Borrowing it
Nothing to install: this file belongs to lijiawei255/agent-edu-reviewkit. 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/lijiawei255/agent-edu-reviewkit/main/AGENTS.mdgit clone --depth 1 https://github.com/lijiawei255/agent-edu-reviewkitWrote 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/lijiawei255/agent-edu-reviewkit/agents-md)<a href="https://agentmods.dev/instructions/lijiawei255/agent-edu-reviewkit/agents-md"><img src="https://agentmods.dev/badge/instructions/lijiawei255/agent-edu-reviewkit/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 5.1 | $0.02157 | $0.02157 |
| Opus 5 | $0.01078 | $0.01078 |
| Sonnet 5 | $0.00431 | $0.00431 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
agent-edu-reviewkit 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 指令
项目概述
本项目（agent-edu-reviewkit）是一个跨平台 AI 技能，将课程原始课件（PDF/PPTX/DOCX）转化为图文并茂的高质量交互式 HTML 考试复习文档。输出为单个自包含 HTML 文件，包含 MathJax 数学排版、内联 SVG 示意图、课件原图、完整公式推导、例题详解、交互式学习组件（可折叠推导、选项卡视图、练习测验、术语闪卡、进度追踪）、答题模板和常见错误附录。
主要技能
完整技能定义：skills/course-review-guide/SKILL.md
请按照该文件中的 6 个 Phase 逐步执行。以下为不同 Agent 平台的特化适配说明。
Agent 平台兼容性
| 平台 | 优先级 | 配置文件 | 交互模式 | 视觉能力 |
|---|---|---|---|---|
| Claude Code | P0 | CLAUDE.md | 完整交互 | 原生视觉 + MCP |
| Codex | P0 | 自定义 Prompt | 完整交互 | 有限 |
| OpenCode | P1 | AGENTS.md, opencode.json | 完整交互 | 取决于模型 |
| OpenClaw/Hermes | P2 | AGENTS.md | 自主（有限交互） | 取决于模型 |
OpenCode 适配（P1）
OpenCode 是一款开源、终端优先、模型无关的 AI 编程智能体。以下为 OpenCode 运行本技能时的适配要点：
工具映射
| 操作 | Claude Code 写法 | OpenCode 写法 |
|---|---|---|
| 扫描课件文件 | Bash("ls ...") |
使用 Glob 模式扫描，如 Glob("**/*.pdf") |
| 读取提取文本 | Read 工具 |
同样使用 Read 工具 |
| 写入 HTML 文件 | Write 工具 |
同样使用 Write 工具 |
| 运行 Python 脚本 | Bash("python ...") |
Bash("python3 ...")（优先使用 python3） |
| MCP 视觉工具 | ListMcpResourcesTool + MCP |
OpenCode 不使用 MCP 资源列表；直接尝试图片读取 |
特殊注意
- 图片识别：OpenCode 可能不包含 MCP 视觉服务器。碰到纯图片课件时，直接尝试用模型视觉能力读取图片，如不可用则按 skill 文件中的 Level 3 降级策略处理。
- 用户交互：OpenCode 支持完整交互式会话，Phase 1 的范围确认步骤按原流程执行，无需跳过。
- 自定义 Agent：本项目提供了
opencode.json中的course-reviewagent 定义，可通过 OpenCode 的 agent 系统直接调用。
自主模式：OpenClaw / Hermes 适配（P2）
OpenClaw 和 Hermes 是 Claw 类自主化智能体，通过消息应用（WhatsApp、Telegram、Discord、Slack）运行，不保证回合制用户交互。以下为自主模式下的 Phase 适配策略。
核心原则
- 永远不要等待交互式用户响应 — 使用"检查是否存在"、"推断自"替代"询问用户"
- 推断值一律标记 — 所有自动推断的信息标注
[自动推断 - 请验证] - 渐进式失败 — 部分完成优于完全停止，缺失部分在输出中明确标注
Phase 1 替代方案：考试范围确定
采用三级范围确定策略：
| 级别 | 方法 | 需要交互 | 可靠性 |
|---|---|---|---|
| 1 | 读取课件目录中的 exam-scope.json |
不需要 | 高 |
| 2 | 从文件名和内容推断范围 | 不需要 | 中 |
| 3 | 通过消息通道请求数据并等待 | 需要（异步） | 高 |
Level 1 — exam-scope.json 配置文件
在课件目录中放置 exam-scope.json，格式参见项目根目录的 exam-scope-template.json。如找到此文件，读取所有配置值作为 Phase 1 的结果，跳过交互确认。
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.
- 7d ago First seen · 154 lines · 2,157 tokens per session scan A 64bcf19dbf1b
agent-edu-reviewkit AGENTS.md is an instructions file published in the GitHub repository lijiawei255/agent-edu-reviewkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,157 tokens to every session, about $0.0108 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
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).
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.