Borrowing it
Nothing to install: this file belongs to ouzlifaneyassine1-dot/onyx-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ouzlifaneyassine1-dot/onyx-engine/master/AGENTS.mdgit clone --depth 1 https://github.com/ouzlifaneyassine1-dot/onyx-engineWrote 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/ouzlifaneyassine1-dot/onyx-engine/agents-md)<a href="https://agentmods.dev/instructions/ouzlifaneyassine1-dot/onyx-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/ouzlifaneyassine1-dot/onyx-engine/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.
<a href="https://agentmods.dev/instructions/ouzlifaneyassine1-dot/onyx-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/ouzlifaneyassine1-dot/onyx-engine/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01028 | $0.01028 |
| Opus 5 | $0.00514 | $0.00514 |
| Sonnet 5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
onyx-engine 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
onyx — Agent Context
This file is for any AI agent that loads context from AGENTS.md (Codex CLI, Factory Droid, etc). It mirrors the onyx onboarding rules — see GEMINI.md for the same content keyed for Gemini.
What you're working with
Onyx Engine is the AI-native game engine the user is building in. Editor, scene graph, asset pipeline, and runtime are all instrumented for programmatic control via the onyx-engine MCP server. Onyx Engine is compatible with Godot 4.6.3 — projects use GDScript (.gd), C# (.cs), scenes (.tscn/.scn), and resources (.tres/.res). Write code in those languages; talk to the engine through MCP tools.
Critical rules
- Always check for a relevant onyx skill before responding. Even a 1% chance a skill applies = invoke it. Start with
onyx:using-onyxon every fresh Onyx Engine session. - The user owns fix decisions. Diagnose first, propose, ask, then edit.
- Don't grep the whole project before reading the actual error. Use
onyx_get_script_errorsfirst. - Don't edit
.tscnfiles directly while the engine is running. Use theonyx_*MCP tools — direct edits get overwritten when the editor saves. - Never call
onyx_set_resource_propertyagainst an inlinesub_resource— it silently drops the value. Instantiate viaonyx_set_propwith a class-name string first.
Skill priority
- Process (
brainstorm-game,debug,play) → how to approach. - Discipline (
gdscript-patterns,scene-composition,art-direction) → how to shape it. - Build (
fps-controller,design-mechanic,design-level,setup-multiplayer,vfx,tune-performance,export-and-ship) → produce the artifact.
MCP tool palette (engine on localhost:6550)
44 tools total. Categories:
- Scene:
onyx_get_scene_tree,onyx_open_scene,onyx_create_scene,onyx_add_node,onyx_set_prop,onyx_set_resource_property,onyx_remove_node,onyx_save_scene,onyx_instantiate_scene,onyx_replace_node,onyx_select_node,onyx_inspect_node,onyx_inspect_resource,onyx_connect_signal,onyx_batch. - Diagnostics:
onyx_get_script_errors,onyx_get_diagnostics,onyx_get_console,onyx_clear_console,onyx_get_debugger_errors,onyx_get_debugger_warnings. - Runtime:
onyx_play,onyx_stop,onyx_is_running. - Project:
onyx_get_project_context,onyx_open_main_scene,onyx_project_setting,onyx_input_map_bind,onyx_get_agent_playbook. - Assets:
onyx_search_assets,onyx_list_my_assets,onyx_get_asset,onyx_get_asset_download_url,onyx_import_asset,onyx_import_asset_by_id,onyx_import_from_url,onyx_import_from_url_batch. - Generation:
onyx_generate_image,onyx_generate_3d,onyx_generate_audio,onyx_generate_video,onyx_generate_motion,onyx_check_job. - Meta:
onyx_start_game_task.
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 · 54 lines · 1,028 tokens per session scan A 6a1f9df4535e
onyx-engine AGENTS.md is an instructions file published in the GitHub repository ouzlifaneyassine1-dot/onyx-engine (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,028 tokens to every session, about $0.0051 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
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.