Codex with ChatGPT Planning Loop
XiaoDuoYa/codex-with-chatgpt
Uses ChatGPT in the browser as the planning and review brain for a Codex session, with Codex keeping all execution and ChatGPT reading the workspace through a bridge.
驅動一個多模型分工的自動迴圈：由 Fable 擔任 orchestrator 規劃並審定升級方案，Sonnet 擔任 implementer 實際執行修改，另一支 Sonnet 擔任唯讀 observer 記錄每個動作供事後查核，唯讀 inspector-ops 在每個完成階段查核驗收；有錯就從最前端的 prompt（先 brief、再 plan）回頭修正再重跑，同一階段最多三次失敗就升級給…
Install Loop Up
$ npx skills add shuotao/REVIT_MCP_study --skill loop-up -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shuotao/REVIT_MCP_study loop-up --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/shuotao/REVIT_MCP_study.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/loop-up .claude/skills/loop-up && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "loop-up" agent skill from https://github.com/shuotao/REVIT_MCP_study/tree/main/.claude/skills/loop-up into .claude/skills/loop-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-up", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/shuotao/REVIT_MCP_study/tree/main/.claude/skills/loop-upType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add shuotao/REVIT_MCP_study --skill loop-up -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shuotao/REVIT_MCP_study loop-up --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shuotao/REVIT_MCP_study.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/loop-up .agents/skills/loop-up && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "loop-up" agent skill from https://github.com/shuotao/REVIT_MCP_study/tree/main/.claude/skills/loop-up into .agents/skills/loop-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-up", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shuotao/REVIT_MCP_study --skill loop-up -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shuotao/REVIT_MCP_study loop-up --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shuotao/REVIT_MCP_study.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/loop-up .cursor/skills/loop-up && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "loop-up" agent skill from https://github.com/shuotao/REVIT_MCP_study/tree/main/.claude/skills/loop-up into .cursor/skills/loop-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-up", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/shuotao/REVIT_MCP_study.git --path .claude/skills/loop-up--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add shuotao/REVIT_MCP_study --skill loop-up -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shuotao/REVIT_MCP_study loop-up --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shuotao/REVIT_MCP_study.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/loop-up .gemini/skills/loop-up && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "loop-up" agent skill from https://github.com/shuotao/REVIT_MCP_study/tree/main/.claude/skills/loop-up into .gemini/skills/loop-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-up", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install shuotao/REVIT_MCP_study loop-upInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add shuotao/REVIT_MCP_study --skill loop-up -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shuotao/REVIT_MCP_study.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/loop-up .github/skills/loop-up && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "loop-up" agent skill from https://github.com/shuotao/REVIT_MCP_study/tree/main/.claude/skills/loop-up into .github/skills/loop-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-up", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shuotao/REVIT_MCP_study --skill loop-up -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shuotao/REVIT_MCP_study loop-up --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shuotao/REVIT_MCP_study.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/loop-up .opencode/skills/loop-up && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "loop-up" agent skill from https://github.com/shuotao/REVIT_MCP_study/tree/main/.claude/skills/loop-up into .opencode/skills/loop-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-up", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
loop-up- GitHub stars
- 102
- Token cost
- ~5.8k tokens
- SKILL.md length
- 1,457 words
- Files
- 3 (incl. references)
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- None found
At a glance
驅動一個多模型分工的自動迴圈：由 Fable 擔任 orchestrator 規劃並審定升級方案，Sonnet 擔任 implementer 實際執行修改，另一支 Sonnet 擔任唯讀 observer 記錄每個動作供事後查核，唯讀 inspector-ops 在每個完成階段查核驗收；有錯就從最前端的 prompt（先 brief、再 plan）回頭修正再重跑，同一階段最多三次失敗就升級給…
- Works in 8 steps: Intake — 建立 Stage Plan（orchestrator） → Stage 執行迴圈（implementer + observer） → Inspection Gate（inspector-ops，唯讀） → …
- Tasks that involve Multi-agent orchestration
- SKILL.md covers 啟動前置門檻（Gate，非建議——四項全過才可啟動）, 角色與模型對應表, Sub-Workflows and Workflow Script 範本（可重複使用的參數化控制流）, plus 6 more sections
- Runs TypeScript scripts from its folder; calls git and npm
What it does
Loop Up is an agent skill from shuotao/REVIT_MCP_study. 驅動一個多模型分工的自動迴圈：由 Fable 擔任 orchestrator 規劃並審定升級方案，Sonnet 擔任 implementer 實際執行修改，另一支 Sonnet 擔任唯讀 observer 記錄每個動作供事後查核，唯讀 inspector-ops 在每個完成階段查核驗收；有錯就從最前端的 prompt（先 brief、再 plan）回頭修正再重跑，同一階段最多三次失敗就升級給 Fable 擔任 advisor 提出修正建議，全程 human out of the loop、所有選項採建議值，直到通過或觸發安全護欄才停下來問人。適用於有明確可自動驗收條件的多階段工作（重構、遷移、規格校對、registry 一致性），不適用於探索性或需要人類美感判斷的任務。觸發條件：loop-up、/loop-up、多模型分工、自動迴圈修正、multi-agent loop、orchestrator advisor loop、observer inspector、prompt-first correction、迴圈驗收、自動重試升級、fable orchestrator sonnet implementer。
Its SKILL.md is about 5.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/workflow-template.ts`).
It sits in Agent Workflows, covering Multi-agent orchestration. It works with Model Context Protocol. The repository describes itself as: LEARN HOW TO BUILD UP YOUR REVIT MCP.
When your agent uses it
- Tasks that involve Multi-agent orchestration
Example prompts
- “/loop-up”
Requirements
- Node.js
Workflow steps
8 steps, taken from the step headings in SKILL.md.
- Intake — 建立 Stage Plan（orchestrator）
- Stage 執行迴圈（implementer + observer）
- Inspection Gate（inspector-ops，唯讀）
- Prompt-First 修正組裝（不是「叫 implementer 亂改 code」）
- 升級 Advisor（3 次失敗後，只升級一次）
- 終止條件（避免無限迴圈）
- Stage 收尾與交接
- 整體完成報告
What it can do on your machine
Read from SKILL.md and the folder at commit 2faacc5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (TypeScript), which the agent can run.
Shell commands in SKILL.md call:
gitnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git and npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Loop Up loads about 5.8k tokens when it runs, and up to ~7.2k if it reads all its reference files. Until then it costs about 130 tokens; SKILL.md has 1,457 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,457 words (~5,777 tokens).
“多模型分工＋自動迴圈修正的可重複流程。設計模式屬於 Iterative Refinement（品質改善迴圈），與 claude-md-sync 同類；也是本專案既有的 mcp-registry-sync（修正）＋ mcp-registry-ops-inspect（唯讀稽核）＋ validate_publish_consistency.py（硬性 gate）三件式迴圈 （見 CLAUDE.md → 「MCP Registry Publish Consistency」）的角色通用化版本 —— 那是這個模式在單一領域（registry 一致性）的既有實例， loop-up 把同樣的「修正角色／唯讀稽核角色／硬性 gate」拆成可套用到任何有明確驗收條件的多階段工作的通用骨架。”
- name
- loop-up
- user-invocable
- true
Files
SKILL.md and 2 other files (references) in .claude/skills/loop-up of shuotao/REVIT_MCP_study.
- SKILL.md
- references/workflow-template.ts
- runs.jsonl
Open the folder on GitHubat commit 2faacc5
Compare with similar skills
Loop Up next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Loop Up this skillshuotao/REVIT_MCP_study | 102 | — | ~5.8k | Automated safety check: Pass | None | |
| Codex with ChatGPT Planning LoopXiaoDuoYa/codex-with-chatgpt | 7.1k | — | ~11k | Automated safety check: Notes | MIT | |
| MemPalace Task HandoffMemPalace/mempalace | 59k | — | ~1.9k | Automated safety check: Pass | MIT | |
| agtx One-Shot Project Runnerfynnfluegge/agtx | 1.7k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Puppetmaster Agent Orchestrationprofessorpalmer/Puppetmaster | 467 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Agent Manager Fleet TUIYoanWai/agent-manager | 576 | — | ~1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
MemPalace Task Handoff
MemPalace/mempalace
Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.
agtx One-Shot Project Runner
fynnfluegge/agtx
Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.
Puppetmaster Agent Orchestration
professorpalmer/Puppetmaster
Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.
Agent Manager Fleet TUI
YoanWai/agent-manager
Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked.
Generate Harness Dsl
QoderAI/better-harness
Generate, revise, or review complete Harness as Code .harness files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and…
More from shuotao/REVIT_MCP_study
All 24 skills in this repoArchicad Skill Adapter
shuotao/REVIT_MCP_study
Translates Revit-oriented BIM Skill intent and terminology into a guarded Archicad MCP workflow while preserving the original Domain method and Revit route.
Domain Diagram
shuotao/REVIT_MCP_study
引導剛寫完 domain 的老師把 SOP 流程圖像化：先討論主流程、做流程健檢（迴圈／死路／缺口），再把流程整理成結構化 spec，交由 .claude/skills/domain-diagram/scripts/mermaidfromspec.py 確定性地產出 GitHub 原生 mermaid 圖與健檢結論並回嵌…
Dll To MCP Tool
shuotao/REVIT_MCP_study
Wrap a standalone Revit IExternalCommand (.cs / DLL, WPF dialog allowed) into a revit-mcp MCP tool.
Quantity Takeoff Excel
shuotao/REVIT_MCP_study
Create or review auditable Revit quantity-takeoff Excel reports for partition walls, baseboards, interior wall finishes, room schedules, and scaffolding.
Align Views On Sheets
shuotao/REVIT_MCP_study
批次對齊 view 範圍 + viewport 在 sheet 上的位置：三階段流程結合 ScopeBox、titleblock 對齊與 viewport 定位。階段一用 setscopeboxforviews 把一組 view 的 CropBox 綁到指定 ScopeBox（範圍統一）；階段二（可選）用 aligntitleblocksonsheets 對齊圖框 instance 位置（解決…
Batch Apply View Template
shuotao/REVIT_MCP_study
批次將指定的 ViewTemplate 套用到多個 view：支援以圖紙（sheets）或 view 名稱/ID 選取目標 view，可搭配 viewTypeFilter 過濾類型，並提供 dryRun 預覽 + skipIfSameTemplate 避免重複套用。適用於：跨專案複製後統一視圖樣式、出圖前批次校正 view template、把整本圖集的 view 改成統一…
Related
Works with
Categories
Questions about Loop Up
What does Loop Up do?
驅動一個多模型分工的自動迴圈：由 Fable 擔任 orchestrator 規劃並審定升級方案，Sonnet 擔任 implementer 實際執行修改，另一支 Sonnet 擔任唯讀 observer 記錄每個動作供事後查核，唯讀 inspector-ops 在每個完成階段查核驗收；有錯就從最前端的 prompt（先 brief、再 plan）回頭修正再重跑，同一階段最多三次失敗就升級給…. Loop Up is an agent skill from shuotao/REVIT_MCP_study.
When should I use Loop Up?
Loop Up fits situations like: tasks that involve Multi-agent orchestration.
How do I install Loop Up in Claude Code?
Run `npx skills add shuotao/REVIT_MCP_study --skill loop-up -a claude-code`. Or copy the skill folder (.claude/skills/loop-up in shuotao/REVIT_MCP_study) into .claude/skills/loop-up in your project. Claude Code loads it when a task matches its description.
How do I install Loop Up in Codex?
Run `npx skills add shuotao/REVIT_MCP_study --skill loop-up -a codex`. Or copy the skill folder (.claude/skills/loop-up in shuotao/REVIT_MCP_study) into .agents/skills/loop-up in your project. Codex loads it when a task matches its description.
Can I use Loop Up in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shuotao/REVIT_MCP_study --skill loop-up -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loop-up, .gemini/skills/loop-up, .github/skills/loop-up and .opencode/skills/loop-up in your project.
What does Loop Up need to run?
Going by SKILL.md and its folder, Loop Up needs TypeScript for the scripts in its folder and the command-line tools its instructions call (git and npm). Our summary lists: Node.js.
Does Loop Up access the network?
SKILL.md contains no URLs. Its commands use git and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Loop Up safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Loop Up use?
No licence was found for Loop Up or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Loop Up use?
About 5.8k tokens (SKILL.md is roughly 23k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.
What are the alternatives to Loop Up?
Skills that share tags, products or a category with Loop Up: Codex with ChatGPT Planning Loop (XiaoDuoYa/codex-with-chatgpt, 7.1k stars), MemPalace Task Handoff (MemPalace/mempalace, 59k stars), agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars) and Puppetmaster Agent Orchestration (professorpalmer/Puppetmaster, 467 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Loop Up?
shuotao (a GitHub user) maintains it in shuotao/REVIT_MCP_study, which has 102 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on August 31, 2026.
Source: shuotao/REVIT_MCP_study on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.