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/dinglebear-ai/unraid/claude-mdgit clone --depth 1 https://github.com/dinglebear-ai/unraidWhat 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 | $0.03561 | $0.03561 |
| Opus 5 | $0.01781 | $0.01781 |
| Sonnet 5 | $0.00712 | $0.00712 |
| Haiku 4.5 | $0.00356 | $0.00356 |
Grade A, and why
unraid CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Docs, manifests, `server.json`, `Cargo.toml`, the npm launcher and the curl-able How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (claude.ai/code) working in this repository.
What this is
A monorepo of Unraid tooling — four release units plus two agent-plugin
integrations. The canonical remote is [email protected]:dinglebear-ai/unraid.git.
Identity and history (read before touching any URL)
Consolidated on 2026-07-27. Two formerly standalone repos — runraid and
incus-unraid — were merged in and then deleted upstream. This repo is now the
only home for that code; do not go looking for those repos, and do not "restore" a
reference to them.
On the same date both the local directory and the GitHub repo were renamed
unraid-mcp → unraid. GitHub's transfer redirect still resolves the old name
(verified, including raw.githubusercontent.com/... paths), so already-deployed
.plg install/update URLs keep working.
Docs, manifests, server.json, Cargo.toml, the npm launcher and the curl-able
install scripts were repointed to dinglebear-ai/unraid. Four files were
deliberately left on the old URL — the three plugins/*/*.plg and
plugins/mcp/source/.../unraid-mcp-update.sh. Installed plugins poll their own
pluginURL and resolve txzURL/REPO at runtime, so editing those ships a
behavioural change to live Unraid boxes; that needs a deliberate release and a test
install, not a drive-by rename. They work today via the redirect and break the day
anyone creates a new dinglebear-ai/unraid-mcp — load-bearing on a redirect, and
tracked follow-up work.
New in-repo references must use dinglebear-ai/unraid.
"unraid-mcp" means five different things
Most unraid-mcp strings in this tree are correct and must not be swept into a
rename. Only GitHub repo URLs are stale.
| Occurrence | Still correct? |
|---|---|
PyPI distribution unraid-mcp (import unraid_mcp) |
✅ unchanged |
Claude/Codex plugin name: unraid-mcp (agents/unraid-py) |
✅ unchanged |
Unraid OS plugin dir plugins/mcp/source/.../unraid-mcp/ and unraid-mcp.plg |
✅ unchanged |
Container image ghcr.io/dinglebear-ai/unraid-mcp |
✅ unchanged |
GitHub URL github.com/dinglebear-ai/unraid-mcp |
⚠️ stale — redirect only |
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 · 184 lines · 3,561 tokens per session scan A df9fbfe58224
unraid CLAUDE.md is an instructions file published in the GitHub repository dinglebear-ai/unraid (129 stars, last pushed yesterday), licensed MIT. It adds 3,561 tokens to every session, about $0.0178 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
google-ai-mcp AGENTS.md
Instructions for sandraschi/google-ai-mcp, covering google-ai-mcp — agent guide, entry points, quick ref, ports and architecture.
google-ai-mcp CLAUDE.md
Instructions for sandraschi/google-ai-mcp, covering google-ai-mcp — claude code guide, entry points, standards and key files.
mcp-kraken CLAUDE.md
Claude Code instructions for XavierBeheydt/mcp-kraken, covering project guidance — mcp-kraken, what this project is, stack, layout and common commands.
IP-MCP CLAUDE.md
Claude Code instructions for kitepon/IP-MCP, covering claude.md, 現状, このプロジェクトが目指すもの, 譲れないアーキテクチャ規則 and なぜキーワード検索を別ツールに分離したのか（パラメータではなく）.
cortex CLAUDE.md
Claude Code instructions for dinglebear-ai/cortex, covering claude.md — cortex, repo facts, commands, architecture and ports.
cortex AGENTS.md
AGENTS.md instructions for dinglebear-ai/cortex, a project described as: Rust MCP/HTTP log aggregation platform for homelab syslog, Docker logs, OTLP ingest, SQLite/FTS search, and AI transcript correlation.