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 skills/jihe520/mathmodelagent/5writingnpx skills add jihe520/MathModelAgent --skill 5writinggit clone --depth 1 https://github.com/jihe520/MathModelAgentWhat 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 | $0.00068 | $0.03913 |
| Opus 5 | $0.00034 | $0.01956 |
| Sonnet 5 | $0.00014 | $0.00783 |
| Haiku 4.5 | $0.00007 | $0.00391 |
Grade A, and why
5writing 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- templates/en/apmcm-latex/main.tex 6.6 KB
- templates/en/apmcm-latex/references.tex 532 B
- templates/en/apmcm-latex/sections/1_introduction.tex 635 B
- templates/en/apmcm-latex/sections/2_assumptions.tex 524 B
- templates/en/apmcm-latex/sections/3_model_design.tex 398 B
- templates/en/apmcm-latex/sections/4_solution.tex 826 B
- templates/en/apmcm-latex/sections/5_sensitivity.tex 535 B
- templates/en/apmcm-latex/sections/6_strengths_weaknesses.tex 600 B
- templates/en/apmcm-latex/sections/7_conclusions.tex 535 B
- templates/en/apmcm-latex/sections/A_code.tex 774 B
- templates/en/apmcm/main.typ 13 KB
- templates/en/apmcm/references.typ 522 B
- templates/en/apmcm/sections/1_introduction.typ 601 B
- templates/en/apmcm/sections/2_assumptions.typ 427 B
- templates/en/apmcm/sections/3_model_design.typ 335 B
- templates/en/apmcm/sections/4_solution.typ 859 B
- templates/en/apmcm/sections/5_sensitivity.typ 608 B
- templates/en/apmcm/sections/6_strengths_weaknesses.typ 415 B
- templates/en/apmcm/sections/7_conclusions.typ 443 B
- templates/en/apmcm/sections/A_code.typ 528 B
- templates/en/default-latex/main.tex 3.6 KB
- templates/en/default-latex/references.tex 532 B
- templates/en/default-latex/sections/1_introduction.tex 635 B
- templates/en/default-latex/sections/2_assumptions.tex 523 B
- templates/en/default-latex/sections/3_notations.tex 560 B
- templates/en/default-latex/sections/4_model.tex 826 B
- templates/en/default-latex/sections/5_results.tex 813 B
- templates/en/default-latex/sections/6_sensitivity.tex 535 B
- templates/en/default-latex/sections/7_evaluation.tex 598 B
- templates/en/default-latex/sections/8_conclusions.tex 534 B
- templates/en/default-latex/sections/A_code.tex 774 B
- templates/en/default/main.typ 5.5 KB
- templates/en/default/references.typ 288 B
- templates/en/default/sections/1_introduction.typ 600 B
- templates/en/default/sections/2_assumptions.typ 421 B
- templates/en/default/sections/3_notations.typ 738 B
- templates/en/default/sections/4_model.typ 975 B
- templates/en/default/sections/5_results.typ 917 B
- templates/en/default/sections/6_sensitivity.typ 712 B
- templates/en/default/sections/7_evaluation.typ 408 B
- templates/en/default/sections/8_conclusions.typ 438 B
- templates/en/default/sections/A_code.typ 527 B
- templates/en/mcm-latex/main.tex 4.4 KB
- templates/en/mcm-latex/references.tex 350 B
- templates/en/mcm-latex/sections/1_introduction.tex 635 B
- templates/en/mcm-latex/sections/2_assumptions.tex 523 B
- templates/en/mcm-latex/sections/3_model_design.tex 398 B
- templates/en/mcm-latex/sections/4_solution.tex 826 B
- templates/en/mcm-latex/sections/5_sensitivity.tex 441 B
- templates/en/mcm-latex/sections/6_strengths_weaknesses.tex 640 B
- templates/en/mcm-latex/sections/7_conclusions.tex 613 B
- templates/en/mcm-latex/sections/A_code.tex 774 B
- templates/en/mcm/main.typ 7.2 KB
- templates/en/mcm/references.typ 56 B
- templates/en/mcm/sections/1_introduction.typ 600 B
- templates/en/mcm/sections/2_assumptions.typ 421 B
- templates/en/mcm/sections/3_model_design.typ 332 B
- templates/en/mcm/sections/4_solution.typ 962 B
- templates/en/mcm/sections/5_sensitivity.typ 714 B
- templates/en/mcm/sections/6_strengths_weaknesses.typ 408 B
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.
- yesterday First seen · 419 lines · 68 tokens per session scan A 9dd985cf54d9
5writing is a skill published in the GitHub repository jihe520/MathModelAgent (3,944 stars, last pushed 5d ago), with no licence file. It adds 68 tokens to every session and 3,913 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
gpt-image-2
面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用：(A) Garden 本地模式，通过 OpenAI 兼容接口直接出图并落盘；(B) Host-Native 模式，把本 Skill 当作提示词工程指引，把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图；(C) Advisor 模式，宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板，覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。.
new
Create a new project to start development quickly.
oss-upload
Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.