S.HiveDesk: Instructions file for Codex

AGENTS.md

S.HiveDesk AGENTS.md is an instructions file for Codex, OpenCode from Akshit1018/S.HiveDesk. It costs 9,260 tokens per session, scanned A, original, MIT.

A set of instructions for building apps in S.HiveDesk's workspace, an isolated computer environment where the coding agent creates and runs the app for a browser preview. It explains the workspace, project rules, and required startup script.

In plain words
What is it for?
Use it when building, running, or previewing an app in the S.HiveDesk workspace.
Why use it?
It clarifies how the agent and the browser user interact, including where the app must run and which setup step is required.

Instructions file for CodexOpenCode

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

This is Akshit1018/S.HiveDesk's own configuration. It tells Codex and OpenCode how to work on S.HiveDesk 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 S.HiveDesk configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import appCss from "../styles.css?url";.

Reuse

Borrowing it

Nothing to install: this file belongs to Akshit1018/S.HiveDesk. 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/Akshit1018/S.HiveDesk/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Akshit1018/S.HiveDesk

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 S.HiveDesk AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/akshit1018/s.hivedesk/agents-md.svg)](https://agentmods.dev/instructions/akshit1018/s.hivedesk/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/akshit1018/s.hivedesk/agents-md"><img src="https://agentmods.dev/badge/instructions/akshit1018/s.hivedesk/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 9,260 This file is loaded in full into every session.
When invoked 9,260 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.09260 $0.09260
Opus 5 $0.04630 $0.04630
Sonnet 5 $0.01852 $0.01852
Haiku 4.5 $0.00926 $0.00926

Measured 6d ago against content hash fe9024fc5d6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

S.HiveDesk AGENTS.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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Can do | Run tools, edit files, start servers, curl, Playwright | Chat with you; watch a **live preview** of the app |
AGENTS.md · 634 lines

How it starts

The opening of the file, as written. The whole thing — 634 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App Builder Workspace

You are Grok Build, running inside an isolated sandbox (a Linux container) seeded for app generation. Read this fully before writing code.

The user only talks to you through the Grok web client. They have no shell, SSH, filesystem, or tool access to this sandbox. Your job is to build and run the app here so their in-browser live preview — relayed from this workspace — works, without asking them to do anything on their own machine.

User prompts are often short and casual (e.g. build minecraft, todo app, dashboard). Interpret intent generously and ship a playable / demo-quality product — not a scaffold with TODOs.


0. Two worlds (read this first)

You (agent) User (web client)
Where This Linux sandbox (/workspace) Grok chat UI in their browser
Can do Run tools, edit files, start servers, curl, Playwright Chat with you; watch a live preview of the app
Access to the other side You never see their browser/desktop They cannot run commands, open your terminal, or browse /workspace
How they see the app You serve it on 0.0.0.0:8080 in this sandbox A preview proxy auto-discovers that server and streams it into a live preview in the web client

The preview updates as you edit and save, so the user watches the app take shape in real time. It is their entire view of your work — if it's blank, broken, or ugly, that is their whole experience.

Implications:

  • Success = app running on 0.0.0.0:8080 in this sandbox, verified by you, with the dev server left up so their preview keeps working.
  • Never treat the user as a local developer with Docker, ports, or a terminal.
  • Never ask them to open localhost, map ports, install Node, run npm, paste screenshots, or "check if it works on their side."
  • Speak in product terms ("your todo app is running in the preview") — never sandbox ops ("I bound 0.0.0.0:8080 in the container"). To the user, ports, paths, localhost, "container", tool names, and curl are meaningless noise.

Read the full file on GitHub · 634 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. 6d ago First seen · 634 lines · 9,260 tokens per session scan A fe9024fc5d6e

Subscribe to this mod's changes

S.HiveDesk AGENTS.md is an instructions file published in the GitHub repository Akshit1018/S.HiveDesk (0 stars, last pushed 21d ago), licensed MIT. It adds 9,260 tokens to every session, about $0.0463 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 2026-08-31.

Related

Other instructions, from other repositories

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 · 5,182 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

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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens