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/khaitrang1995/claude-code-architecture/claude-mdgit clone --depth 1 https://github.com/KhaiTrang1995/claude-code-architectureWrote 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/khaitrang1995/claude-code-architecture/claude-md)<a href="https://agentmods.dev/instructions/khaitrang1995/claude-code-architecture/claude-md"><img src="https://agentmods.dev/badge/instructions/khaitrang1995/claude-code-architecture/claude-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 | $0.01723 | $0.01723 |
| Opus 5 | $0.00861 | $0.00861 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
claude-code-architecture 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 4d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
File này được Claude Code load tự động mỗi phiên làm việc.
This file is automatically loaded by Claude Code at the start of every session.
Tổng quan Dự án · Project Overview
claude-code-architecture — Tài liệu phân tích kiến trúc hệ thống Claude Code + thư viện scaffold claude-code-structure.
Architecture analysis documentation for the Claude Code system + the claude-code-structure scaffold library.
- Repo:
github.com/KhaiTrang1995/claude-code-architecture - Ngôn ngữ · Languages: Markdown, HTML, JavaScript, Python
- Package Manager: npm (Node.js ≥18), pip (Python ≥3.9)
- License: MIT
- Author: TechSphereX TA
Cấu trúc Dự án · Project Structure
claude-code-architecture/
├── README.md ← Main README (bilingual VI/EN)
├── CLAUDE.md ← File này · This file
├── claude-code-architecture.md ← Kiến trúc 6 layer · 6-layer architecture
├── architecture-visual.html ← Trực quan hóa HTML · Visual HTML
├── architecture.md ← Hướng dẫn build · Build guide
├── structủe-readme.md ← README cho thư viện npm/pip · Library README
└── .github/
├── CONTRIBUTING.md ← Hướng dẫn đóng góp · Contributing guide
├── SECURITY.md ← Chính sách bảo mật · Security policy
└── CODE_OF_CONDUCT.md ← Quy tắc ứng xử · Code of conduct
Lệnh thường dùng · Common Commands
# Scaffold dự án mới · Scaffold a new project
npx claude-code-structure ./my-project
# Python alternative
pip install claude-code-structure
claude-init ./my-project
# Build npm package
cd packages/npm && npm pack
# Build Python package
cd packages/python && python -m build
# Chạy tests · Run tests
npm test # npm package
pytest # Python package
Quy tắc Tài liệu · Documentation Rules
- Tất cả tài liệu phải song ngữ Việt/Anh · All docs must be bilingual Vietnamese/English
- Format:
Tiếng Việt · *English translation*cho headings - Format:
Nội dung Việt\n*English content*cho paragraphs - Sử dụng Mermaid cho diagrams · Use Mermaid for diagrams
- Emoji được dùng cho layer numbers (①②③④⑤⑥) · Emoji used for layer numbering
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.
- 4d ago First seen · 143 lines · 1,723 tokens per session scan A 7be6ba5c6372
claude-code-architecture CLAUDE.md is an instructions file published in the GitHub repository KhaiTrang1995/claude-code-architecture (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,723 tokens to every session, about $0.0086 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
agentic-ai-learning-journey CLAUDE.md
Instructions for JSchOBL/agentic-ai-learning-journey, covering agentic ai learning journey, layout, conventions, non-negotiable and gotchas.
skills CLAUDE.md
Claude Code instructions for foyzulkarim/skills, covering claude.md, what this repo is, the 5-phase pipeline + qa gate, plugin structure and the pipeline.
skills AGENTS.md
AGENTS.md instructions for foyzulkarim/skills, covering agents.md — foyzulkarim/skills, repo nature, developer commands, local testing workflow (scripts/sync-skills.sh) and pipeline artifacts on master.
ClaudeMarketplace CLAUDE.md
Claude Code instructions for RealDougEubanks/ClaudeMarketplace, covering claude code skills marketplace — project context, contribution conventions, pre-commit checklist (mandatory — run before every commit) and golden rules.
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).
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.