sweetcornna/mathodology
专为数学建模竞赛设计的数模 Agent Skills：MCM/ICM 美赛、CUMCM 国赛、华数杯、M3、HiMCM 等，面向 Claude Code 与 Codex 的获奖级建模工作流。Math modeling contest skills for Claude Code & Codex.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add search -e SEARCH_MCP_DOWNLOAD_DIR=YOUR_SEARCH_MCP_DOWNLOAD_DIR -- uvx free-search-mcp $ npx degit sweetcornna/mathodology/.claude ./rig-mathodology # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add search -e SEARCH_MCP_DOWNLOAD_DIR=YOUR_SEARCH_MCP_DOWNLOAD_DIR -- uvx free-search-mcp $ npx degit sweetcornna/mathodology/.claude/skills/mathodology-agent-pipeline .claude/skills/mathodology-agent-pipeline $ npx degit sweetcornna/mathodology/.claude/skills/mathodology-award-gates .claude/skills/mathodology-award-gates $ npx degit sweetcornna/mathodology/.claude/skills/mathodology-dev-test-release .claude/skills/mathodology-dev-test-release $ npx degit sweetcornna/mathodology/.claude/skills/mathodology-evidence-search .claude/skills/mathodology-evidence-search $ npx degit sweetcornna/mathodology/.claude/skills/mathodology-figure-presets .claude/skills/mathodology-figure-presets $ npx degit sweetcornna/mathodology/.claude/skills/mathodology-project-orientation .claude/skills/mathodology-project-orientation $ npx degit sweetcornna/mathodology/.claude/skills/mathodology-skill-authoring .claude/skills/mathodology-skill-authoring $ npx degit sweetcornna/mathodology/.claude/skills/mathodology-whole-project .claude/skills/mathodology-whole-project
$ curl -fsSL --create-dirs -o .claude/agents/mathodology-coder.md https://raw.githubusercontent.com/sweetcornna/mathodology/main/.claude/agents/mathodology-coder.md $ curl -fsSL --create-dirs -o .claude/agents/mathodology-critic.md https://raw.githubusercontent.com/sweetcornna/mathodology/main/.claude/agents/mathodology-critic.md $ curl -fsSL --create-dirs -o .claude/agents/mathodology-evidence-researcher.md https://raw.githubusercontent.com/sweetcornna/mathodology/main/.claude/agents/mathodology-evidence-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/mathodology-lead.md https://raw.githubusercontent.com/sweetcornna/mathodology/main/.claude/agents/mathodology-lead.md $ curl -fsSL --create-dirs -o .claude/agents/mathodology-modeler.md https://raw.githubusercontent.com/sweetcornna/mathodology/main/.claude/agents/mathodology-modeler.md $ curl -fsSL --create-dirs -o .claude/agents/mathodology-paper-editor.md https://raw.githubusercontent.com/sweetcornna/mathodology/main/.claude/agents/mathodology-paper-editor.md $ curl -fsSL --create-dirs -o .claude/agents/mathodology-problem-analyst.md https://raw.githubusercontent.com/sweetcornna/mathodology/main/.claude/agents/mathodology-problem-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/mathodology-submission-packager.md https://raw.githubusercontent.com/sweetcornna/mathodology/main/.claude/agents/mathodology-submission-packager.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| free-search-mcp · "search" env: SEARCH_MCP_DOWNLOAD_DIR | pypi | 2.5k |
Skills (8)
mathodology-agent-pipelinemathodology-award-gatesmathodology-dev-test-releasemathodology-evidence-searchmathodology-figure-presetsmathodology-project-orientationmathodology-skill-authoringmathodology-whole-project
Subagents (8)
| mathodology-coder model: inherit | Implement reproducible modeling calculations, experiments, figures and tables. |
| mathodology-critic model: inherit | Independently review mathematical claims, evidence, code and communication. |
| mathodology-evidence-researcher model: inherit | Find and verify primary literature, datasets, citations and visual references. |
| mathodology-lead model: inherit | Coordinate a modeling task and integrate findings into one coherent answer. |
| mathodology-modeler model: inherit | Formulate models, objectives, constraints, assumptions and meaningful validation. |
| mathodology-paper-editor model: inherit | Write and revise a modeling paper, figures, captions and final narrative. |
| mathodology-problem-analyst model: inherit | Understand contest questions, requirements, mechanisms and decision needs. |
| mathodology-submission-packager model: inherit | Prepare the final modeling deliverable and reproduction instructions. |
Similar rigs
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Orchestrator 2.6k tok ·
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
Orchestrator 14.5k tok ·
alirezarezvani/claude-skills
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, complian
Orchestrator 48.5k tok ·
czlonkowski/n8n-mcp
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
Orchestrator 3.8k tok ·