.py | script | 4.6 KB |
| templates/claude-flow-result-example.json | config | 431 B |
scripts/ensure_ruflo_init.py
View on GitHub#!/usr/bin/env python3
import argparse
import json
import subprocess
import sys
from pathlib import Path
def detect_state(project_dir: Path) -> dict:
codex_initialized = (
(project_dir / 'AGENTS.md').exists()
and (project_dir / '.agents' / 'config.toml').exists()
)
runtime_initialized = (project_dir / '.claude-flow' / 'config.yaml').exists()
return {
'project_dir': str(project_dir),
'codex_initialized': codex_initialized,
'runtime_initialized': runtime_initialized,
}
def command_for_target(target: str) -> list[str]:
if target == 'codex':
return ['ruflo', 'init', '--codex']
if target == 'runtime':
return ['ruflo', 'init', '--minimal', '--force']
raise ValueError(f'unsupported target: {target}')
def recommend_target(state: dict) -> str:
if not state['codex_initialized']:
return 'codex'
if not state['runtime_initialized']:
return 'runtime'
return 'none'
def run_command(project_dir: Path, cmd: list[str]) -> int:
shell_cmd = (
'source /home/jetio/.nvm/nvm.sh '
'&& nvm use 20 >/dev/null '
f"&& cd {project_dir} && {' '.join(cmd)}"
)
return subprocess.run(['/bin/bash', '-lc', shell_cmd]).returncode
def main() -> int:
parser = argparse.ArgumentParser(
description='Check or initialize Ruflo integration/runtime for a project.'
)
parser.add_argument('--project-dir', default='.')
parser.add_argument(
'--target',
choices=['auto', 'codex', 'runtime'],
default='auto',
help='codex = AGENTS/.agents integration, runtime = .claude-flow runtime',
)
parser.add_argument('--execute', action='store_true')
args = parser.parse_args()
project_dir = Path(args.project_dir).resolve()
state = detect_state(project_dir)
target = args.target
if target == 'auto':
target = recommend_target(state)
result = {
**state,
'requested_target': args.target,
'selected_target': target,
'action_needed': target != 'none',
'recommended_command': None,
'executed': False,
'exit_code': 0,
}
if target != 'none':
cmd = command_for_target(target)
result['recommended_command'] = (
'source /home/jetio/.nvm/nvm.sh && nvm use 20 >/dev/null && cd '
+ str(project_dir)
+ ' && '
+ ' '.join(cmd)
)
if args.execute:
result['executed'] = True
result['exit_code'] = run_command(project_dir, cmd)
print(json.dumps(result, indent=2, sort_keys=True))
return int(result['exit_code'])
if __name__ == '__main__':
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |