What is oraclarr CLAUDE.md?

Repository instructions for Oraclarr, a read-only diagnostic server for self-hosted media services. It combines information from services such as downloaders, media libraries, storage, and monitoring tools to answer operational questions.

Use them when adding service connections or diagnostic tools, investigating why a media job failed, or handling the one explicitly gated operation that starts a job.

They keep diagnostic tools separate from service connection details and make read-only access the default, reducing the risk of unintended changes.

How bdog720/oraclarr configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bdog720/oraclarr. 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/bdog720/oraclarr/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/bdog720/oraclarr

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bdog720/oraclarr/claude-md/github.svg)](https://agentmods.dev/instructions/bdog720/oraclarr/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bdog720/oraclarr/claude-md"><img src="https://agentmods.dev/badge/instructions/bdog720/oraclarr/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bdog720/oraclarr/claude-md"><img src="https://agentmods.dev/badge/instructions/bdog720/oraclarr/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,236 This file is loaded in full into every session.

When invoked 4,236 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.

Model	Per session	Once invoked
Fable 5.1	$0.04236	$0.04236
Opus 5.5	$0.01694	$0.01694
Sonnet 5.5	$0.00847	$0.00847
Haiku 4.5	$0.00424	$0.00424

Measured 6d ago against content hash 17d97e930024, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oraclarr 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 · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oraclarr

Read-only-by-default diagnostic MCP server (Python/FastMCP) for a self-hosted arr media stack. Answers operational "why" questions by aggregating across services. Phased toward full read+write coverage. Reads are the default; writes are opt-in through one gated tool, start_job (since 2.0.0).

Architecture

Layered. Clients talk to services; tools answer questions. Keep the boundary clean: a tool composes clients, never embeds HTTP/auth detail.

config.py    ORACLARR_* env (parse_env) over optional YAML -> typed Config (load_settings)
registry.py  instance.type -> client class; build_clients(cfg)
clients/     async adapters: base, arr, prowlarr, qbittorrent, tdarr, profilarr, jellyfin, cleanuparr,
             netdata (httpx), truenas (JSON-RPC over WebSocket),
             docker (httpx, read-only socket proxy). Clients are read-only; the only writes are
             the command/scan POSTs that `start_job` sends through the plan flow
tools/       outcome tools; each composes clients via fan_out/probe
guards.py    per-tool risk+domain tags; toolset filter; write gate
auth.py      HTTP bearer-token check (ORACLARR_HTTP_TOKEN); startup refuses writes on http without it
plans.py     in-memory single-use plans (10 min) for the two-step write flow
audit.py     `audit event=<planned|executed|refused|failed|unknown>` log lines for every write event
tools/jobs_write.py  start_job: dry-run builds a plan, execute rebuilds it and compares fingerprints
budget.py    per-call deadline ContextVar; probe() reads it (partial results on timeout)
redact.py    Redactor (config secrets + key patterns) + log record-factory redaction
call_guard.py guarded(): deadline, backstop (budget+2s), output cap, redaction, Any return
server.py    FastMCP app; registers only tools whose domain is in cfg.server.toolsets
models.py    InstanceResult envelope; MediaRef (carries tvdb/tmdb/imdb ids)

v1 services: sonarr, sonarr-anime, radarr, sportarr, prowlarr, qbit, tdarr, profilarr, jellyfin, cleanuparr, netdata, truenas, docker. Tools: stack_health, get_queues, diagnose, explain_decision, get_quality_config, get_history, get_wanted, search_media, get_indexers, get_transcodes, get_upcoming, get_library, get_cleanup, get_host (toolset host), get_containers (toolset containers), get_jobs, start_job (the only write tool; registered only when writes are enabled).

Read the full file on GitHub · 238 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.

6d ago Changed · +4 lines · +77 tokens per session 17d97e930024
8d ago First seen · 234 lines · 4,159 tokens per session scan A c3e2edf2fef5

Subscribe to this mod's changes

oraclarr CLAUDE.md is an instructions file published in the GitHub repository bdog720/oraclarr (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 4,236 tokens to every session, about $0.0169 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 2026-10-30.

Debugging DevOps and cloud

oraclarr CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
oraclarr CLAUDE.mdbdog720/oraclarr	Instructions file	0	7d ago	Apache-2.0	A	4,236	Claude Code
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

oraclarr: Instructions file for Claude Code