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/cuti27/mcp-arr-lite/agents-mdgit clone --depth 1 https://github.com/Cuti27/mcp-arr-liteWrote 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.
[](https://agentmods.dev/instructions/cuti27/mcp-arr-lite/agents-md)<a href="https://agentmods.dev/instructions/cuti27/mcp-arr-lite/agents-md"><img src="https://agentmods.dev/badge/instructions/cuti27/mcp-arr-lite/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00915 | $0.00915 |
| Opus 5 | $0.00458 | $0.00458 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
mcp-arr-lite 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Compact guide for OpenCode sessions working in this repo.
Toolchain
- Node >= 20, ES modules (
"type": "module"),module/moduleResolution: NodeNext. Use.jsextensions in relative imports (required at runtime under NodeNext). - No ESLint/Prettier —
npm run lintandnpm run typecheckare bothtsc --noEmit. Do not look for a separate linter config. npm run buildcompilessrc/->dist/(rootDir: src,outDir: dist);tests/is excluded fromtsconfig.jsonbut included intsconfig.test.json.
Commands
- Dev:
npm run dev(tsx watch onsrc/index.ts). - Build:
npm run build; run built:npm start(stdio) ornpm run start:stdio/npm run start:http. - Tests:
npm test(vitest run). Coverage:npm run test:coverage. - Single test:
npx vitest run tests/tools.test.tsornpx vitest run -t "pattern". - Run both
npm run typecheckandnpm run typecheck:testsbefore pushing.
Tests
vitest.config.tssetsglobals: trueandenvironment: 'node'; tests live intests/**/*.test.ts.tests/setup.tsstubs env vars (RADARR_URL,RADARR_API_KEY,SONARR_URL,SONARR_API_KEY,MCP_TRANSPORT=http,LOG_LEVEL=error) for the whole suite viabeforeAll. Don't assume a real Radarr/Sonarr is reachable.- Tests mock
ArrClient/ globalfetch— no integration services required.
Architecture
- Entry:
src/index.ts(bindist/index.js). Loads config, buildsArrClientinstances for configured apps, creates the MCPMcpServer, then selects transport fromMCP_TRANSPORT. src/config.tsowns all env loading and validation;validateHttpConfigrequiresMCP_AUTH_TOKENwhenMCP_TRANSPORT=http. Radarr/Sonarr config is optional.src/server.tsregisters tools frombuildTools()into the MCPMcpServerand wraps handlers with safe-error normalization.- Transport:
src/transport/stdio.tsandsrc/transport/http.ts. HTTP transport adds bearer auth, rate limiting (60 req/min/IP), and 1 MB body limit; defaultsHOST=127.0.0.1. - Tools live in
src/tools/handlers/and are aggregated insrc/tools/registry.ts(buildTools()). Adding a tool = create handler file + append it inbuildTools();server.tspicks the rest up automatically. src/arr/client.tsis the only Arr API surface (X-Api-Key auth);src/arr/radarr.ts/src/arr/sonarr.tswrap resource-specific calls and default-resolution (quality profile, root folder);src/arr/indexer.tshas the preferred-indexer logic (lowest numeric priority among enabled).- Search tools default to the preferred indexer; pass a specific
indexerid to force an alternative. Read-only tools (*_lookup,list_indexers) are safe to auto-approve; mutations (*_add,*_search_releases,*_grab) should require HITL.
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.
- 5d ago First seen · 44 lines · 915 tokens per session scan A addce063bdb1
mcp-arr-lite AGENTS.md is an instructions file published in the GitHub repository Cuti27/mcp-arr-lite (0 stars, last pushed 18d ago), licensed MIT. It adds 915 tokens to every session, about $0.0046 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
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).
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.
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.
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 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).
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.