downloader-mcp: Instructions file for Codex

AGENTS.md

downloader-mcp AGENTS.md is an instructions file for Codex, OpenCode from CarlDog/downloader-mcp. It costs 2,046 tokens per session, scanned A, original, MIT.

Project instructions for downloader-mcp, a Docker-based server that connects download clients such as SABnzbd and qBittorrent to other software. They describe the project’s status, technology choices, and design decisions.

In plain words
What is it for?
Orienting agents before making changes to downloader-mcp. They help with its TypeScript code, API connections, Docker setup, and project status.
Why use it?
They give coding agents one consistent source of project context and explain why the two download clients do not share a common code base.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is CarlDog/downloader-mcp's own configuration. It tells Codex and OpenCode how to work on downloader-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 downloader-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to CarlDog/downloader-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/CarlDog/downloader-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/CarlDog/downloader-mcp

Made for: Codex, OpenCode.

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 downloader-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/carldog/downloader-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/carldog/downloader-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,046 This file is loaded in full into every session.
When invoked 2,046 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 $0.02046 $0.02046
Opus 5 $0.01023 $0.01023
Sonnet 5 $0.00409 $0.00409
Haiku 4.5 $0.00205 $0.00205

Measured 8d ago against content hash 6fa58552e827, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

downloader-mcp AGENTS.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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

downloader-mcp

MCP server for download clients (SABnzbd, qBittorrent), packaged as a Docker container. Designed as a companion to media-management MCPs like servarr-mcp.

Status

Single source of truth: STATUS.md. Do not duplicate status into this file, MEMORY.md, or Serena memories — reference STATUS.md.

Current Sprint

Phase: deployed and verified (NAS) — see STATUS.md for the active phase, what's done, and what's next.

Stack

  • TypeScript (Node 22+, ESM, NodeNext module resolution)
  • @modelcontextprotocol/sdk (high-level McpServer API)
  • zod for tool input schemas
  • Each client uses its own auth/HTTP shape (no shared base — see below)
  • Docker multi-stage build (alpine, non-root user mcp)

Why no shared base class

Unlike servarr-mcp (where Sonarr/Radarr/Lidarr/Readarr/Prowlarr share a v1/v3 REST + X-Api-Key shape), SABnzbd and qBittorrent have nothing in common at the API layer:

  • SABnzbd: query-string GET API (/api?mode=queue&apikey=X&output=json). Single endpoint, mode-driven dispatch.
  • qBittorrent: REST-ish (/api/v2/...) with a static Authorization: Bearer <API key> header on every request.

Each client is fully self-contained in its own file. Adding a third client (Deluge, Transmission, NZBGet, etc.) means a new file and a new optional registration in src/index.ts — no inheritance refactor.

Layout

  • src/index.ts — MCP server entry. Computes which clients are enabled from env vars at startup, then decides transport (stdio vs HTTP) based on MCP_PORT. Per-session McpServer instances via the createServer() factory.
  • src/mcp-route.ts — the Streamable HTTP /mcp route: bearer auth, per-session transport map, idle sweep, session dispatch. Split out of index.ts so it can be imported by a test — index.ts self-executes on import (and exit(1)s with no client configured), so nothing in it was reachable without booting a server. Covered by src/mcp-route.test.ts.
  • src/util.tsasText(), redactSecrets(), and fetchWithCause() (wraps fetch so a network-level failure surfaces its real cause instead of the generic fetch failed), all shared by both clients.
  • src/sabnzbd.tsSabnzbdClient + registerSabnzbdTools.
  • src/qbittorrent.tsQBittorrentClient (static Bearer API-key auth) + registerQbittorrentTools.
  • Dockerfile — multi-stage build (alpine, non-root user).
  • docker-compose.yml — Compose/Portainer deployment using HTTP transport.
  • .githooks/pre-commit — gitleaks + PII pattern scan.

Read the full file on GitHub · 182 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. 8d ago First seen · 182 lines · 2,046 tokens per session scan A 6fa58552e827

Subscribe to this mod's changes

downloader-mcp AGENTS.md is an instructions file published in the GitHub repository CarlDog/downloader-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 2,046 tokens to every session, about $0.0102 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 · 5,153 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens