Borrowing it
Nothing to install: this file belongs to arr-mcps/autobrr-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.
curl -O https://raw.githubusercontent.com/arr-mcps/autobrr-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/arr-mcps/autobrr-mcpWrote 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/arr-mcps/autobrr-mcp/agents-md)<a href="https://agentmods.dev/instructions/arr-mcps/autobrr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/arr-mcps/autobrr-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.
<a href="https://agentmods.dev/instructions/arr-mcps/autobrr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/arr-mcps/autobrr-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01539 | $0.01539 |
| Opus 5.5 | $0.00616 | $0.00616 |
| Sonnet 5.5 | $0.00308 | $0.00308 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
autobrr-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 2mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — autobrr-mcp
MCP server exposing autobrr's REST API (read + write) as tools so an LLM can read and manage a full autobrr instance: filters, indexers, IRC networks, RSS/Torznab feeds, download clients, actions, the release queue and its stats, import lists, notifications, API keys, proxies, config, health, and update checks. Uses FastMCP, uv for deps.
Exposed as 13 resource-scoped portmanteau tools, not one tool per endpoint — see "Portmanteau registration" below. autobrr's API has no OpenAPI spec, so the endpoint table is hand-written from autobrr's Go source rather than generated from a vendored spec.
Testing
- Offline suite:
make test(oruv run pytest) - Live integration (needs
AUTOBRR_URL/AUTOBRR_API_KEY):make test-integration- GET endpoints run against the live instance.
- POST/PUT/PATCH/DELETE only run when
AUTOBRR_WRITE_TESTS=1(safe create→update→delete cycles against a scratch filter and a scratch API key, then cleanup). Never point write tests at a production instance you care about.
Tool registry and the autobrr source
_TOOL_REGISTRYinautobrr_mcp.pylists every JSON-producing autobrr endpoint. autobrr publishes no OpenAPI spec (docs/ holds only man pages), so this table is maintained by hand against autobrr'sinternal/http/<resource>.gohandlerRoutesmethods (currently pinned to develop HEAD). Each entry carries name/method/path/path-params/query-params/body-kind/doc.- Excluded on purpose:
/api/auth(session/OIDC, not usable over an API token),/api/events(SSE stream, not JSON), the inbound/api/webhooklist-trigger routes (same job as/api/lists/refresh), and/api/logs/files/{logFile}(raw text download). - Response caveats: healthz endpoints return
text/plain("OK") and/api/feeds/{id}/latestreturns a raw string body —_reqfalls back tor.textfor non-JSON 2xx bodies and returns{}for empty bodies, anddispatchis typedJSONVal | straccordingly. Keep that union widened; a too-narrow return type breaks structured-content validation at runtime. - To refresh coverage after an autobrr update, diff
internal/http/*.goRoutesmethods and update_TOOL_REGISTRY+_GROUPSby hand. Do not hand-edit generated per-endpoint functions;register_tools()regenerates them from the registry. - Endpoint function naming (internal, not an MCP tool name):
autobrr_<verb>_<resource>derived from path + method (e.g.autobrr_list_filters,autobrr_create_filter,autobrr_delete_releases,autobrr_retry_release_action).
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.
- 2mo ago First seen · 56 lines · 1,539 tokens per session scan A 76da34c8c3d4
autobrr-mcp AGENTS.md is an instructions file published in the GitHub repository arr-mcps/autobrr-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 1,539 tokens to every session, about $0.0062 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.
autobrr-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| autobrr-mcp AGENTS.mdarr-mcps/autobrr-mcp | Instructions file | 0 | yesterday | MIT | A | 1,539 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |