agentmods.dev

mcpx: Instructions file for Claude Code

CLAUDE.md

mcpx CLAUDE.md is an instructions file for Claude Code from arcadeai-labs/mcpx. It costs 424 tokens per session, scanned A, original, MIT.

Project instructions for mcpx, a command-line tool for working with MCP servers. They define its commands, coding rules, and documentation requirements.

In plain words
What is it for?
Running development, test, lint, format, and build commands; updating the CLI; and maintaining its README and related agent instructions.
Why use it?
They give coding agents the project’s expected workflow and help keep versioning, diagnostics, tests, formatting, and documentation consistent.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is arcadeai-labs/mcpx's own configuration. It tells Claude Code how to work on mcpx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcpx configures →

not rated 37repo 21d ago A scan 424 tokens original MIT
View source ↗ arcadeai-labs/mcpx
Reuse

Borrowing it

Nothing to install: this file belongs to arcadeai-labs/mcpx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arcadeai-labs/mcpx/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/arcadeai-labs/mcpx

Made for: Claude Code.

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 mcpx CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arcadeai-labs/mcpx/claude-md/github.svg)](https://agentmods.dev/instructions/arcadeai-labs/mcpx/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/arcadeai-labs/mcpx/claude-md"><img src="https://agentmods.dev/badge/instructions/arcadeai-labs/mcpx/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.

agentmods 80×15 button for mcpx CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/arcadeai-labs/mcpx/claude-md"><img src="https://agentmods.dev/badge/instructions/arcadeai-labs/mcpx/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 424 This file is loaded in full into every session.
When invoked 424 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00424 $0.00424
Opus 5.5 $0.00170 $0.00170
Sonnet 5.5 $0.00085 $0.00085
Haiku 4.5 $0.00042 $0.00042

Measured 2mo ago against content hash 6d034f2d7980, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpx CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

mcpx — A CLI for MCP servers. "curl for MCP."
CLAUDE.md · 23 lines

What it actually says

CLAUDE.md

Project

mcpx — A CLI for MCP servers. "curl for MCP."

Commands

  • bun run dev — Run in development mode
  • bun test — Run tests
  • bun lint — Check formatting and types
  • bun format — Auto-fix formatting
  • bun run build — Build single binary

Rules

  • Always bump the patch version in package.json when making any code changes (source, tests, config). Use semver: patch for fixes/small changes, minor for new features, major for breaking changes.
  • Always keep README.md, .claude/skills/mcpx.md, and .cursor/rules/mcpx.mdc in sync with any CLI changes (commands, flags, syntax, examples). Both skill files include workflow steps, code examples, and a command table that must all reflect the current CLI surface.
  • Always run bun run format before committing to fix formatting issues.
  • Always use the logger (src/output/logger.ts) for diagnostic output instead of process.stderr.write or raw console.error/console.warn. The logger is spinner-aware and respects JSON/TTY/log-level configuration. Use logger.error / logger.warn / logger.info / logger.debug for line-oriented messages, or logger.writeRaw when you need to preserve hand-rolled ANSI / newlines (e.g., interactive prompts). console.log for structured stdout output is still fine.
  • Never merge or auto-merge a PR without explicit human approval. Create the PR and report the URL, but do not merge it. The human will review and merge manually.
  • When a PR closes a GitHub issue, include Closes <issue URL> in the PR body (e.g., Closes https://github.com/arcadeai-labs/mcpx/issues/29). This lets GitHub auto-close the issue when the PR is merged.
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. 2mo ago First seen · 23 lines · 424 tokens per session scan A 6d034f2d7980

Subscribe to this mod's changes

mcpx CLAUDE.md is an instructions file published in the GitHub repository arcadeai-labs/mcpx (37 stars, last pushed 21d ago), licensed MIT. It adds 424 tokens to every session, about $0.0017 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsWriting and docs
Related

mcpx CLAUDE.md compared with instructions from other repositories

mcpx CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcpx CLAUDE.mdarcadeai-labs/mcpxInstructions file3721d agoMITA424Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode