agentmods.dev

AI-fundamentals: Instructions file for Claude Code

CLAUDE.md

AI-fundamentals CLAUDE.md is an instructions file for Claude Code from ForceInjection/AI-fundamentals. It costs 2,970 tokens per session, scanned A, original, Apache-2.0.

Repository-specific instructions for AI Fundamentals, a Chinese-language collection of Markdown lessons about artificial intelligence infrastructure and programming. They describe its structure and writing conventions.

In plain words
What is it for?
Use them when adding, editing, organizing, or committing documentation in the AI Fundamentals repository.
Why use it?
They help keep new or edited learning material in the right place and consistent with the repository’s organization and commit style.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is ForceInjection/AI-fundamentals's own configuration. It tells Claude Code how to work on AI-fundamentals itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AI-fundamentals configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/wangtianqing/Project/ai-infra/vLLM/.

not rated 3.3krepo +87 changed 3d ago A scan 2,970 tokens original Apache-2.0
View source ↗ ForceInjection/AI-fundamentals forceinjection.github.io
About the project

AI Fundamentals is a learning resource about the foundations and infrastructure behind artificial intelligence, including GPU architecture, CUDA programming, large language models, AI systems, and related operations. It is intended for AI engineers, system architects, GPU developers, application developers, and researchers. The catalogue add-ons support learning or working with these AI infrastructure topics.

ForceInjection/AI-fundamentals · 3,324 stars · on GitHub · forceinjection.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to ForceInjection/AI-fundamentals. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ForceInjection/AI-fundamentals/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ForceInjection/AI-fundamentals

Made for: Claude Code.

Wrote 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.

agentmods badge for AI-fundamentals CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/forceinjection/ai-fundamentals/claude-md/github.svg)](https://agentmods.dev/instructions/forceinjection/ai-fundamentals/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/forceinjection/ai-fundamentals/claude-md"><img src="https://agentmods.dev/badge/instructions/forceinjection/ai-fundamentals/claude-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.

agentmods 80×15 button for AI-fundamentals CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/forceinjection/ai-fundamentals/claude-md"><img src="https://agentmods.dev/badge/instructions/forceinjection/ai-fundamentals/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,970 This file is loaded in full into every session.
When invoked 2,970 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02970 $0.02970
Opus 5.5 $0.01188 $0.01188
Sonnet 5.5 $0.00594 $0.00594
Haiku 4.5 $0.00297 $0.00297

Measured 3d ago against content hash 85b144a09254, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AI-fundamentals CLAUDE.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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository overview

AI Fundamentals is a Chinese-language knowledge repository covering the full AI infrastructure stack: GPU architecture, CUDA programming, LLM theory, inference systems, cloud-native AI platforms, agentic systems, RAG, and more. Content is Markdown-first; interactive HTML, PDF/PPTX decks, images, and notebooks live alongside the articles.

  • License: Apache 2.0
  • Structure: semantically numbered top-level directories (01_hardware_architecture/ … 11_ai_native_everything/, plus 98_llm_programming/ and 99_misc/), each with its own README.md portal. 02_dpu_programming/, 02_gpu_programming/, 02_npu_programming/ share the 02_ prefix — all three are sub-modules under "底层计算与异构编程".
  • 99_misc/ hosts standalone project folders (e.g., token_factory_talk/: outline + illustrated article + PPTX + img/ + references/). This "project folder" pattern is reusable for any new talk or long-form deliverable.
  • Directory map: 01_hardware_architecture 硬件架构与互联(GPUDirect/PCIe/NVLink) · 02_dpu_programming DPU/DOCA 编程 · 02_gpu_programming GPU 编程基础(CUDA 范式、显存/跨卡访问与调优) · 02_npu_programming 华为 NPU/CANN 编程 · 03_ai_cluster_ops 集群运维与通信(IB 网络/NCCL/GPU 运维) · 04_cloud_native_ai_platform 云原生 AI(K8s/GPU 池化 HAMi/调度) · 05_model_training_and_fine_tuning 训练与微调(SFT 实践) · 06_llm_theory_and_fundamentals LLM 理论(量化/MoE/Embedding) · 07_rag_and_tools RAG 与工具(KG/GraphRAG/PDF 解析/分块) · 08_agentic_system 智能体(多 Agent/记忆/MCP/上下文工程) · 09_inference_system 推理系统(KV Cache/LMCache/vLLM) · 10_ai_related_course 课程课件与讲稿 · 11_ai_native_everything AI Native 工程实践(FDE 案例) · 98_llm_programming LLM 编程(LangGraph/Spring AI/Harness) · 99_misc 独立项目与杂项
  • AGENTS.md is a stable one-line pointer to this file — Copilot/Trae/Qoder auto-read it, so don't grow it; edit here instead.

Commit conventions

Conventional Commits with Chinese descriptions: docs(scope):, chore(scope):, refactor(scope):, feat(scope):.

Read the full file on GitHub · 108 lines

Changes

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.

  1. 3d ago Changed · +41 tokens per session 85b144a09254
  2. 25d ago Changed · +100 tokens per session f1beaa175652
  3. 1mo ago Changed · -16 lines · +134 tokens per session adb7b101bd47
  4. 1mo ago Changed · +1 lines · +134 tokens per session 5c54f4b3fee3
  5. 1mo ago Changed · +11 lines · +367 tokens per session 49874098e148
  6. 1mo ago Changed · -35 lines · -672 tokens per session a7037f76e5b1
  7. 2mo ago Changed · +15 lines · +694 tokens per session 47b613667afc
  8. 2mo ago First seen · 132 lines · 2,172 tokens per session scan A 326eb8767b4e

Subscribe to this mod's changes

AI-fundamentals CLAUDE.md is an instructions file published in the GitHub repository ForceInjection/AI-fundamentals (3,324 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,970 tokens to every session, about $0.0119 per session on Opus 5.5. 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.

Learning and teachingSGLangai-agentai-infracudavLLM
Related

AI-fundamentals CLAUDE.md compared with instructions from other repositories

AI-fundamentals CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
AI-fundamentals CLAUDE.mdForceInjection/AI-fundamentalsInstructions file3.3kyesterdayApache-2.0A2,970Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode