agentmods.dev

arch-viewer CLAUDE.md

arch-viewer CLAUDE.md is an instructions file for coding agents from axumquant/arch-viewer. It costs 454 tokens per session, scanned A, original, MIT.

Project instructions for arch-viewer, a tool that examines a codebase’s structure and displays it in an interactive dashboard. It analyzes functions, classes, imports, dependencies, code quality, and maintainability in Python, JavaScript, and TypeScript projects.

In plain words
What is it for?
Use it when analyzing a repository’s architecture, finding dependency relationships or structural problems, checking project health, or working with the arch-viewer dashboard.
Why use it?
It gives an agent the project’s architecture, important modules, commands, and conventions so it can work on the codebase without guessing.

Instructions file

not rated 1 1mo ago A scan 454 tokens original MIT
View the source file axumquant/arch-viewer
Install

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.

agentmods
npx agentmods add instructions/axumquant/arch-viewer/claude-md
Clone the repo
git clone --depth 1 https://github.com/axumquant/arch-viewer

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 arch-viewer CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/axumquant/arch-viewer/claude-md.svg)](https://agentmods.dev/instructions/axumquant/arch-viewer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/axumquant/arch-viewer/claude-md"><img src="https://agentmods.dev/badge/instructions/axumquant/arch-viewer/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 454 This file is loaded in full into every session.
When invoked 454 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00454 $0.00454
Opus 5 $0.00227 $0.00227
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00045 $0.00045

Measured 3d ago against content hash df2675acda31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arch-viewer 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.

CLAUDE.md · 42 lines

What it actually says

arch-viewer

MCP-native architecture viewer with AI-powered codebase analysis, AST parsing, architecture scoring, dependency graphs, and interactive dashboard.

Architecture

  • Python package (arch_viewer/) — MCP server with 17 tools, AI agent (pydantic-ai), AST analyzer, scoring engine, dependency graph builder, aiohttp web server
  • Node.js server (src/) — Zero-dep express dashboard with WebSocket file watching (subset of Python features)
  • Web dashboard (web/index.html) — Single-file enhanced dashboard with settings modal for API keys + model selection

Key Modules

  • ast_analyzer.py — Python AST via ast module, JS/TS via regex heuristics. Extracts functions, classes, imports, exports, cyclomatic complexity.
  • scoring.py — 0-100 health score across 4 categories (Modularity, Code Quality, Maintainability, Structure). Anti-pattern detection.
  • dep_graph.py — Builds import/call/package/component graphs. Hotspot analysis, isolated node detection.
  • agent.py — pydantic-ai agent with 4 providers (Ollama Cloud, OpenAI, Anthropic, Groq). API keys in .arch-viewer.keys.json.
  • mcp_server.py — 17 MCP tools. MCP mode is default (no --mcp flag).
  • scanner.py — Static scanner. Component detection, route extraction, dependency collection.

Commands

# Node.js dashboard
npm start                    # http://localhost:3777

# Python MCP server (full features)
python -m arch_viewer        # MCP + dashboard
python -m arch_viewer --web  # dashboard only
python -m arch_viewer --scan # JSON output

Provider priority

ollama > openai > anthropic > groq (auto-detected from available keys)

Conventions

  • Online providers only — no local model support
  • API keys stored in .arch-viewer.keys.json (gitignored)
  • Python 3.11+, Node 18+
  • Ruff for Python linting (line-length 100)
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 First seen · 42 lines · 454 tokens per session scan A df2675acda31

Subscribe to this mod's changes

arch-viewer CLAUDE.md is an instructions file published in the GitHub repository axumquant/arch-viewer (1 stars, last pushed 1mo ago), licensed MIT. It adds 454 tokens to every session, about $0.0023 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.

Analytics and metricsarchitecturecode-analysismcpneo4jvisualization
Related

Other instructions, from other repositories

truecourse CLAUDE.md

Claude Code instructions for truecourse-ai/truecourse, covering truecourse — claude instructions, key files to keep updated, project layout, development commands and storage.

truecourse-ai/truecourse · 7,282 tokens

truecourse AGENTS.md

AGENTS.md instructions for truecourse-ai/truecourse, covering truecourse — codex instructions, key files to keep updated, project layout, development commands and rules.

truecourse-ai/truecourse · 689 tokens

codebase-intelligence CLAUDE.md

Instructions for bntvllnt/codebase-intelligence, covering codebase intelligence - claude code rules, project overview, architecture, pipeline and key conventions.

bntvllnt/codebase-intelligence · 2,108 tokens

codebase-intelligence AGENTS.md

Instructions for bntvllnt/codebase-intelligence, covering codebase intelligence, setup, interfaces, mcp (for ai agents — preferred) and cli (for humans and ci).

bntvllnt/codebase-intelligence · 1,066 tokens

ckb CLAUDE.md

Claude Code instructions for SimplyLiz/ckb, covering claude.md, build & test commands, build, run all tests and run tests for a specific package.

SimplyLiz/ckb · 2,614 tokens

DotNetAnalyzer CLAUDE.md

Claude Code instructions for CartapenaBark/DotNetAnalyzer, covering claude.md, 常用命令, 构建和测试, 打包和安装 and mcp 服务器.

CartapenaBark/DotNetAnalyzer · 584 tokens