Codex Local
The codex_local adapter runs OpenAI's Codex CLI locally. It supports session persistence via previous_response_id chaining and skills injection through the global Codex skills directory.
Prerequisites
- Codex CLI installed (
codexcommand available) OPENAI_API_KEYset in the environment or agent config
Configuration Fields
| Field | Type | Required | Description |
|---|---|---|---|
cwd | string | Yes | Working directory for the agent process (absolute path; created automatically if missing when permissions allow) |
model | string | No | Model to use |
instructionsFilePath | string | No | Absolute path to the bundle entry file Baton prepends to the prompt |
promptTemplate | string | No | Prompt used for all runs |
env | object | No | Environment variables (supports secret refs) |
timeoutSec | number | No | Process timeout (0 = no timeout) |
graceSec | number | No | Grace period before force-kill |
dangerouslyBypassApprovalsAndSandbox | boolean | No | Skip safety checks (dev only) |
Session Persistence
Codex uses previous_response_id for session continuity. The adapter serializes and restores this across heartbeats, allowing the agent to maintain conversation context.
Skills Injection
The adapter symlinks Baton skills into the global Codex skills directory (~/.codex/skills). Existing user skills are not overwritten.
Instructions And Project Context
Codex local receives:
- the agent bundle entry file from
instructionsFilePath - any composed project instructions Baton generates from project conventions
This keeps long-lived role behavior and project-specific context separate while still presenting one effective runtime prompt.
Environment Test
The environment test checks:
- Codex CLI is installed and accessible
- Working directory is absolute and available (auto-created if missing and permitted)
- Authentication signal (
OPENAI_API_KEYpresence) - A live hello probe (
codex exec --json -with promptRespond with hello.) to verify the CLI can actually run