Borrowing it
Nothing to install: this file belongs to axumquant/arch-viewer. 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/axumquant/arch-viewer/main/CLAUDE.mdgit clone --depth 1 https://github.com/axumquant/arch-viewerWrote 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/axumquant/arch-viewer/claude-md)<a href="https://agentmods.dev/instructions/axumquant/arch-viewer/claude-md"><img src="https://agentmods.dev/badge/instructions/axumquant/arch-viewer/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.
<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="Reviewed on agentmods" width="80" 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 | $0.00454 | $0.00454 |
| Opus 5.5 | $0.00182 | $0.00182 |
| Sonnet 5.5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00045 | $0.00045 |
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 2mo 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.
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 viaastmodule, 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--mcpflag).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)
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.
- 2mo ago First seen · 42 lines · 454 tokens per session scan A df2675acda31
arch-viewer CLAUDE.md is an instructions file published in the GitHub repository axumquant/arch-viewer (5 stars, last pushed 3mo ago), licensed MIT. It adds 454 tokens to every session, about $0.0018 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 2026-08-31.
arch-viewer CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| arch-viewer CLAUDE.mdaxumquant/arch-viewer | Instructions file | 5 | 3mo ago | MIT | A | 454 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |