Borrowing it
Nothing to install: this file belongs to dinglebear-ai/unraid. 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/dinglebear-ai/unraid/main/AGENTS.mdgit clone --depth 1 https://github.com/dinglebear-ai/unraidWrote 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/dinglebear-ai/unraid/agents-md)<a href="https://agentmods.dev/instructions/dinglebear-ai/unraid/agents-md"><img src="https://agentmods.dev/badge/instructions/dinglebear-ai/unraid/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/dinglebear-ai/unraid/agents-md"><img src="https://agentmods.dev/badge/instructions/dinglebear-ai/unraid/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 | $0.01345 | $0.01345 |
| Opus 5.5 | $0.00538 | $0.00538 |
| Sonnet 5.5 | $0.00269 | $0.00269 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
unraid 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 1mo 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.
This is a copy
100% identical to skills AGENTS.md — 108 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unraid tooling monorepo
This is dinglebear-ai/unraid, not Unraid Core. The Python and Rust MCP servers, OS plugins, and client-agent integrations share repository policy, not one application runtime. Read the component's guide before changing its implementation.
Component map
| Path | Responsibility | Guide |
|---|---|---|
unraid-py/ |
Python server; package unraid-mcp, import unraid_mcp |
AGENTS |
unraid-rs/ |
Rust server and CLI; crate unraid-rmcp, binary runraid |
AGENTS |
plugins/mcp/ |
Native Unraid plugin packaging the Rust server and settings UI | README |
plugins/incus/ |
Classic Incus OS plugin, NestJS backend, Vue frontends | AGENTS |
plugins/codex/ |
Classic Codex chathead plugin and React UI | README |
agents/unraid-py/ |
Client integration named unraid-mcp |
Plugin guide |
agents/unraid-rs/ |
Client integration named runraid |
Rust guide |
Cross-component contracts
Python routes the consolidated unraid(action=..., subaction=...) tool through
domain handlers. Rust's src/mcp/schemas.rs::ACTIONS owns action identity and
scope; action_params.rs owns parameter metadata. Its legacy (default),
atomic, and both projections share enabled actions, authorization,
confirmation guards, and dispatch. Do not create a second execution path.
Both servers can mutate Unraid. Keep outbound Unraid API credentials separate from inbound MCP bearer/OAuth credentials. Live disk, array, VM, container, and plugin tests require an explicitly selected disposable target. The component guides own routing, scopes, TLS, and test-patching details; ARCHITECTURE.md maps execution and trust boundaries.
Build roots
The root Cargo.toml is a zero-member policy mirror, not the
Rust build root. Run Cargo in unraid-rs/; its workspace contains the server,
crates/lab-auth, and xtask, and owns its lockfile. The frozen lab-auth
compatibility floor is separate from the main compiler policy.
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.
- 1mo ago Changed · -86 lines · -1,375 tokens per session 899b79dd193c
- 1mo ago Changed · +192 lines · +2,716 tokens per session d80bc143c4c4
- 2mo ago First seen · 1 lines · 4 tokens per session scan A 6ebdb617a810
unraid AGENTS.md is an instructions file published in the GitHub repository dinglebear-ai/unraid (150 stars, last pushed 4d ago), licensed MIT. It adds 1,345 tokens to every session, about $0.0054 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to skills AGENTS.md, differing in 108 lines, and is treated as a copy.
unraid AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unraid AGENTS.mddinglebear-ai/unraid | Instructions file | 150 | 4d ago | MIT | A | 1,345 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |