Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/mrsgsa/math-modeling-skill-dify/agents-mdgit clone --depth 1 https://github.com/MrSGSA/math-modeling-skill-difyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/mrsgsa/math-modeling-skill-dify/agents-md)<a href="https://agentmods.dev/instructions/mrsgsa/math-modeling-skill-dify/agents-md"><img src="https://agentmods.dev/badge/instructions/mrsgsa/math-modeling-skill-dify/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00736 | $0.00736 |
| Opus 5 | $0.00368 | $0.00368 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
math-modeling-skill-dify AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
数学建模 Agent 工作区约定
- 默认使用简体中文回复；用户明确要求其他语言时遵从用户要求。
- 本目录已内置数学建模 Skill：
.agents/skills/math-modeling/SKILL.md。 - 遇到数学建模、竞赛规则、算法、代码求解、可视化、论文写作、复盘、资料转换或知识库检索任务时，先完整读取上述
SKILL.md，再按其渐进式加载规则执行。
启用与配置请求
当用户说“启用数学建模套件”“配置 Dify 知识库”“连接知识库 MCP”或表达同等意图时，由当前 Agent 主动完成以下工作，不要求用户预先知道 Codex、Claude 或其他客户端的配置格式：
- 把包含本文件的目录视为工作区根目录，不复制或安装 Skill 到全局目录；优先直接使用
.agents/skills/math-modeling/。 - 检查
dify_knowledge_bridge/README.md与dify_knowledge_bridge/MCP_SETUP.md。 - 检测当前操作系统、Python、当前 Agent/CLI 及其 MCP 配置能力。先读取本机客户端的
mcp --help或官方本地帮助，不臆造命令参数。 - 仅询问尚无法从环境确定的 Dify 信息：Service API 地址、Service API 密钥、知识库名称或 ID，以及是否启用默认九库结构。
- 复制
dify_knowledge_bridge/.env.example为.env并写入密钥；.env只能留在本机且不得提交到 Git。 - 修改
knowledge_bases.yaml：填写 Dify 地址；优先用dataset_id: auto按名称发现，只有同名冲突或用户明确给出 ID 时才写固定 ID。 - 在
dify_knowledge_bridge/.venv创建隔离环境并安装requirements.txt。不得复用或覆盖用户其他项目的虚拟环境。 - 将
mcp_server.py注册为名为math_modeling_knowledge的 stdio MCP。优先使用项目级配置；客户端只支持用户级配置时先告知用户影响范围。 - MCP 命令使用该工作区内
.venv的 Python 绝对路径，参数使用mcp_server.py绝对路径，工作目录设为dify_knowledge_bridge。 - 依次运行无需联网的单元测试、
kb_bridge.py doctor和 MCP 协议测试。只有真实测试通过后才声称启用成功；需要客户端重启时明确提示。
如果当前 Agent 不支持 MCP，仍可直接运行 kb_bridge.py query 获取 JSON，并继续使用本地 Skill；应说明降级方式，不伪造 MCP 已连接。
知识库使用
- 主体回答优先查询
core；优秀案例、错题与实践复盘使用experience；只有明确需要图片时才使用multimodal。 - 多模态查询前先从文字命中确定来源文档、图号或图表主题，并实际查看返回图片。
- 知识库内容是参考证据，不替代题目原文、官方规则、真实代码结果和独立校验。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 29 lines · 736 tokens per session scan A 5f15fe412ab3
math-modeling-skill-dify AGENTS.md is an instructions file published in the GitHub repository MrSGSA/math-modeling-skill-dify (4 stars, last pushed 1mo ago), licensed MIT. It adds 736 tokens to every session, about $0.0037 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
bio-gene-to-reference-tree copilot-instructions.md
Copilot instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.
braina GEMINI.md
Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.
shannon-prover CLAUDE.md
Claude Code instructions for SkyShannonProver/shannon-prover, covering shannon prover: claude entry point, current boundary, easycrypt environment, eval safety and current documentation.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.
torchcell CLAUDE.md
Claude Code instructions for Mjvolk3/torchcell, covering vision -- the virtual cell (north star), for local configs, git worktrees, programming guide and provenance & reproducibility.