Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/indlns/mcp-arrstack/agents-mdgit clone --depth 1 https://github.com/indlns/mcp-arrstackWhat 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 | $0.03594 | $0.03594 |
| Opus 5 | $0.01797 | $0.01797 |
| Sonnet 5 | $0.00719 | $0.00719 |
| Haiku 4.5 | $0.00359 | $0.00359 |
Grade A, and why
mcp-arrstack 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP ARR Stack — Agent Instructions
Purpose
MCP (Model Context Protocol) server providing LLM tools for ARR Stack media automation services: Sonarr, Radarr, Lidarr, Prowlarr, Readarr, Seerr, Tautulli, Plex.
Directory Structure
src/
server.py # Main entry point — tool definitions, dispatch table, MCP server factory
config.py # Dataclass configs per service; load_config() reads env vars
client.py # Async HTTP clients: BaseARRClient (v3 API), SeerrClient (v1), TautulliClient (/api/v2), PlexClient
http_server.py # ASGI app: Starlette + StreamableHTTPSessionManager, API key auth middleware, CORS
utils.py # In-memory cache, rate limiter, safe_execute helper
tools/
sonarr_tools.py
radarr_tools.py
lidarr_tools.py
prowlarr_tools.py
readarr_tools.py # Exists as config but no tool file yet — add src/tools/readarr_tools.py when needed
seerr_tools.py
tautulli_tools.py
plex_tools.py
tests/ # pytest tests (conftest has env-var isolation + mock fixtures)
Build, Test, Lint Commands
Важно: Python не установлен на хост-машине. Все команды должны выполняться внутри Docker-контейнера.
# Install deps (editable) — inside container
docker compose exec mcp-arr-stack pip install -e ".[dev]"
# Run tests — inside container
docker compose exec mcp-arr-stack pytest tests/ -v
docker compose exec mcp-arr-stack pytest tests/ -v --cov=src --cov-report=term-missing
# Format — inside container
docker compose exec mcp-arr-stack black src/ tests/
docker compose exec mcp-arr-stack ruff check src/ tests/
docker compose exec mcp-arr-stack ruff check src/ tests/ --fix
Быстрый запуск тестов
# Все тесты
docker compose exec mcp-arr-stack pytest tests/ -v
# Один файл
docker compose exec mcp-arr-stack pytest tests/test_sonarr_tools.py -v
# С покрытием
docker compose exec mcp-arr-stack pytest tests/ -v --cov=src --cov-report=term-missing
# Только упавшие (last failures)
docker compose exec mcp-arr-stack pytest tests/ -v --lf
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.
- yesterday First seen · 287 lines · 3,594 tokens per session scan A 1fb4c72bc442
mcp-arrstack AGENTS.md is an instructions file published in the GitHub repository indlns/mcp-arrstack (0 stars, last pushed 1mo ago), licensed MIT. It adds 3,594 tokens to every session, about $0.0180 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.
Other instructions, from other repositories
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.
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.
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).
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.