qurl-mcp: Instructions file for Claude Code

CLAUDE.md

qurl-mcp CLAUDE.md is an instructions file for Claude Code from layervai/qurl-mcp. It costs 4,557 tokens per session, scanned A, original, MIT.

Repository instructions for Claude Code, an AI coding assistant, covering project rules, architecture, and the required code-change process.

In plain words
What is it for?
Use it when making code changes in the qurl-mcp project, including creating branches, running checks, opening pull requests, and responding to review feedback.
Why use it?
It helps prevent changes that violate the repository’s contribution rules, such as pushing directly to the main branch or creating unsigned commits.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is layervai/qurl-mcp's own configuration. It tells Claude Code how to work on qurl-mcp 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 qurl-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to layervai/qurl-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.

Copy the file
curl -O https://raw.githubusercontent.com/layervai/qurl-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/layervai/qurl-mcp

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 qurl-mcp CLAUDE.md

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

agentmods 80×15 button for qurl-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/layervai/qurl-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/layervai/qurl-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,557 This file is loaded in full into every session.
When invoked 4,557 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.04557 $0.04557
Opus 5.5 $0.01823 $0.01823
Sonnet 5.5 $0.00911 $0.00911
Haiku 4.5 $0.00456 $0.00456

Measured 12d ago against content hash 0353952d33f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qurl-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 12d 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 · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

CRITICAL RULES - NEVER VIOLATE

NEVER push directly to main branch. All changes MUST go through a Pull Request, no exceptions. This applies even for "quick fixes" or "urgent" changes. Create a branch, open a PR, and let CI run.

All commits must be GPG/SSH signed. Unsigned commits will be rejected by GitHub branch protection rules.

Code Change Workflow

Follow this process for all code changes:

  1. Switch to main and fetch latest

    git checkout main && git pull origin main
    
  2. Create branch for code change

    git checkout -b <type>/<short-description>
    
  3. Make code changes - Think deeply about the implementation. Consider edge cases, error handling, and maintainability.

  4. Run checks before committing

    npm run build && npm run lint && npm test
    
  5. Create a PR

    git push -u origin <branch>
    gh pr create --title "<type>(scope): description" --body "..."
    
  6. Wait for code review feedback - CI runs automatically. Review comments will be posted on the PR.

  7. Address review feedback - Think critically about each suggestion.

  8. Update the PR - Push fixes, update PR description if needed.

  9. Repeat steps 6-8 until feedback requires no further action.


Project Overview

qURL MCP Server is a TypeScript Model Context Protocol server that exposes qURL operations as tools for AI agents. It supports local stdio and authenticated Streamable HTTP transports, and communicates with the qURL API plus an optional upload connector.

Architecture

qurl-mcp/
├── src/
│   ├── index.ts           # Entry point, env validation, stdio transport (API key or local CLI)
│   ├── qurl-cli.ts        # Bounded runner for the local qURL CLI (no-account stdio mode)
│   ├── http.ts            # Authenticated HTTP transport and runtime wiring
│   ├── http-sessions.ts   # Session registry, expiry, disconnect grace, and teardown
│   ├── http-public-routes.ts # Public legal/video routes, rate limits, and streaming
│   ├── http-config.ts     # Bounded listener/session/proxy configuration
│   ├── config.ts          # Shared qURL, connector, SMTP, and media config
│   ├── server.ts          # MCP server factory, tool/resource/prompt registration
│   ├── client.ts          # Adapter over the @layervai/qurl SDK (IQURLClient + QURLAPIError)
│   ├── tools/
│   │   ├── _shared.ts       # resourceIdSchema, zodErrorToToolResult
│   │   ├── duration.ts      # Duration grammar and bounds mirrored from qurl-service
│   │   ├── upload-mint-options.ts # Shared upload link options and descriptions
│   │   ├── create-qurl.ts
│   │   ├── consumer-access.ts # Private publishing, invitations, and consumer grants
│   │   ├── local-cli.ts     # No-account tools that run the local qURL CLI
│   │   ├── resolve-qurl.ts
│   │   ├── list-qurls.ts
│   │   ├── get-qurl.ts
│   │   ├── delete-qurl.ts
│   │   ├── extend-qurl.ts
│   │   ├── update-qurl.ts
│   │   ├── share-by-crid.ts
│   │   ├── mint-link.ts
│   │   ├── batch-create.ts
│   │   ├── revoke-qurl-token.ts
│   │   ├── update-qurl-token.ts
│   │   ├── list-qurl-sessions.ts
│   │   ├── terminate-qurl-sessions.ts
│   │   └── upload-*.ts    # File/data/text upload workflows
│   ├── auth/
│   │   ├── request-context.ts # Request-scoped credentials and validation state
│   │   └── static-bearer.ts   # Passthrough bearer verifier/client construction
│   ├── services/
│   │   ├── email.ts       # Policy-controlled SMTP delivery and quotas
│   │   ├── text-pdf.ts    # Bounded text-to-PDF generation
│   │   ├── html.ts        # Shared HTML escaping
│   │   ├── legal-pages.ts # Static legal document rendering
│   │   └── video-page.ts  # Optional public video page rendering
│   ├── resources/
│   │   ├── links.ts
│   │   └── usage.ts
│   └── prompts/
│       ├── secure-a-service.ts
│       ├── audit-links.ts
│       └── rotate-access.ts
├── dist/                  # Compiled output (gitignored)
├── package.json
└── tsconfig.json

Read the full file on GitHub · 316 lines

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. 12d ago Changed · +10 lines · +161 tokens per session 0353952d33f3
  2. 13d ago Changed · +7 lines · +299 tokens per session 119a45c0bf88
  3. 1mo ago Changed · +9 lines · +178 tokens per session fb671becc151
  4. 1mo ago Changed · +3 lines · +75 tokens per session 425b7db1a6aa
  5. 1mo ago Changed · +13 lines · +229 tokens per session f90117e48220
  6. 1mo ago Changed · +1 lines · +24 tokens per session 0980a288a713
  7. 2mo ago First seen · 273 lines · 3,591 tokens per session scan A 2b3d67497223

Subscribe to this mod's changes

qurl-mcp CLAUDE.md is an instructions file published in the GitHub repository layervai/qurl-mcp (4 stars, last pushed today), licensed MIT. It adds 4,557 tokens to every session, about $0.0182 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.

Related

qurl-mcp CLAUDE.md compared with instructions from other repositories

qurl-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
qurl-mcp CLAUDE.mdlayervai/qurl-mcpInstructions file4todayMITA4,557Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file281ktodayMITA4,335Codex, OpenCode