ChineseResearchLaTeX is a collection of LaTeX templates and an AI-assisted workflow for preparing Chinese research documents such as grant proposals, papers, theses, and academic CVs. Researchers use it to plan, format, review, compile, and revise these documents with human oversight. The catalogue skills and instructions support its agent-based research-writing workflow.
Borrowing it
Nothing to install: this file belongs to huangwb8/ChineseResearchLaTeX. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/huangwb8/ChineseResearchLaTeX/main/AGENTS.mdgit clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeXWrote 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/huangwb8/chineseresearchlatex/agents-md)<a href="https://agentmods.dev/instructions/huangwb8/chineseresearchlatex/agents-md"><img src="https://agentmods.dev/badge/instructions/huangwb8/chineseresearchlatex/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/huangwb8/chineseresearchlatex/agents-md"><img src="https://agentmods.dev/badge/instructions/huangwb8/chineseresearchlatex/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02081 | $0.02081 |
| Opus 5 | $0.01040 | $0.01040 |
| Sonnet 5 | $0.00416 | $0.00416 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
ChineseResearchLaTeX 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChineseResearchLaTeX 项目指令
本仓库是面向科研文档的 LaTeX 工具链与 AI Skill 协作仓库，包含可复用的 LaTeX 包、项目级模板入口、安装/构建/发布脚本和研究写作相关 Skill。本文档是跨工具的通用协作约定；详细用法应放在对应的 README.md、docs/ 或 Skill 自身文档中，不要把实现细节重复写在这里。
项目目标
- 维护稳定、可安装、可验证的科研文档模板与公共包。
- 让项目入口保持轻薄，共享版式、字体、宏和构建逻辑集中在
packages/。 - 维护可复用的安装、构建、校验、发布脚本，以及面向科研工作的
skills/。 - 让源码、文档、测试、变更记录和贡献证据保持一致，方便人类与 AI 协作。
任务流程
处理任何任务时遵循：理解意图 → 定位责任层 → 读取真实接口 → 最小修改 → 定向验证 → 同步文档与记录。
定位责任层
packages/：跨项目共享的样式、资源、宏、公共 API 和构建逻辑。projects/：示例正文、项目元数据、学校或项目类型的薄封装；不要复制公共实现。scripts/：仓库级安装、同步、测试、打包和发布入口。skills/：AI Skill 的触发边界、执行流程、脚本、参考资料和测试。docs/：面向维护者和用户的现行说明、迁移文档与正式计划；docs/plans/专门保存计划。tests/及包内测试目录：可执行的回归、smoke 或集成测试；测试产物不放在源码目录。
先检查当前目录、脚本参数、相关 README/CHANGELOG 和必要的历史记录。当前源码与可执行脚本优先于旧计划、旧版本记忆或臆测的目录结构。
修改与验证
- 先读取足够上下文，再做最小、可回退的修改；不因顺手而重构无关内容。
- 共享问题上收公共包或公共脚本，项目差异留在项目层；Skill 的领域流程留在 Skill 内。
- 修改代码、脚本、模板或 Skill 后，运行与风险匹配的定向测试、静态检查或构建；失败时说明原因，不掩盖 warning 或未验证项。
- LaTeX 优先使用对应产品线的官方 Python wrapper；只有排查底层编译链路时才直接运行
xelatex等原生命令。 - 运行缓存和中间文件集中到项目约定的位置，优先使用
.bensz-api/或.latex-cache/；不得污染仓库根目录、源码目录或提交无关产物。 - 发布任务使用
scripts/pack_release.py。只有上传命令成功后才能表述为“已发布”；只打包和上传是两个不同状态。
默认约束
语言、搜索与安全
- 默认使用简体中文与用户沟通、写文档和写注释；用户指定语言时遵从用户要求。
- 默认先查本地源码和文档；本地信息不足或用户明确要求时再联网，并核对来源与当前状态。
- 不记录或提交 API Key、访问令牌、密码、Cookie、环境/凭据文件、完整私有 Prompt、个人隐私或不必要的大体积原始数据。
- 文件路径必须规范化并限制在授权项目范围内；外部 URL、网络访问和子进程遵循最小权限，注意路径穿越、SSRF 与命令注入。
- 未经明确要求，不删除、迁移、覆盖用户文件，不向远程服务写入，不创建 Git commit 或分支。
任务工作区
需要落盘的 AI 任务只使用一个任务目录：
./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/。
shared/放任务级输入、跨步骤材料和验证摘要。- 每个实际使用的 Skill 使用独立的
input/、output/、log/子目录。 - 正式源码、文档、计划和交付物仍写入项目约定路径，不放进任务工作区。
- 工作区中不得保存密钥、完整私有 Prompt、个人身份信息或无关原始数据。
首次使用某个 Skill 前，向用户说明“Skill 名称 → 具体工作”；多 Skill 任务说明调用顺序。没有适用 Skill 时也应说明不调用及原因。
BAC 贡献记录
项目默认启用 bensz-auto-contribution 的 bac，账本为 docs/contribution.bac。BAC 用于记录人类、AI 和工具在项目维护中的可核验证据，是过程审计材料，不替代署名、责任或合规判断。
- 开始维护任务时检查 Python、
bac命令和账本状态；账本不存在则初始化，存在则先验证。 - 记录用户需求、AI 计划与产出、关键工具命令、文件改动、人工确认和验证结果；摘要应简短、客观、可脱敏。
- 常用查看入口：
bac --root . --bac-file docs/contribution.bac inspect；完成后用bac --root . --bac-file docs/contribution.bac verify检查账本。 - 不得把密钥、密码、Cookie、完整私有 Prompt、个人隐私、本地用户名/主机名或大体积原始数据写入 BAC。
- 只有项目负责人明确要求时才关闭 BAC；关闭必须在任务记录和交付说明中明确标注，不能静默跳过。
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.
- today Changed · -584 lines · -9,346 tokens per session scan C → A 3170e0447984
- 4d ago Changed · +1 lines · +141 tokens per session 2dd941fde0f1
- 9d ago First seen · 682 lines · 11,286 tokens per session scan C fabd4de82f5e
ChineseResearchLaTeX AGENTS.md is an instructions file published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,711 stars, last pushed yesterday), licensed MIT. It adds 2,081 tokens to every session, about $0.0104 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.