# codex-job-orchestrator

> codex-job-orchestrator — awslew-codex-job-orchestrator. Use this tool when you need to run long-running tasks in the background, turning brief MCP calls into hours-long jobs. It solves the problem of managing asynchronous tasks, allowing for unattended execution of AI coding agents on Windows. The tool accepts MCP calls as input and outputs a managed job that can run for an extended period, ideal for use cases requiring prolonged processing without blocking main threads.

Canonical page: https://skillsregistry.net/skills/awslew-codex-job-orchestrator  
JSON: https://api.skillsregistry.net/v1/skills/awslew-codex-job-orchestrator

## Description

想省 Codex 主会话额度？方案与验收留给主 agent，简单执行和复杂推理走合适的 agent 路径；Claude Code/DSH 长作业可后台运行。 Route work by role to save Codex quota.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-25

## Source

- **Source listing:** [GitHub](https://github.com/awslew/codex-job-orchestrator)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "awslew-codex-job-orchestrator"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/awslew-codex-job-orchestrator` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/awslew-codex-job-orchestrator/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt