Math Modeling Environment Doctor
jihe520/MathModelAgent
Checks that the tools and Python packages needed for a math modeling paper workflow are installed and offers platform-specific install commands for anything missing.
Runs a math modeling contest pipeline for CUMCM and MCM/ICM entries in Codex CLI, with git checkpoints, verified solver code and human review at each stage.
SKILL.md written in Chinese; this summary is our English description.
Install AutoMCM-Pro for Codex CLI
$ npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --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/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/auto-mcm .claude/skills/auto-mcm && 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 "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.agents/skills/auto-mcm into .claude/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", 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/RealSeaberry/AutoMCM-Pro/tree/main/.agents/skills/auto-mcmType 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 RealSeaberry/AutoMCM-Pro --skill auto-mcm -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/auto-mcm .agents/skills/auto-mcm && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.agents/skills/auto-mcm into .agents/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", 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 RealSeaberry/AutoMCM-Pro --skill auto-mcm -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/auto-mcm .cursor/skills/auto-mcm && 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 "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.agents/skills/auto-mcm into .cursor/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", 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/RealSeaberry/AutoMCM-Pro.git --path .agents/skills/auto-mcm--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 RealSeaberry/AutoMCM-Pro --skill auto-mcm -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/auto-mcm .gemini/skills/auto-mcm && 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 "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.agents/skills/auto-mcm into .gemini/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", 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 RealSeaberry/AutoMCM-Pro auto-mcmInstalls 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 RealSeaberry/AutoMCM-Pro --skill auto-mcm -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/auto-mcm .github/skills/auto-mcm && 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 "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.agents/skills/auto-mcm into .github/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", 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 RealSeaberry/AutoMCM-Pro --skill auto-mcm -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install RealSeaberry/AutoMCM-Pro auto-mcm --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RealSeaberry/AutoMCM-Pro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/auto-mcm .opencode/skills/auto-mcm && 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 "auto-mcm" agent skill from https://github.com/RealSeaberry/AutoMCM-Pro/tree/main/.agents/skills/auto-mcm into .opencode/skills/auto-mcm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auto-mcm", 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
auto-mcm- GitHub stars
- 257
- Token cost
- ~1.6k tokens
- SKILL.md length
- 393 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Runs a math modeling contest pipeline for CUMCM and MCM/ICM entries in Codex CLI, with git checkpoints, verified solver code and human review at each stage.
- Working through a CUMCM or MCM/ICM modeling contest problem with Codex CLI
- SKILL.md covers 【触发时的依赖安装询问】, 【与其他 runtime 最大的差异：Codex…, 【工具映射表】 and 【已知能力缺口：网络搜索】, plus 4 more sections
- Calls python, codex and bash
- Producing a LaTeX paper whose solver code has been run and checked
What it does
This is the Codex CLI binding of the AutoMCM-Pro protocol, a full pipeline for Chinese (CUMCM) and English (MCM/ICM) mathematical modeling contests. It has two modes: an AI-led mode and a manual mode led by your own specification. Git checkpoints are mandatory, all solver code must be run and checked before it is included in the LaTeX paper, and a human cross-check happens at every stage.
Most of the file adapts that process to Codex, where the model sees a single exec tool that runs JavaScript and calls exec_command for shell work, apply_patch for edits, view_image for charts and update_plan for task lists. It notes that no first-party web search tool was confirmed and that the authoritative rules sit in a separate AutoMCM_SOP.md in the repository. In each new session it asks before installing Python modeling packages (pdfplumber, scipy, numpy, matplotlib, pandas, openpyxl) or the optional Lean 4 support, and never installs silently.
When your agent uses it
- Working through a CUMCM or MCM/ICM modeling contest problem with Codex CLI
- Producing a LaTeX paper whose solver code has been run and checked
- Keeping a contest project under git checkpoints with a human reviewing each stage
Example prompts
- “Start an MCM/ICM modeling run in AP mode using the problem PDF in ./problem/.”
- “Use manual mode: I wrote the model spec in spec.md, you write and verify the solver code.”
- “Set up AutoMCM-Pro for our CUMCM team and ask me before installing any Python packages.”
Requirements
- Codex CLI
- Python packages pdfplumber, scipy, numpy, matplotlib, pandas and openpyxl, installed on request
- Optional Lean 4 and LeanGate
What it can do on your machine
Read from SKILL.md and the folder at commit 90c4727. 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
Shell commands in SKILL.md call:
pythoncodexbash
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
AutoMCM-Pro for Codex CLI loads about 1.6k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 393 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
The full file from RealSeaberry/AutoMCM-Pro at commit 90c4727, republished under its MIT licence (© RealSeaberry). 393 words, ~1,619 tokens.
Download SKILL.mdSave it as
.claude/skills/auto-mcm/SKILL.md (or your agent's skills folder).- name
- auto-mcm
- description
- AutoMCM-Pro industrial-grade math modeling agent (Codex CLI binding). Supports AP (AI-led) and Manual (human-spec-led) dual modes with mandatory GitOps checkpoints, forced self-verification of all solver code before LaTeX inclusion, and structured human cross-validation at each pipeline stage. Use for both CUMCM (Chinese) and MCM/ICM (English) competitions.
AutoMCM-Pro：Codex CLI 绑定
这是 AutoMCM-Pro 协议在 OpenAI Codex CLI 上的运行时绑定（Binding），不是另一套
独立协议。 行为规范权威来源仍是仓库根目录的 AutoMCM_SOP.md（工具无关，原样
复用）；可选探索层见 LOS_ALAMOS_DESIGN.md。Claude Code 绑定是
.claude/skills/auto-mcm/SKILL.md，DeepSeek Harness 绑定是
.dsh/skills/auto-mcm/SKILL.md——三份文件描述同一套流程，只是把"怎么调用工具"
换成各自 runtime 的实际工具，流程逻辑、Checkpoint 规则、质量门控、Prompt 内容
不应该在几份文件间产生分歧。完整背景见
CODEX_INTEGRATION.md。
【触发时的依赖安装询问】
每个新的 Codex 会话首次触发本 Skill 时，先询问用户是否安装核心 Python 建模依赖
（pdfplumber、scipy、numpy、matplotlib、pandas、openpyxl），以及是否准备可选的
LeanGate / Lean 4。不得预扫描或静默安装；用户同意后才调用
bash install.sh --with-python-deps 和/或 --with-lean。拒绝后同一会话不重复询问。
非交互执行无法取得回答时，显示问题并暂停，不得把沉默当作同意。
【与其他 runtime 最大的差异：Codex 只给模型一个"代码模式"工具，实测确认】
这不是源码调研的推测，是实跑一次任务、解压
~/.codex/sessions/**/rollout-*.jsonl 核对过的：Codex 模型端 function-calling
只看得到一个叫 exec 的顶层工具，参数是一段 JavaScript 代码；
tools.exec_command({cmd, workdir, ...}) 是这段 JS 代码内部能调用的异步
函数，不是模型能单独调用的顶层工具。也就是说，Bash/Read（文本）在 Codex
上都是：模型写一段 JS，里面调用 tools.exec_command({cmd: "..."})，再用
text(r.output) 把结果吐出来——不是直接的 {"tool": "exec_command", "cmd": "..."} 这种扁平 function call。
实测时甚至连读 SKILL.md 本身也是这样做的：模型用
tools.exec_command({cmd: "sed -n '1,240p' .agents/skills/auto-mcm/SKILL.md"})
直接读档，没有专门的 skill 载入工具——这点跟 opencode/dsh 都不一样（它们有
独立的 skill 工具）。
这件事对 AutoMCM-Pro 反而是天然契合——本项目的流水线绝大部分工作本来就是
"用 bash 调 Python 脚本"，很少直接依赖结构化文件工具，翻译成 Codex 的
JS-in-exec 模式没有额外损失。
【工具映射表】
| Claude Code | Codex 工具 | 说明 |
|---|---|---|
Bash | 顶层工具 exec（参数是一段 JS），内部调 tools.exec_command({cmd,...}) | ✅ 实测确认（喚醒協議 Step 1 跑通）。万能工具：跑 Python 脚本、cat 读文件、rg/grep/find 搜索、curl 抓网页，本文件后续所有"执行 python scripts/..."都是这个模式，不是直接的扁平 function call |
Read | 同上，exec 里的 JS 调 tools.exec_command({cmd: "cat ..."}) | ✅ 实测确认（读 SKILL.md 本身就是这么做的） |
Read（图片） | view_image | 专用图片查看工具，读图表/PDF 截图用它，不要用 cat |
Write/Edit | apply_patch | 结构化 diff 应用工具，写/改模型代码、.tex 文件优先用它（比 shell heredoc 更可靠地保留缩进/编码） |
Glob/Grep | exec_command 里 rg/find | 没有专用搜索工具 |
TodoWrite | update_plan | 语义对应 |
AskUserQuestion | 请求用户输入的工具（模块 request_user_input，确切工具名未逐字核对，见下方核验清单） | 语义对应 |
Agent(description, prompt) | 多代理协同工具家族（模块 multi_agents/multi_agents_v2，确切工具名未逐字核对） | Codex 有原生多代理能力，但这次没有把确切的工具调用 schema 读完，接入前务必先跑一个最小测试确认参数格式 |
WebSearch/WebFetch | 没有确认到的第一方工具 | 见下方【已知能力缺口】 |
上表里 exec_command/apply_patch/view_image/update_plan 四个工具名是从
codex-rs/core/src/tools/handlers/ 源码里的 ToolName::plain(...) 字面量直接
核对过的（不是猜的）；request_user_input、multi_agents/multi_agents_v2 是
从模块/文件命名推断，没有找到对应的字符串字面量，接入前务必先用一个最简单的
任务实测一次，确认真实暴露给模型的工具名。
【已知能力缺口：网络搜索】
Codex 核心代码里没找到独立的 web_search/web_fetch 工具（dsh/opencode 都有，
Codex 没有内置）。看到的只有 MCP（Model Context Protocol）相关模块，猜测 Codex
把网络检索能力交给用户自行配置的 MCP server，而不是内置。这意味着：
AutoMCM_SOP.md里"文献调研至少 5 篇"这条硬性要求，在 Codex 上落地前必须先 确认有可用的网络检索能力（配置一个 MCP 网络搜索 server，或者退化成exec_command里curl调用一个你自己有权限的搜索 API）；- 若确认没有任何网络检索能力，不要静默跳过文献调研——按
AutoMCM_SOP.md第 7 节"禁止静默跳过验证失败"的同一精神，在 Checkpoint①里如实告知用户"当前 环境无网络检索工具，本阶段建模假设未经文献交叉验证"，让人类决定要不要补充 MCP 配置或人工提供文献。 - 同样的缺口也影响
AutoMCM_SOP.md§18"画图前先查领域惯例"——判断某类问题的 常规可视化形式本质上也是一次网络检索。不要因为查不到就直接静默退化成随手 选个图表类型：先按上面同一套办法确认有没有可用的检索能力；确实没有的话， 在thought_process.md里如实记录"当前环境无网络检索工具，图表形式选择依据 建模者常识判断、未经领域惯例检索确认"，而不是不留痕迹地直接画图。
Show full SKILL.md (156 more words)Show less
【运行方式】（Codex 特有）
codex # 交互式
codex exec "task" # 单次任务模式，类似 claude --print / dsh --profile headlessSkill 发现路径是 .agents/skills/auto-mcm/SKILL.md（仓库根向上找 .git，Codex
官方文档确认），显式调用用 $auto-mcm，或让模型按 description 隐式匹配。
【流水线执行】
阶段定义、状态机、Checkpoint 编号（①~⑤）、质量门控（quality_gate.py）、
Los Alamos 探索层（路径 C）、图表风格规范（plot_style.py）、Andon 紧急停止
（pipeline_manager.py andon-pull/andon-clear/andon-status）、Go/No-Go 发射前检查
（quality_gate.py launch-check，final_compile 前强制）、Skunk Works 轻量模式
（pipeline_manager.py init --skunk-works）、Track2 的 RAND Delphi 多轮收敛
（adjudicate.py delphi-summary）、Kaizen 质量打磨循环
（pipeline_manager.py kaizen-assess/kaizen-round-start/kaizen-status）、工作日志
（worklog.py append/tail，单文件简体中文完整记录，唤醒协议 Step 0）、文献引用
真实性核验+共享池（cite_check.py register/verify/list/export-bibitems）、写作
风格打磨（style_check.py scan，latex_draft 固有规范非可选 addon）、官方格式
合规（quality_gate.py anon-check、ai_usage_doc.py generate/cite-format/ mcm-entry、compile_pdf.py 编译后页数提醒，AutoMCM_SOP.md §17）、画图前先查
领域惯例（AutoMCM_SOP.md §18）全部内容
与 Claude Code 版本一致，见
.claude/skills/auto-mcm/SKILL.md 对应小节（标题相同），
按上方【工具映射表】替换调用方式：
- 子 Agent 调用：原文里每个
Agent(description=..., prompt=<模板>)，改为 Codex 的多代理工具调用，prompt字段内容完全不变（先按【已知能力缺口】小节的 提醒实测确认参数格式，再套用到 Los Alamos 路径 C 的四套 Prompt 模板） - 人类确认环节：
ask_user_question换成 Codex 的用户输入请求工具 - 文件读写：模型代码/验证脚本/LaTeX 文件优先用
apply_patch，图表结果查看用view_image scripts/*.py系列命令（pipeline_manager.py/quality_gate.py/los_alamos/*.py/plot_style.py）完全不变，全部通过exec_command调用
【安全规程】
AutoMCM_SOP.md 的 S1~S5 原样适用。S3（外部服务调用告知）在 Codex 上尤其重要——
既然网络检索要靠用户自配的 MCP server，调用前更要做好关键词抽象化，不要把题目
原文整段发给一个你不确定信任边界的外部 MCP server。
【LeanGate：可选 Lean 形式化验证门禁】
LeanGate 默认关闭；行为规范见 AutoMCM_SOP.md §19。Codex 通过 exec 内的
tools.exec_command 调用共享命令：
python scripts/leangate.py doctor
python scripts/leangate.py --workspace CUMCM_Workspace init --policy selected
python scripts/leangate.py --workspace CUMCM_Workspace status --problem-n 1
python scripts/leangate.py --workspace CUMCM_Workspace verify --problem-n 1
python scripts/quality_gate.py formal --problem-n 1LeanGate 启用后，离开 problem_analysis 前必须逐问题登记适用性并执行
leangate.py seal-assessment；安全边界、整数可行性、守恒、不变量、递推、收敛、
求解器证书或决策关键结论必须用 --risk-category 标注，自动成为 mandatory。
不得直接编辑 claims.json 或报告来制造 PASS。任何输入变化后重新执行语义审查、冻结
与验证；Lean FAIL、UNKNOWN、STALE 或 Python FAIL 都是 NO-GO。
LeanGate 启用后的 model_N_verify 推进必须传入工作区内真实验证脚本：
pipeline_manager.py advance model_N_verify --verify-script CUMCM_Workspace/src/verifications/verify_*.py。
required claim 还必须使用人类文件中的 [APPROVED LeanGate ...] 与 [REQUIRED LeanGate ...] 标记。
© RealSeaberry, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/auto-mcm of RealSeaberry/AutoMCM-Pro.
Open the folder on GitHubat commit 90c4727
Compare with similar skills
AutoMCM-Pro for Codex CLI 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 |
|---|---|---|---|---|---|---|
| AutoMCM-Pro for Codex CLI this skillRealSeaberry/AutoMCM-Pro | 257 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Math Modeling Environment Doctorjihe520/MathModelAgent | 6.2k | — | ~1.5k | Automated safety check: Notes | None | |
| Python Executorcortega26/chile-hub | 113 | 2 repos | ~1.5k | Automated safety check: Pass | MIT | |
| NSFC Budget Justification Writerhuangwb8/ChineseResearchLaTeX | 2.9k | 1 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Academic LaTeX Formatterlingzhi227/agent-research-skills | 386 | — | ~603 | Automated safety check: Pass | None | |
| Exploratory Data AnalysisOleafly/Oleafly | 209 | 2 repos | ~3.4k | Automated safety check: Notes | MIT |
Similar skills
Python Executor
cortega26/chile-hub
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).
NSFC Budget Justification Writer
huangwb8/ChineseResearchLaTeX
Writes a submission-ready NSFC budget justification as a LaTeX project and renders budget.pdf from your grant proposal text and supporting materials.
Academic LaTeX Formatter
lingzhi227/agent-research-skills
Sets up conference-specific LaTeX paper templates, checks a draft for formatting and submission issues, and auto-fixes common problems for venues like ICML, ICLR, NeurIPS, AAAI and ACL.
Exploratory Data Analysis
Oleafly/Oleafly
Perform bounded, local exploratory analysis of explicitly supported scientific files.
Math Modeling Workflow Starter
jihe520/MathModelAgent
Entry point for a math modeling competition project: asks about preferences, writes plan.md and todo.md, then calls stage skills for analysis, code, diagrams, paper and verification.
More from RealSeaberry/AutoMCM-Pro
AutoMCM Math Modeling Agent
RealSeaberry/AutoMCM-Pro
Runs a staged workflow for math modeling contests such as CUMCM and MCM/ICM, with checkpoints, verified solver code and a LaTeX paper, on DeepSeek Harness.
AutoMCM-Pro for opencode
RealSeaberry/AutoMCM-Pro
The opencode binding of the AutoMCM-Pro math modeling pipeline for CUMCM and MCM/ICM contests, with tool mappings, install prompts and checkpointed runs.
CUMCM Math Modeling Agent
RealSeaberry/AutoMCM-Pro
Drives an end-to-end workflow for the CUMCM math modeling contest: reads the problem and data, researches, codes and verifies models, then writes a LaTeX paper and PDF.
Draw Image Diagrams
RealSeaberry/AutoMCM-Pro
Generates diagrams, flowcharts and conceptual illustrations with OpenAI's gpt-image models, while leaving data plots and result figures to real plotting code.
MCM/ICM Autonomous Modeling Agent
RealSeaberry/AutoMCM-Pro
Runs an MCM/ICM math modeling competition end to end: collects contest metadata, builds and verifies models and code, then generates an English LaTeX paper and any required memo.
AutoMCM-Pro Math Modeling Agent
RealSeaberry/AutoMCM-Pro
Runs a math modeling competition entry end to end, in AI-led or human-led mode, with Git checkpoints and self-verified solver code before it enters the LaTeX paper.
Related
Works with
Categories
Questions about AutoMCM-Pro for Codex CLI
What does AutoMCM-Pro for Codex CLI do?
Runs a math modeling contest pipeline for CUMCM and MCM/ICM entries in Codex CLI, with git checkpoints, verified solver code and human review at each stage. This is the Codex CLI binding of the AutoMCM-Pro protocol, a full pipeline for Chinese (CUMCM) and English (MCM/ICM) mathematical modeling contests. It has two modes: an AI-led mode and a manual mode led by your own specification.
When should I use AutoMCM-Pro for Codex CLI?
AutoMCM-Pro for Codex CLI fits situations like: working through a CUMCM or MCM/ICM modeling contest problem with Codex CLI; producing a LaTeX paper whose solver code has been run and checked; keeping a contest project under git checkpoints with a human reviewing each stage.
How do I install AutoMCM-Pro for Codex CLI in Claude Code?
Run `npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a claude-code`. Or copy the skill folder (.agents/skills/auto-mcm in RealSeaberry/AutoMCM-Pro) into .claude/skills/auto-mcm in your project. Claude Code loads it when a task matches its description.
How do I install AutoMCM-Pro for Codex CLI in Codex?
Run `npx skills add RealSeaberry/AutoMCM-Pro --skill auto-mcm -a codex`. Or copy the skill folder (.agents/skills/auto-mcm in RealSeaberry/AutoMCM-Pro) into .agents/skills/auto-mcm in your project. Codex loads it when a task matches its description.
Can I use AutoMCM-Pro for Codex CLI 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 RealSeaberry/AutoMCM-Pro --skill auto-mcm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-mcm, .gemini/skills/auto-mcm, .github/skills/auto-mcm and .opencode/skills/auto-mcm in your project.
What does AutoMCM-Pro for Codex CLI need to run?
Going by SKILL.md and its folder, AutoMCM-Pro for Codex CLI needs the command-line tools its instructions call (python, codex and bash). Our summary lists: Codex CLI; Python packages pdfplumber, scipy, numpy, matplotlib, pandas and openpyxl, installed on request; Optional Lean 4 and LeanGate.
Does AutoMCM-Pro for Codex CLI access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is AutoMCM-Pro for Codex CLI 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 AutoMCM-Pro for Codex CLI use?
AutoMCM-Pro for Codex CLI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does AutoMCM-Pro for Codex CLI use?
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to AutoMCM-Pro for Codex CLI?
Skills that share tags, products or a category with AutoMCM-Pro for Codex CLI: Math Modeling Environment Doctor (jihe520/MathModelAgent, 6.2k stars), Python Executor (cortega26/chile-hub, 113 stars), NSFC Budget Justification Writer (huangwb8/ChineseResearchLaTeX, 2.9k stars) and Academic LaTeX Formatter (lingzhi227/agent-research-skills, 386 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains AutoMCM-Pro for Codex CLI?
RealSeaberry (a GitHub user) maintains it in RealSeaberry/AutoMCM-Pro, which has 257 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 10, 2026.
Source: RealSeaberry/AutoMCM-Pro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.