Borrowing it
Nothing to install: this file belongs to xenarch-ai/xenarch-mcp. 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/xenarch-ai/xenarch-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/xenarch-ai/xenarch-mcpWrote 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/xenarch-ai/xenarch-mcp/claude-md)<a href="https://agentmods.dev/instructions/xenarch-ai/xenarch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/xenarch-ai/xenarch-mcp/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/xenarch-ai/xenarch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/xenarch-ai/xenarch-mcp/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 | $0.00445 | $0.00445 |
| Opus 5.5 | $0.00178 | $0.00178 |
| Sonnet 5.5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
xenarch-mcp 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
xenarch-mcp
MCP (Model Context Protocol) servers for Xenarch. Lets AI agents discover and pay for content, and lets publishers manage their pricing.
Structure
Monorepo with three packages:
packages/
agent/ — MCP server for AI agents (discover content, make payments)
publisher/ — MCP server for publishers (manage pricing, view earnings)
shared/ — Shared types and utilities
Stack
- TypeScript, @modelcontextprotocol/sdk
- Package manager: npm (workspaces)
Commands
- Build:
npm run build - Test:
npm test - Publish agent:
npm publish --workspace packages/agent - Publish publisher:
npm publish --workspace packages/publisher
Design Principle
These are thin API clients to the xenarch.dev backend. No business logic lives here — just MCP tool definitions that call the platform API.
Workflow
See root ../CLAUDE.md for branching, PR, and commit conventions.
First Run Check
On first interaction with a contributor, verify git hooks are set up by checking git config core.hooksPath. If it doesn't return .githooks, tell the contributor:
"This project requires git hooks for commit message enforcement. Can I run
git config core.hooksPath .githooksto enable them?"
Do not proceed with any code changes until hooks are confirmed active.
Architecture
See ../Information/design/mcp-servers.md for MCP server design.
Dev workflow & prod deploy baton
Follow the canonical workspace workflow in ../Information/workflow.md (Retasc issue → claim → worktree → PR → deploy → validate on prod → merge-commit, never squash).
Parallel sessions: before any kamal deploy of platform or dashboard, claim the per-service deploy baton in Retasc issue XEN-524 (via its append-only CLAIM/RELEASE comment log) and merge main into your branch first — one session validates on a given prod service at a time. See ../Information/workflow.md → "Parallel sessions — prod deploy baton".
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 · 53 lines · 445 tokens per session scan A a11433008da0
xenarch-mcp CLAUDE.md is an instructions file published in the GitHub repository xenarch-ai/xenarch-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 445 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.
xenarch-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xenarch-mcp CLAUDE.mdxenarch-ai/xenarch-mcp | Instructions file | 1 | 3mo ago | MIT | A | 445 | 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 |