gorked AGENTS.md

gorked AGENTS.md is an instructions file for Codex, OpenCode from iBerry420/gorked. It costs 295 tokens per session, scanned A, original, MIT.

Project instructions for gorked, a computer-use framework in which Grok controls a desktop through an MCP server. They describe the system structure, safe UI automation practices, commands, and generated files.

In plain words
What is it for?
Automating desktop interfaces, running gorked commands, planning agent tasks, and locating captures or other files under output/.
Why use it?
They give the agent project-specific rules for inspecting screens, clicking safely, confirming live actions, and storing outputs.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/iberry420/gorked/agents-md
Clone the repo
git clone --depth 1 https://github.com/iBerry420/gorked

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 gorked AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/iberry420/gorked/agents-md.svg)](https://agentmods.dev/instructions/iberry420/gorked/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/iberry420/gorked/agents-md"><img src="https://agentmods.dev/badge/instructions/iberry420/gorked/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 295 This file is loaded in full into every session.
When invoked 295 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00295 $0.00295
Opus 5 $0.00148 $0.00148
Sonnet 5 $0.00059 $0.00059
Haiku 4.5 $0.00030 $0.00030

Measured 3d ago against content hash 2726730cbbe2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gorked 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 3d 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 · 33 lines

What it actually says

Gorked — project rules for Grok Build

This repo is a computer-use framework. Grok drives the desktop through the gorked MCP server, not the HTTP API.

Architecture

  • Eyes: analyze_screen / find_text — OCR boxes + center click pixels
  • Hands: mouse_click, click_text, type_text, hotkey, mouse_drag, …
  • Brain: headless Grok CLI (this process) with streaming thoughts + MCP tools
  • Safety: dry-run by default; live requires set_live_mode + confirmation phrase

When automating the UI

  1. Load skill computer-use if available.
  2. Call thought(...) so the user sees your process.
  3. analyze_screen() before inventing any coordinates.
  4. Prefer click_text("label") over raw pixels.
  5. Stay dry-run unless the user explicitly asked for live control.

Commands

gorked mcp --install          # register MCP in .grok/config.toml
gorked drive "goal"           # headless grok + MCP tools
gorked analyze                # OCR only
gorked agent "goal"           # planner loop (structured plan JSON)

Artifacts

All under output/: captures, annotated boxes, scene JSON, thought traces.

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. 3d ago First seen · 33 lines · 295 tokens per session scan A 2726730cbbe2

Subscribe to this mod's changes

gorked AGENTS.md is an instructions file published in the GitHub repository iBerry420/gorked (1 stars, last pushed 1mo ago), licensed MIT. It adds 295 tokens to every session, about $0.0015 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.

Related

Other instructions, from other repositories