원클릭으로
respond
Manually write response back to Claude. Use if read-task did not auto-complete or to finalize response.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Manually write response back to Claude. Use if read-task did not auto-complete or to finalize response.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Review code using GPT-5.5 Pro via Claude Code's Chrome integration. Use when the user asks to review code with ChatGPT, use their ChatGPT Pro subscription, get GPT-5.5 Pro to review code, or wants a second opinion from GPT. Requires Claude Code running with --chrome flag and user logged into chat.com. Triggers on "review with ChatGPT", "ChatGPT Pro review", "GPT-5.5 Pro code review", "get GPT's opinion".
Delegate arbitrary implementation, debugging, refactoring, planning, review, or custom coding tasks to ChatGPT GPT-5.5 Pro through the chatgpt-pro-worker MCP server. Use when the user asks to use ChatGPT Pro, GPT-5.5 Pro, or a Pro subagent/worker for a task.
[TMUX MODE] Delegate implementation to Codex via tmux file-based IPC. Only use when user explicitly runs /codex-implement command. For natural language requests, use the delegate_codex_implement MCP tool instead.
[TMUX MODE] Send plan to Codex via tmux file-based IPC. Only use when user explicitly runs /codex-plan-review command. For natural language requests, use the delegate_codex_plan_review MCP tool instead.
[TMUX MODE] Send code to Codex via tmux file-based IPC. Only use when user explicitly runs /codex-review command. For natural language requests like 'review with codex', use the delegate_codex_review MCP tool instead.
Read and integrate response from Codex. Use when user says codex read, get codex response, or check codex results.
| name | respond |
| description | Manually write response back to Claude. Use if read-task did not auto-complete or to finalize response. |
Manually write response back to Claude.
/read-task didn't auto-completeBefore any file operations, resolve the .agent-collab directory so commands work outside the project root:
AGENT_COLLAB_DIR="${AGENT_COLLAB_DIR:-}"
if [ -n "$AGENT_COLLAB_DIR" ]; then
if [ -d "$AGENT_COLLAB_DIR/.agent-collab" ]; then
AGENT_COLLAB_DIR="$AGENT_COLLAB_DIR/.agent-collab"
elif [ ! -d "$AGENT_COLLAB_DIR" ]; then
AGENT_COLLAB_DIR=""
fi
fi
if [ -z "$AGENT_COLLAB_DIR" ]; then
AGENT_COLLAB_DIR="$(pwd)"
while [ "$AGENT_COLLAB_DIR" != "/" ] && [ ! -d "$AGENT_COLLAB_DIR/.agent-collab" ]; do
AGENT_COLLAB_DIR="$(dirname "$AGENT_COLLAB_DIR")"
done
AGENT_COLLAB_DIR="$AGENT_COLLAB_DIR/.agent-collab"
fi
If $AGENT_COLLAB_DIR does not exist, stop and ask for the project root.
If task not yet completed, finish it now.
Collect all findings, code, or analysis.
Write to $AGENT_COLLAB_DIR/responses/response.md:
# Codex Response
## Task Type
[CODE_REVIEW | IMPLEMENT | PLAN_REVIEW]
## Completed At
[Current timestamp]
## Summary
[Brief summary]
## Detailed Findings/Output
[Full response content]
Write done to $AGENT_COLLAB_DIR/status
Tell user: "Response written. Claude can now use /codex-read to retrieve it."