Skip to content
skillterm

← use cases · runtime

Running the generator on Codex instead of Claude Code

Switch the headless agent runtime from Claude Code to Codex with a single config value.

Who it's for

Teams standardised on a different agent runtime, or anyone who wants to compare generation quality across runtimes.

The problem

skillterm should not lock you to one agent vendor. The generator logic is runtime-agnostic; only the binary that does the reasoning changes.

How skillterm does it

  1. 1

    Install the alternative runtime (npm install -g @openai/codex).

  2. 2

    Set runtime = "codex" in ~/.skillterm/config.toml, with its binary path, model, and timeout.

  3. 3

    Run skillterm generate as usual, or override per-invocation with the provider flag.

  4. 4

    The SKILL.md format and the Tab-time behaviour are identical regardless of which runtime wrote the file.

The outcome

The same skill-generation workflow on a different agent runtime — configuration, not a fork.