drag-mcp-server: Instructions file for Claude Code

CLAUDE.md

drag-mcp-server CLAUDE.md is an instructions file for Claude Code from nick-timms/drag-mcp-server. It costs 1,133 tokens per session, scanned A, original, MIT.

Project instructions for developing and publishing a public DragApp MCP server. An MCP server lets AI clients use tools, while the instructions also define rules for protecting secrets and private information.

In plain words
What is it for?
They are for implementing, documenting, testing, and releasing the DragApp shared-inbox server while keeping public repository contents safe.
Why use it?
They reduce the risk of exposing credentials, internal system details, or other information in source code, tests, documentation, commits, or published packages.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is nick-timms/drag-mcp-server's own configuration. It tells Claude Code how to work on drag-mcp-server 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 drag-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nick-timms/drag-mcp-server. 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/nick-timms/drag-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nick-timms/drag-mcp-server

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 drag-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nick-timms/drag-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/nick-timms/drag-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nick-timms/drag-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/nick-timms/drag-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,133 This file is loaded in full into every session.
When invoked 1,133 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01133 $0.01133
Opus 5 $0.00566 $0.00566
Sonnet 5 $0.00227 $0.00227
Haiku 4.5 $0.00113 $0.00113

Measured 6d ago against content hash 80dd06308c66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

drag-mcp-server 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 6d 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 · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DragApp MCP Server

MCP server exposing DragApp shared-inbox tools to AI clients. TypeScript, published to npm as @dragapp/mcp-server.

⚠️ Guardrails — this repository is PUBLIC

Everything here — every file, every commit, every published npm tarball — is world-readable. Treat it that way. The git history was reset once already to remove leaked internal details; do not reintroduce them.

Never reference private repo names or internal backend symbols in code, comments, tests, docs, or commit messages. The canonical list of blocked terms is maintained outside this repository (a private CI secret and an untracked local file), so it is never itself published here.

When you need to explain why the code does something, describe the observable behavior of the public API (https://app.dragapp.com) — not the internal system that produces it. "The backend returns X" is fine; naming a private repo or an internal class/function is not.

Never hardcode credentials. All secrets come from the environment — always process.env.DRAG_API_KEY, never a literal token or key. There are no exceptions, including in tests or examples (use obvious placeholders like your-api-key).

Never commit .env. Only .env.example (placeholders) is tracked. Real .env, *.pem, *.hex, *.key, and *privkey* files must never be staged.

Mechanical enforcement

These guardrails are backed by tooling so they can't be bypassed by accident:

  • .gitignore — blocks .env, key material, the private term list, and build artifacts from ever being staged.
  • Pre-commit hook (.pre-commit-config.yaml + .gitleaks.toml) — gitleaks scans staged changes for generic secrets (keys, JWTs, tokens). Install with pip install pre-commit && pre-commit install.
  • prepublishOnly tarball guard (scripts/check-tarball.mjs) — npm publish packs the tarball, greps every shipped file (including source maps) for the private term list, and aborts if any are found. This is the check that would have caught the original npm leak (comments survive into compiled output).
  • CI (.github/workflows/secret-scan.yml) — gitleaks runs on every push and pull request, plus a term scan driven by the private list.

Read the full file on GitHub · 42 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. 6d ago First seen · 42 lines · 1,133 tokens per session scan A 80dd06308c66

Subscribe to this mod's changes

drag-mcp-server CLAUDE.md is an instructions file published in the GitHub repository nick-timms/drag-mcp-server (1 stars, last pushed 4d ago), licensed MIT. It adds 1,133 tokens to every session, about $0.0057 per session on Opus 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

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens