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/summerengine/summer-engine-agent/gemini-mdgit clone --depth 1 https://github.com/SummerEngine/summer-engine-agentWrote 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/summerengine/summer-engine-agent/gemini-md)<a href="https://agentmods.dev/instructions/summerengine/summer-engine-agent/gemini-md"><img src="https://agentmods.dev/badge/instructions/summerengine/summer-engine-agent/gemini-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 5.1 | $0.01153 | $0.01153 |
| Opus 5 | $0.00576 | $0.00576 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
summer-engine-agent GEMINI.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 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.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summer — Context Primer for Gemini
Summer is the AI game-dev studio for Summer Engine — the AI-native game engine. When you see this file in a session, it means the user has installed the Summer Gemini extension and you have access to the summer-engine MCP server plus Summer skills under the summer: namespace.
What Summer Engine is
Summer Engine is designed for AI-assisted creation. The user is making a Summer game with the Summer SDK, normally in GDScript. The editor, scene graph, asset pipeline, and runtime are instrumented for programmatic control via MCP. Summer currently uses the 4.6.1 upstream technical base, plans to adopt 4.7.1 next, and follows upstream continuously. Those numbers are compatibility facts, not the product identity. Projects use GDScript (.gd), C# (.cs), scenes (.tscn/.scn), resources (.tres/.res), and the technical project.godot filename.
How to behave
Always check for a relevant Summer skill before writing code or running tools. Skills encode discipline that matters — debug protocols, scene-composition rules, GDScript idioms Gemini regularly gets wrong. If a skill might apply, even at 1% probability, activate it via activate_skill.
The single most important skill to know is summer:using-summer — it explains the workflow, priority, and the red-flag table of rationalizations the model needs to resist. Activate it first thing in any Summer Engine session.
Skill priority
- Process skills first:
brainstorm-game,debug,play. These determine HOW. - Discipline skills second:
gdscript-patterns,scene-composition,art-direction,audio-direction. These shape content. - Build skills third:
fps-controller,design-mechanic,design-level,setup-multiplayer,vfx,tune-performance,export-and-ship.
MCP tools (when the project-matched local editor is running)
The summer-engine MCP server exposes a focused tool registry. The most important:
- Scene mutation:
summer_add_node,summer_set_prop,summer_set_resource_property,summer_remove_node,summer_save_scene,summer_replace_node,summer_batch. Every scene mutation requires the exactres://...tscnscenePath; opening a scene is a user-visible UI action, not a mutation prerequisite. Mutation tools append one finalSaveScene; raw engine batches must do the same. - Scene inspection:
summer_get_scene_tree,summer_inspect_node,summer_inspect_resource. - Diagnostics:
summer_create_debug_report,summer_get_script_errors(cheapest),summer_get_diagnostics,summer_get_console,summer_get_debugger_errors,summer_get_debugger_warnings. - Run game:
summer_play,summer_stop,summer_is_running. - Visual:
summer_screenshot(capture the viewport or running game as an image you can see). - Project:
summer_get_project_context,summer_open_main_scene,summer_project_setting,summer_input_map_bind. - Files:
summer_read_file,summer_write_file,summer_replace_text(identity-bound, create-only or sha256-guarded mutations). - Assets:
summer_search_assets,summer_import_asset,summer_import_from_url,summer_generate_image,summer_generate_3d,summer_generate_audio,summer_generate_video,summer_check_job.
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.
- 6d ago First seen · 59 lines · 1,153 tokens per session scan A b7bd5688b42c
summer-engine-agent GEMINI.md is an instructions file published in the GitHub repository SummerEngine/summer-engine-agent (57 stars, last pushed yesterday), licensed MIT. It adds 1,153 tokens to every session, about $0.0058 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 2026-08-30.
Other instructions, from other repositories
comedot AGENTS.md
AGENTS.md instructions for InvadingOctopus/comedot, covering agents.md, guidelines for the comedot project and repository, project overview, folder structure & module organization and subsystems.
yume CLAUDE.md
Instructions for kamwoh/yume, covering yume (夢) — json-driven game framework on godot, quick start, framework structure, how the engine works and tick rate is the engine's heartbeat (2026-05-16).
o3de-mcp AGENTS.md
AGENTS.md instructions for nickschuetz/o3de-mcp, covering agent guide — o3de-mcp, quick start decision tree, tool surface, token efficiency rules and 1. batch over individual calls.
Unity-MCP copilot-instructions.md
Copilot instructions for IvanMurzak/Unity-MCP, covering project guidelines, critical rules, no c# reflection for private access, code review and code style.
mcp-unity AGENTS.md
AGENTS.md instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
turn-based-game-mcp shared-library.instructions.md
Shared library development patterns for the turn-based games platform.