// Use when you explicitly want a second Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final result.
| name | collaborating-with-codex |
| description | Use when you explicitly want a second Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final result. |
python scripts/codex_bridge.py --cd "/path/to/project" --PROMPT "Your task"
Output: JSON with success, SESSION_ID, agent_messages, and optional error.
usage: codex_bridge.py [-h] --PROMPT PROMPT --cd CD [--sandbox {read-only,workspace-write,danger-full-access}] [--SESSION_ID SESSION_ID] [--skip-git-repo-check]
[--return-all-messages] [--image IMAGE] [--model MODEL] [--yolo] [--profile PROFILE]
Codex Bridge
options:
-h, --help show this help message and exit
--PROMPT PROMPT Instruction for the task to send to codex.
--cd CD Set the workspace root for codex before executing the task.
--sandbox {read-only,workspace-write,danger-full-access}
Sandbox policy for model-generated commands. Defaults to `read-only`.
--SESSION_ID SESSION_ID
Resume the specified session of the codex. Defaults to `None`, start a new session.
--skip-git-repo-check
Allow codex running outside a Git repository (useful for one-off directories).
--return-all-messages
Return all messages (e.g. reasoning, tool calls, etc.) from the codex session. Set to `False` by default, only the agent's final reply message is
returned.
--image IMAGE Attach one or more image files to the initial prompt. Separate multiple paths with commas or repeat the flag.
--model MODEL The model to use for the codex session. This parameter is strictly prohibited unless explicitly specified by the user.
--yolo Run every command without approvals or sandboxing. Only use when `sandbox` couldn't be applied.
--profile PROFILE Configuration profile name to load from `~/.codex/config.toml`. This parameter is strictly prohibited unless explicitly specified by the user.
Always capture SESSION_ID from the first response for follow-up:
# Initial task
python scripts/codex_bridge.py --cd "/project" --PROMPT "Analyze auth in login.py"
# Continue with SESSION_ID
python scripts/codex_bridge.py --cd "/project" --SESSION_ID "uuid-from-response" --PROMPT "Write unit tests for that"
Prototyping (read-only, request diffs):
python scripts/codex_bridge.py --cd "/project" --PROMPT "Generate unified diff to add logging"
Debug with full trace:
python scripts/codex_bridge.py --cd "/project" --PROMPT "Debug this error" --return-all-messages
Use when the user wants multi-agent division of labor for research-led work and the lead should stay on the critical path while 1-2 bounded sidecars handle low-coupling tasks. Do not use this for tiny tasks, fully sequential debugging, or overlapping refactors.
Use when the user asks to review a skill, analyze skill quality, update a skill version, or run a repeatable keep/disable/archive decision loop from real failures instead of abstract best practices.
Use when the user explicitly wants to upload a final or near-final PDF to paperreview.ai for an external second opinion. Skip this for local paper critique, which should go through `paper-review-pipeline` first.
学术论文写作助手，专门用于 LaTeX 论文编写、BibTeX 管理、格式化、学术写作规范检查。适用于 AI/ML 研究论文、会议投稿（NeurIPS、ICML、ICLR 等）
Use when a task is ambiguous and needs deep multi-role planning with designer, inspiration, and reviewer perspectives before execution. Skip this for ordinary task plans.
落实 CLAUDE.md / AGENTS.md 中的“主动探索”原则，在向用户提问前自动使用 Grep、Read、Bash、WebSearch 等工具获取信息