Stats
Actions
Tags
From starter-kit
Sends a single question to Codex (OpenAI's coding model) and relays its answer, providing a quick second opinion alongside Claude. Includes privacy check and user confirmation before sending.
How this command is triggered — by the user, by Claude, or both
Slash command
/starter-kit:codex <question or request>The summary Claude sees in its command listing — used to decide when to auto-load this command
# /codex — one-shot Codex query Send the user's request to the Codex CLI and relay the answer. One question, one reply, read-only — Codex edits nothing. ## Steps 1. **Privacy check (required, every time).** Sending this question transmits its content to another AI service. If the request or any pasted content includes confidential records, personal contact details, research-participant or human-subjects data, unpublished sensitive material, or anything the user wouldn't paste into a public website — do NOT send it. Explain why in one sentence and offer either a Claude-only answer or a re...
Send the user's request to the Codex CLI and relay the answer. One question, one reply, read-only — Codex edits nothing.
Privacy check (required, every time). Sending this question transmits its content to another AI service. If the request or any pasted content includes confidential records, personal contact details, research-participant or human-subjects data, unpublished sensitive material, or anything the user wouldn't paste into a public website — do NOT send it. Explain why in one sentence and offer either a Claude-only answer or a redacted version the user approves first.
Explicit send confirmation (required, every time). If the privacy check passes, ask: "Send this prompt to Codex for a second opinion? (yes/no)" Proceed only if the user answers yes. If they answer no or do not answer clearly, stop and offer a Claude-only answer.
Check it's enabled. Read ~/.claude/starter-kit/engines.json. If the file is missing, unparseable, or codex.available is not true, print exactly this and stop:
Running on Claude only — that's the normal setup and everything here works. (Have ChatGPT or Gemini? Run /kit-setup to plug them in.)
Re-check the binary. Run command -v codex. Not found → print the same note and stop.
Make a private workspace. Run mktemp -d once and use the directory it prints (below: <rundir>) for both files. Never use predictable fixed paths like /tmp/codex-prompt.txt.
Write the prompt to <rundir>/prompt.txt with the Write tool (NOT echo or a heredoc — shell quoting mangles multi-line prompts). Content: the user's request, verbatim. If empty, ask one line: "What should I ask Codex?"
Run the wrapper (it picks the best available model and falls back automatically — never call codex exec directly):
bash "${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.sh" <rundir>/reply.txt < <rundir>/prompt.txt
Run in the foreground and wait — it can take a minute or two.
Relay the reply. Read <rundir>/reply.txt. If it's short, show it verbatim; if long, summarize the key points and offer the full text. Label it clearly as Codex's answer, and add one sentence on where you agree or differ.
If the wrapper fails, tell the user in plain language — "I couldn't reach Codex just now, so here's my own answer instead. If this keeps happening, run /kit-setup." — then answer the question yourself. Keep the technical error details to yourself unless the user asks for them.
Clean up. Remove the temp directory (rm -rf <rundir>).
npx claudepluginhub chrisblattman/claudeblattman --plugin starter-kit/consult-codexConsults OpenAI Codex CLI on current repo for code analysis, review, and refactoring; synthesizes with Claude's reasoning in 5-part response.
/rescueDelegates a task to Codex AI via background codex exec using arguments, based on OpenAI or OpenRouter provider. Presents unfiltered response and awaits user action.
/codexDelegates coding tasks to OpenAI Codex CLI for autonomous execution via natural language prompts, handling code refactoring, testing, bug fixes, explanations, features, and reviews.
/codexGenerates a compact markdown index of your codebase covering routes, schema, components, and lib exports to reduce token usage for AI assistants.