Skip to main content
OpenAI Codex extends through skills, MCP servers declared in ~/.codex/config.toml, and AGENTS.md instructions. Wire up all three in one step: 
bunx smithers-orchestrator skills add --agent codex
bunx smithers-orchestrator mcp add --agent codex
That installs the Smithers skill set into ~/.codex/skills/ and registers the MCP server in Codex’s config. Restart Codex and it can drive workflows.

​
Install the skill

Codex reads skills from ~/.codex/skills/ (global) and .agents/skills/ (project). Drop the onboarding skill in manually if you prefer: 
mkdir -p ~/.codex/skills/smithers
curl -fsSL https://raw.githubusercontent.com/smithersai/smithers/main/skills/smithers/SKILL.md \
  -o ~/.codex/skills/smithers/SKILL.md
curl -fsSL https://smithers.sh/llms-full.txt \
  -o ~/.codex/skills/smithers/llms-full.txt
Codex auto-selects a skill by its description, or you invoke it explicitly with /skills.

​
Register the MCP server

mcp add writes the entry for you. The native config is a TOML table in ~/.codex/config.toml: 
[mcp_servers.smithers]
command = "bunx"
args = ["smithers-orchestrator", "--mcp"]
Or use the Codex CLI: 
codex mcp add smithers -- bunx smithers-orchestrator --mcp
Codex launches the server at session start and the semantic tools (list_workflows, run_workflow, watch_run, resolve_approval, …) appear in the /mcp list. Full reference: MCP Server.

​
Standing instructions

Codex reads AGENTS.md from the repo root down to the working directory. Add a section so Codex knows to reach for Smithers: 
## Orchestration
Use Smithers for durable, multi-step, or human-in-the-loop agent work.
Run `bunx smithers-orchestrator starters` to see ready-made workflows,
then `bunx smithers-orchestrator workflow run <name> --prompt "…"`.
This same AGENTS.md is read by Cursor, Copilot, Hermes, and Pi; one file covers several agents.

​
Smithers runs Codex too

In the other direction, Smithers spawns Codex as a worker via CodexAgent (codex exec with a streamed JSON protocol and native thread hijack): 
import { CodexAgent } from "smithers-orchestrator";

const codex = new CodexAgent({ model: "gpt-5.5", sandbox: "workspace-write" });
See CLI Agents → Codex.