Borrowing it
Nothing to install: this file belongs to adawalli/nexus. 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/adawalli/nexus/main/CLAUDE.mdgit clone --depth 1 https://github.com/adawalli/nexusWrote 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/adawalli/nexus/claude-md)<a href="https://agentmods.dev/instructions/adawalli/nexus/claude-md"><img src="https://agentmods.dev/badge/instructions/adawalli/nexus/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/adawalli/nexus/claude-md"><img src="https://agentmods.dev/badge/instructions/adawalli/nexus/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 | $0.00455 | $0.00455 |
| Opus 5.5 | $0.00182 | $0.00182 |
| Sonnet 5.5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
nexus 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
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Nexus MCP is a Model Context Protocol server providing AI-powered web search via OpenRouter's Perplexity Sonar models. It's designed for zero-install deployment via npx nexus-mcp.
Essential Commands
bun run dev # Watch mode with type checking
bun run build # Production build
bun run test # Full test suite (unit + integration)
bun run test:unit # Unit tests only
bun run test:watch # Watch mode for development
# Single test execution
bun run test -- tests/unit/clients/openrouter.test.ts
bun run test -- --grep "OpenRouter"
Architecture
Request Flow
Client Request → STDIO Transport → MCP Server (src/index.ts)
→ Correlation ID → Input Validation (Zod) → Deduplication → Cache Check
→ OpenRouter Client (src/clients/openrouter.ts) → Response Optimization
→ Structured Response with Metadata
Key Directories
src/index.ts- MCP server entry point with tool/resource handlerssrc/tools/search.ts- Search tool with caching, deduplication, retry logicsrc/clients/openrouter.ts- OpenRouter API client with error handlingsrc/config/- Configuration management with JSON schema validationsrc/utils/- Shared utilities (caching, deduplication, error handling, logging)src/schemas/- Zod validation schemassrc/types/- TypeScript type definitions
Testing Structure
tests/unit/- Component tests with mockingtests/integration/- End-to-end MCP server teststests/fixtures/- Test data and mock responses- Coverage threshold: 80%
Environment Variables
OPENROUTER_API_KEY- Required for OpenRouter API accessNODE_ENV- Environment (development, production, test)LOG_LEVEL- Logging verbosity (debug, info, warn, error)
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 · 56 lines · 455 tokens per session scan A 18f169bf9fdd
nexus CLAUDE.md is an instructions file published in the GitHub repository adawalli/nexus (21 stars, last pushed 16d ago), licensed MIT. It adds 455 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 2026-08-30.
nexus CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nexus CLAUDE.mdadawalli/nexus | Instructions file | 21 | 16d ago | MIT | A | 455 | 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 |