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.
npx agentmods add instructions/iberry420/gorked/agents-mdgit clone --depth 1 https://github.com/iBerry420/gorkedWrote 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/iberry420/gorked/agents-md)<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>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 | $0.00295 | $0.00295 |
| Opus 5 | $0.00148 | $0.00148 |
| Sonnet 5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00030 | $0.00030 |
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.
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
- Load skill
computer-useif available. - Call
thought(...)so the user sees your process. analyze_screen()before inventing any coordinates.- Prefer
click_text("label")over raw pixels. - 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.
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.
- 3d ago First seen · 33 lines · 295 tokens per session scan A 2726730cbbe2
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).
browser_oxide AGENTS.md
AGENTS.md instructions for yfedoseev/browser_oxide, covering browseroxide — conventions for ai coding assistants, build & test, architecture, key conventions and where to read more.
shantycrawl-mcp AGENTS.md
AGENTS.md instructions for schlemperdev/shantycrawl-mcp, covering shantycrawl mcp -- dynamic firecrawl mcp server, purpose, ownership, local contracts and work guidance.