From superpowers
Ask Codex CLI (gpt-5.6-sol with high reasoning) to run local app verification that needs computer use, browser automation, simulators, screenshots, app launching, or independent runtime inspection. This is how gpt-5.6-sol is invoked for computer-use work. Use when the user asks Claude to have Codex or gpt-5.6-sol test a flow, verify UI behavior, inspect a running app, capture screenshots, or report confirmation and feedback about implemented behavior.
How this skill is triggered — by the user, by Claude, or both
Slash command
/superpowers:codex-computer-useThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use Codex as a separate local verification agent when the task needs real UI
Use Codex as a separate local verification agent when the task needs real UI interaction, screenshots, simulator/browser/device state, or an independent runtime check outside of Claude's current context.
Do not use this for ordinary code reading, type-checking, linting, or tests Claude can run directly. Launching apps, simulators, or browsers to verify the requested work is fine without asking; ask first only if the run could disrupt the user's environment beyond that (closing their apps, changing system settings, acting on real accounts or data).
codex exec non-interactivelyUse this command shape:
ARTIFACT_DIR="$(mktemp -d "${TMPDIR:-/tmp}/codex-computer-use.XXXXXX")"
REPORT="$ARTIFACT_DIR/report.md"
PROMPT="$ARTIFACT_DIR/prompt.md"
# Write a self-contained prompt to $PROMPT, then run:
codex exec \
-m gpt-5.6-sol \
-c 'model_reasoning_effort="high"' \
-C "$PWD" \
--add-dir "$ARTIFACT_DIR" \
-s danger-full-access \
-o "$REPORT" \
"$(cat "$PROMPT")"
Use -s danger-full-access for GUI automation, desktop app launching, screenshots, or access outside the repo. For non-GUI checks that only need the repo and artifact directory, prefer -s workspace-write. Add --skip-git-repo-check when the working directory is not a git repository.
Tell Codex:
Keep the prompt specific enough that Codex does not need the surrounding Claude conversation.
npx claudepluginhub phiyerion/claude-superpowers --plugin superpowersCreates, edits, and verifies skills using a test-driven development approach with pressure scenarios and subagents.