ClaudeSuperPower

codex-exec

Skill

Run one caller-supplied Codex command non-interactively and capture evidence. Triggers: "run Codex headless", "capture Codex evidence".

Install

git clone https://github.com/boshu2/agentops.git ~/.claude/skills/codex-exec

What is codex-exec?

Run one caller-supplied Codex command non-interactively and capture evidence. Triggers: "run Codex headless", "capture Codex evidence".

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Inherit all session tools

Declares no tool restrictions — inherits every session tool

~34 tokens of context used while enabled, before you invoke anything

Documentation

README · ~3 min read

Codex Exec — one-shot runtime adapter

Run exactly one caller-supplied Codex prompt and capture its result. This skill does not choose work, retry failures, validate by itself, or control continuation.

One prompt, one process, one captured artifact is what makes the run auditable: when nothing loops, every byte of output traces to exactly one invocation, and a disagreement about what happened is settled by the artifact.

Named failure mode — stdin hang: a non-TTY run left waiting forever on an open stdin nobody will write to; always pipe the prompt or close the stream.

Anti-pattern: granting workspace-write or network access "in case the prompt needs it". Corrective: match the sandbox to the declared effects; a review

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.