codex-comm

Bridge Codex communications to CC infrastructure with health checks and session resume.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/isaenter/UES-PRO --skill codex-comm-isaenter
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codex-comm
Source: https://github.com/isaenter/UES-PRO/tree/main/frontend-vben/.claude/skills/codex-comm
Command: npx skills add https://github.com/isaenter/UES-PRO --skill codex-comm-isaenter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Bridges Codex communications to CC infrastructure to enable deterministic, managed AI interactions across single-turn and multi-turn use cases.

Core Features & Use Cases

  • Availability checks and health monitoring to ensure Codex readiness.
  • Dual modes: exec (single-turn) and serve (multi-turn HTTP API) for flexible workflows.
  • Session resume to maintain context across turns.
  • UUID-based request tracking and concurrency-safe identifiers.
  • Sensitive data redaction to protect secrets in prompts and responses.
  • Automatic downgrade to CC-alone execution when Codex is unavailable.

Quick Start

Start a single-turn prompt with execMode or initialize the HTTP bridge with ensureServe for multi-turn sessions.

Frequently Asked Questions about codex-comm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage AI conversation sessions to maintain context across multiple turns?

AI conversation session management maintains context across turns by using a serve mode HTTP API bridge with session resume functionality. This enables deterministic, multi-turn interactions while tracking requests via UUIDs.

What is the best way to execute single-turn AI prompts deterministically?

Single-turn AI prompts execute deterministically through an exec mode that bridges communications to managed infrastructure. This approach enforces prompt filtering and availability checks before processing the request.

How does fallback handling work when the AI model becomes unavailable?

Fallback handling automatically downgrades to CC-alone execution when the AI model is unavailable. Health checks and availability monitoring detect the failure to ensure the workflow degrades safely without crashing.

Can I redact sensitive data and secrets before sending prompts to the AI model?

Sensitive data redaction protects secrets in prompts and responses by filtering content before and after AI model execution. This ensures secure usage and traceable interactions across both exec and serve modes.

Does the AI session bridge require any external dependencies to run?

The AI session bridge requires no external dependencies to run. It operates standalone using internal scripts to handle availability checks, UUID generation, and health monitoring for managed interactions.