localutils-mcp-server: Instructions file for Codex

AGENTS.md

localutils-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from arjshiv/localutils-mcp-server. It costs 552 tokens per session, scanned A, original, MIT.

Repository instructions for localutils-mcp-server, a TypeScript server that provides local utility tools through MCP, a standard way for AI agents to use tools.

In plain words
What is it for?
Installing dependencies with pnpm, building committed output, running tests, and following the repository's TypeScript and import rules.
Why use it?
They give contributors the project's required commands, code conventions, build expectations, and testing guidance.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Cursor.

This is arjshiv/localutils-mcp-server's own configuration. It tells Codex and OpenCode how to work on localutils-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything localutils-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to arjshiv/localutils-mcp-server. 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/arjshiv/localutils-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/arjshiv/localutils-mcp-server

Made for: Codex, OpenCode.

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.

agentmods badge for localutils-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arjshiv/localutils-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/arjshiv/localutils-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/arjshiv/localutils-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/arjshiv/localutils-mcp-server/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.

agentmods 80×15 button for localutils-mcp-server AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/arjshiv/localutils-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/arjshiv/localutils-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 552 This file is loaded in full into every session.
When invoked 552 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00552 $0.00552
Opus 5.5 $0.00221 $0.00221
Sonnet 5.5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 2mo ago against content hash cfb4ff4a6822, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

localutils-mcp-server 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.

AGENTS.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo Guidelines for localutils-mcp-server

This project is a TypeScript implementation of an MCP (Model Context Protocol) server that exposes several local utilities. All source lives under src/ and the compiled output is committed in build/.

Development Workflow

  • Use pnpm for dependency management. Install dependencies with pnpm install which also sets up the Husky pre-commit hook.
  • Build compiled output with pnpm run build. The pre-commit hook automatically runs npm run build to ensure build/ is up to date.
  • Run tests with pnpm test. Aim for over 80% coverage as noted in .cursor/rules/testing.mdc.
  • Node.js version 16 or higher is required.

Coding Standards

TypeScript style guidelines are defined in .cursor/rules/typescript.mdc and include:

  • Use named exports, avoid default exports.
  • Order imports as: Node built-ins, external packages, internal modules. Separate groups with blank lines.
  • Avoid any; prefer explicit types and interfaces.
  • Use PascalCase for classes/interfaces and camelCase for variables/functions. Prefix interfaces with I and type aliases with T.
  • Use arrow functions for callbacks, handle errors properly, and prefer async/await.
  • Format with two-space indentation, 100 character line length, semicolons, single quotes, and trailing commas in multiline structures.

Documentation standards from .cursor/rules/documentation.mdc require thorough README files, JSDoc comments for public APIs, and Markdown with proper heading hierarchy. Keep comments focused on why and ensure all public functions are documented.

MCP-specific documentation must follow .cursor/rules/mcp-docs.mdc which mandates Mermaid diagrams describing workflows and protocol details. Each MCP implementation under src/mcp/ should include these diagrams and explanations.

Testing guidelines in .cursor/rules/testing.mdc specify placing tests in src/__tests__ with .test.ts suffix, following the Arrange/Act/Assert pattern, and keeping tests independent.

Read the full file on GitHub · 37 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.

  1. 2mo ago First seen · 37 lines · 552 tokens per session scan A cfb4ff4a6822

Subscribe to this mod's changes

localutils-mcp-server AGENTS.md is an instructions file published in the GitHub repository arjshiv/localutils-mcp-server (2 stars, last pushed 10mo ago), licensed MIT. It adds 552 tokens to every session, about $0.0022 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.

Related

localutils-mcp-server AGENTS.md compared with instructions from other repositories

localutils-mcp-server AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
localutils-mcp-server AGENTS.mdarjshiv/localutils-mcp-serverInstructions file210mo agoMITA552Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode