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/a3rdlab/llm-dev-demo/agents-mdgit clone --depth 1 https://github.com/A3RDLab/LLM-dev-demoWhat 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 | $0.01682 | $0.01682 |
| Opus 5 | $0.00841 | $0.00841 |
| Sonnet 5 | $0.00336 | $0.00336 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
LLM-dev-demo AGENTS.md scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 企业专属实例的 Key 常有模型白名单,跑 demo 前先用 `curl $API_BASE/models` 探测可用模型。 How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Qoder (qoder.com) when working with code in this repository.
仓库性质
这是一个 LLM 应用开发教学实验合集,不是单一应用:每个 demo 是自包含脚本,按学习路线递进(基础调用 → 结构化输出 → Function Calling → LangGraph → Agent Harness → MCP → RAG → Text2SQL → 完整项目)。根目录 实验手册.md 是面向学员的引导式手册,其中的命令均经实机验证——修改 demo 的用法、参数或依赖后,必须同步更新实验手册与相关 README,保持文档与代码一致。
环境与密钥约定
- 密钥一律走仓库根目录
.env(模板见.env.example),切勿硬编码 API Key。关键变量:API_KEY/API_BASE(OpenAI 兼容端点)/MODEL/EMBED_MODEL/DASHSCOPE_API_KEY。 - 所有脚本在启动时用
load_dotenv()按相对路径显式加载根目录.env(子目录脚本用Path(__file__).resolve().parent.parent / ".env"这类写法定位),新增脚本应保持此约定。 - 所有 demo 支持
--model/--api_key/--base_url命令行参数覆盖默认值(默认平台为硅基流动)。切换平台示例:--base_url https://dashscope.aliyuncs.com/compatible-mode/v1 --api_key $DASHSCOPE_API_KEY。 - 企业专属实例的 Key 常有模型白名单,跑 demo 前先用
curl $API_BASE/models探测可用模型。
依赖管理
根目录 requirements.txt 管理公共依赖;子项目独立依赖不得混入根 requirements,各自维护:
| 子项目 | 依赖位置 | 安装/运行 |
|---|---|---|
function_call_and_agent_demo/excel-process/ |
自己的 requirements.txt |
streamlit run app.py(需本机有 Docker,llm-sandbox 基于容器) |
function_call_and_agent_demo/agent_harness_demo/ |
自己的 requirements.txt(deepagents) |
python agent_harness_demo.py |
finance_doc_review/ |
pyproject.toml(uv) |
uv venv .venv --python 3.12 && uv pip install -p .venv/bin/python -e .,然后 finance-doc-review samples/xxx.txt [--json] |
版本约束用 >= 宽松策略,但 mcp[cli] 必须锁 <2:2.0 移除了 mcp.server.fastmcp 高层封装,MCP demo 依赖 1.x。
常用命令
# 根目录脚本(示例)
python first_llm_app.py
python structured_output_demo.py
python mini_rag_demo.py --query "..." --top_k 3 # --rebuild 强制重建向量索引
python text2sql_demo.py # 依赖根目录 Chinook.sqlite
python wiki_kb_agent_demo/kb_agent.py --once "问题"
# Function Calling / Agent
python function_call_and_agent_demo/demo-agent-with-tools-arg.py
python function_call_and_agent_demo/langgraph_demo/langgraph_agent_scaffold.py --query "..."
python function_call_and_agent_demo/mcp_server_demo.py # MCP 服务端
python function_call_and_agent_demo/mcp_client_agent_demo.py # MCP 客户端 agent
# Streamlit 应用
streamlit run function_call_and_agent_demo/excel-process/app.py
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.
- 2d ago First seen · 69 lines · 1,682 tokens per session scan A a9fe52ef28d7
LLM-dev-demo AGENTS.md is an instructions file published in the GitHub repository A3RDLab/LLM-dev-demo (44 stars, last pushed 10d ago), licensed Apache-2.0. It adds 1,682 tokens to every session, about $0.0084 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
designing-real-world-ai-agents-workshop CLAUDE.md
Instructions for iusztinpaul/designing-real-world-ai-agents-workshop, covering project, project structure, tech stack, access documentation and running qa.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
Instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
paper-pilot CLAUDE.md
Instructions for aytzey/paper-pilot, covering claude.md, best fit, setup, first workflow to try and claude prompt patterns.