What is jetkvm-mcp AGENTS.md?

A set of AGENTS.md instructions for developing jetkvm-mcp, a project that lets an agent control another computer through JetKVM hardware. JetKVM sends video and keyboard or mouse input between computers.

Use it when changing jetkvm-mcp, especially work involving the remote macOS computer, JetKVM behavior, security, or development checks.

It gives coding agents project rules for handling secrets, avoiding unintended computer input, and keeping tests and builds working.

How YokihitoOkiBiz/jetkvm-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to YokihitoOkiBiz/jetkvm-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.

Copy the file

curl -O https://raw.githubusercontent.com/YokihitoOkiBiz/jetkvm-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/YokihitoOkiBiz/jetkvm-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/yokihitookibiz/jetkvm-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/yokihitookibiz/jetkvm-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/yokihitookibiz/jetkvm-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yokihitookibiz/jetkvm-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/yokihitookibiz/jetkvm-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yokihitookibiz/jetkvm-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 744 This file is loaded in full into every session.

When invoked 744 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	$0.00744	$0.00744
Opus 5	$0.00372	$0.00372
Sonnet 5	$0.00149	$0.00149
Haiku 4.5	$0.00074	$0.00074

Measured 8d ago against content hash d327cc437dfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

jetkvm-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 8d 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 · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project overview

This repository is an open-source project for operating a business computer that is not directly accessible through an API or MCP. The control path is:

Hermes Agent on PC2
  → MCP
jetkvm-mcp
  → WebRTC video / HID
JetKVM
  → HDMI / USB
PC1 macOS

PC1 is expected to run applications such as Chrome, Jira, Google Sheets, Figma, VS Code, GitHub Copilot, and GitHub CLI.

The design model is:

The agent on PC2 coordinates work.
GitHub Copilot on PC1 may perform implementation work when explicitly directed.
jetkvm-mcp abstracts PC1's screen, keyboard, and mouse.
Keep JetKVM hardware and firmware as close to the official implementation as possible.
Do not depend on Developer Mode or Cloud/Remote Access.

Priority

When requirements conflict, use this order:

Security
Prevent unintended PC1 input
Keep tests green
Keep the build green
Preserve official JetKVM behavior
Maintainability
Development speed

Secret handling

These rules are absolute:

Never commit .env.
Never log passwords, tokens, or API keys.
Never output JETKVM_PASSWORD or JETKVM_PC_PASSWORD.
Never include secrets in MCP responses or exceptions.
Never put real secrets in README files, examples, tests, fixtures, screenshots, or filenames.

PC1 safety

PC1 is a dedicated validation machine for this project. During the active remaining-tasks development mode, agents may run these tools without a separate conversational confirmation:

take_screenshot
analyze_screen
move_mouse
click
double_click
scroll
press_key
hotkey
type_text
unlock_pc
ensure_unlocked

For ordinary UI actions, inspect the observed state before deciding whether a bounded corrective attempt is safe. Unlock and login remain limited to one authentication attempt per call and must never enter an automatic retry loop. When authentication state is uncertain, fail closed and send no credential or Enter input. Codex CLI sandbox and approval prompts remain authoritative and must not be bypassed.

Read the full file on GitHub · 104 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.

8d ago First seen · 104 lines · 744 tokens per session scan A d327cc437dfc

Subscribe to this mod's changes

jetkvm-mcp AGENTS.md is an instructions file published in the GitHub repository YokihitoOkiBiz/jetkvm-mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 744 tokens to every session, about $0.0037 per session on Opus 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.

Hardware and IoT

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

jetkvm-mcp: Instructions file for Codex