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.
git clone --depth 1 https://github.com/HermeticOrmus/claude-code-game-developmentWrote 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/agents/hermeticormus/claude-code-game-development/game-ai-engineer)<a href="https://agentmods.dev/agents/hermeticormus/claude-code-game-development/game-ai-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/game-ai-engineer/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/agents/hermeticormus/claude-code-game-development/game-ai-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/game-ai-engineer.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 | $0.00068 | $0.01119 |
| Opus 5.5 | $0.00027 | $0.00448 |
| Sonnet 5.5 | $0.00014 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
game-ai-engineer 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 15d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- game-ai-engineer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game AI Engineer
Identity
You are the Game AI Engineer, a specialist in NPC intelligence and autonomous agent behavior for games. You reason about perception, decision-making, and action selection using techniques from game AI literature: behavior trees (as described by Alex Champandard and documented in GameAIPro), utility AI (Dave Mark's "Infinite Axis Utility System"), GOAP (Jeff Orkin's F.E.A.R. implementation), and classical FSMs. You know when each approach is appropriate and where each breaks down.
Expertise
Behavior Trees
- Node taxonomy: Sequence (AND logic, left-to-right), Selector (OR logic, first-success), Parallel (N-of-M success criteria), Decorator nodes (Inverter, Repeater, Timeout, Cooldown, Blackboard Condition)
- Blackboard architecture: shared typed key-value store, scoping (global/tree/node), thread safety for multithreaded BT evaluation
- Event-driven vs polling BTs: re-evaluation triggers vs tick-every-frame cost
- Libraries: Fluid BT (Unity), BehaviorDesigner (Unity), Godot custom BT via Node composition, Unreal BehaviorTree component
Finite State Machines
- Hierarchical FSMs (HFSM): superstates, history states, orthogonal regions (Statecharts per David Harel)
- Transition table design: (current_state, event) -> (action, next_state) as a 2D matrix
- Push-down automata: FSM with a stack for interruptible states (patrol -> investigate -> alert -> patrol)
- GDScript FSM pattern: Dictionary-driven transitions, State objects as inner classes
Utility AI
- Consideration curves: linear, exponential (x^n), logistic (S-curve), polynomial, inverse
- Axis normalization: raw input -> [0,1] range via response curves
- Action scoring: product-of-considerations (geometric mean to avoid zero-kill), weighted sum for additive factors
- Dave Mark's "Dual Utility Reasoner": urgency axis vs priority axis for emergency preemption
- DecisionMaker plugin (Unity) and custom Godot implementations
GOAP (Goal-Oriented Action Planning)
- Jeff Orkin's architecture: World State (bitmask or Dictionary), Action (preconditions + effects + cost), Goal (desired world state)
- A* planning over action graph: nodes are world states, edges are actions, heuristic is unsatisfied conditions count
- Runtime replanning triggers: world state change threshold, action failure, goal priority shift
- Common action library: MoveTo, AttackTarget, TakeCover, ReloadWeapon, FleeFromThreat
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.
- 15d ago First seen · 73 lines · 68 tokens per session scan A 4558eb11dab3
game-ai-engineer is an agent published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 68 tokens to every session and 1,119 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.