菜单
Verify or set the ChatGPT composer to the Extended Pro target (reasoning Pro + model 5.5; pill reads "Extended Pro" or "Pro"). Required before any analytical submission.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Fan out a 4-member council (1 Codex thinking-high + 1 Gemini Pro + 1 Claude Opus + 1 ChatGPT Extended Pro) on a stalled re-attack. Preserves all four independent memos; hands off to the regular Strategy Searcher for pure selection. Opt-in (attempt ≥2), ~3× the cost of a single search.
Harvest a completed ChatGPT chat's last assistant message into a response file. Use when a role finished but the response file wasn't captured (e.g., orchestrator lost the chat URL, or the submit script died after the model responded).
Create or update {PROOF_REPO}/referee_targets.yaml — the target-journal registry the paper_referee role consults to judge whether the result clears the bar at the journals you might submit to. Optional; without it the referee falls back to a generic publishability check.
Use when working in MathPipeProver on ChatGPT project preparation, durable source refresh, project-source inspection, or browser-backed external_agent submission. Prefer scripts/chatgpt_browser_agent.sh prepare/submit over ad hoc UI work, enforce the Extended Pro target, and keep durable sources separate from temporary attachments.
Read-only one-shot inspection of a live ChatGPT chat — returns generating flag, assistant turn count, last assistant message length and tail. Use during long-running roles to check whether the chat is still working or done.
Add or remove durable files in a ChatGPT project's Sources tab. Use after a verified result lands, after a route pivot, or when the durable proof-state file has been updated locally.
| name | set-model-extended |
| description | Verify or set the ChatGPT composer to the Extended Pro target (reasoning Pro + model 5.5; pill reads "Extended Pro" or "Pro"). Required before any analytical submission. |
Canonical content: .claude/commands/set-model-extended.md in this repo.
Codex and Claude Code share the same procedure — edit the Claude command
file, not this stub.
Use before any role submission via submit-role. Shells out to:
scripts/chatgpt_browser_agent/cdp_set_model_pro.mjs --port PORT [--check-only]
--check-only just verifies (exit 0 = correct, exit 1 = wrong); without it
the script will actively toggle the composer into Extended Pro and
auto-disable Deep Research if it's currently active.
All DOM logic for the model pill lives in
scripts/chatgpt_browser_agent/lib/model_pill.mjs — when ChatGPT's
composer DOM changes, fix the lib once, not each entry-point script.
Read .claude/commands/set-model-extended.md for the full step-by-step.