akiiwa-games/AgentCompass / skills/chatgpt-pro-consult
chatgpt-pro-consult
FlaggedCarry out a agent-compass-authorized Pro consultation or plan critique through the isolated codex-chatgpt-web Browser-only bridge, with recorded submission and complete answer capture. Use for GPT Pro or 6pro reasoning queries; return advice, not execution or approval.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.0 KB |
| agents/openai.yaml | config | 416 B |
| references/browser-workflow.md | markdown | 14.4 KB |
| references/consult-bridge.md | markdown | 5.8 KB |
| scripts/browser_surface_preflight.mjs | script | 3.7 KB |
| scripts/build_consult_packet.py | script | 9.1 KB |
| scripts/check_consult_state.py | script | 6.5 KB |
| scripts/consult_bridge.py | script | 12.2 KB |
| scripts/launch_cua_mcp.py | script | 1.8 KB |
| scripts/test_consult_bridge.py | script | 5.7 KB |
scripts/launch_cua_mcp.py
View on GitHub"""Expose the installed desktop CUA runtime to another Codex host.
Read the app-generated manifest on every launch so desktop upgrades and pipe
changes do not leave copied runtime paths in that host's config.
This launches the existing MCP server; it does not implement browser control.
"""
import argparse
import json
import os
from pathlib import Path
import subprocess
import sys
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--desktop-home', type=Path, required=True)
parser.add_argument('--check', action='store_true')
args = parser.parse_args()
root = args.desktop_home / 'plugins/cache/openai-bundled/unified-computer-use'
candidates = list(root.glob('*/.mcp.json'))
if not candidates:
raise RuntimeError('Desktop CUA manifest is missing; open/update Codex desktop.')
manifest = max(candidates, key=lambda p: p.stat().st_mtime_ns)
server = json.loads(manifest.read_text(encoding='utf-8'))['mcpServers']['cua_repl']
command = [server['command'], *server.get('args', [])]
for item in command[:2]:
if not Path(item).is_file():
raise RuntimeError('Desktop CUA executable or entrypoint is missing.')
if args.check:
print(json.dumps({'manifest': str(manifest), 'runtime_exists': True,
'surfaces': server.get('env', {}).get('CUA_REPL_ENABLED_SURFACES') }))
return 0
env = os.environ.copy()
env.update(server.get('env', {}))
child = subprocess.Popen(command, env=env)
try:
return child.wait()
except KeyboardInterrupt:
child.terminate()
return child.wait()
if __name__ == '__main__':
try:
sys.exit(main())
except (OSError, KeyError, ValueError, RuntimeError) as exc:
print(f'CUA launcher: {exc}', file=sys.stderr)
sys.exit(1)
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: 472k | 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 |