Borrowing it
Nothing to install: this file belongs to jmpijll/unraid-code-mode-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/jmpijll/unraid-code-mode-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/jmpijll/unraid-code-mode-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/jmpijll/unraid-code-mode-mcp/agents-md)<a href="https://agentmods.dev/instructions/jmpijll/unraid-code-mode-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jmpijll/unraid-code-mode-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/jmpijll/unraid-code-mode-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jmpijll/unraid-code-mode-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 | $0.00767 | $0.00767 |
| Opus 5.5 | $0.00307 | $0.00307 |
| Sonnet 5.5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
unraid-code-mode-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 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working on unraid-code-mode-mcp. This file is consumed by Cursor, Claude Code, and similar tools to set repo conventions.
Project shape
- TypeScript ESM, Node ≥ 22.19.
- Source under
src/. Tests undersrc/__tests__/. Scripts underscripts/. Cloudflare scaffold undercf-worker/. - The MCP server exposes exactly two tools:
searchandexecute. Don't add more without an architectural discussion — the whole point of "code mode" is the small surface. - Two namespaces are reserved in the type system:
local(the LAN GraphQL API) andconnect(the future Unraid Connect cloud API). v0.1 only implementslocal. New code that needs a credential map should accept'local' | 'connect'even if it only handleslocaltoday.
House style
- Match the conventions in
unifi-code-mode-mcp. When in doubt, look there first. - Prefer
import typefor type-only imports (ESLint enforces this). - No
console.login production code. Useconsole.error/console.warnfor diagnostics; the lint config allows those. - Avoid
ascasts in test files — write tiny type-narrowing helpers instead. - Don't add comments that narrate the code ("// loop over items"). Comment when the code's intent isn't obvious.
- Don't proactively add new docs files. Extend
README.mdor the existingdocs/*.md.
Required workflow
Before declaring work "done":
npm run check
All gates must pass. The offline built-MCP smoke checks metadata and both search and execute in tools/list; intentional tool changes must update smoke:mcp too.
Commits
Conventional Commits. When committing AI-assisted work, include a Co-authored-by: trailer. Example:
feat(sandbox): expose findOperationsByName in search executor
Co-authored-by: Cursor <[email protected]>
Areas that bite
- QuickJS asyncify. Host functions exposed via
newAsyncifiedFunctionappear synchronous inside the sandbox even though they're real promises in Node. Don't accidentally turn them into pure host promises in the prelude — the sandbox would deadlock. - GraphQL document synthesis.
dispatchOperationbuilds thequery opName($a: A!) { field(a: $a) { selection } }string from introspected arg types. If you changeIndexedOperation, double-checkbuildOperationDocumentand thedispatch.test.tssnapshots. - TLS. A custom
Dispatcherpassed toundicibypassesMockAgent. Tests that need the mock agent must not trigger the custom-dispatcher path. Unit-test the dispatcher builder in isolation instead. - SDL fallback.
src/spec/local-fallback.graphqlis committed and refreshed byscripts/update-spec.ts. The Unraid SDL contains custom directives like@usePermissions—buildSchemais called withassumeValidSDL: true. Don't strip that flag.
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 · +3 lines · +58 tokens per session 374d4d7d427b
- 2mo ago First seen · 50 lines · 709 tokens per session scan A c6d4e08b9d74
unraid-code-mode-mcp AGENTS.md is an instructions file published in the GitHub repository jmpijll/unraid-code-mode-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 767 tokens to every session, about $0.0031 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.
unraid-code-mode-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unraid-code-mode-mcp AGENTS.mdjmpijll/unraid-code-mode-mcp | Instructions file | 1 | 4d ago | MIT | A | 767 | 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 |