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 skills/thearcforge/hades/unity-ai-behaviornpx skills add TheArcForge/Hades --skill unity-ai-behaviorgit clone --depth 1 https://github.com/TheArcForge/HadesWhat 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 | $0.00032 | $0.08174 |
| Opus 5 | $0.00016 | $0.04087 |
| Sonnet 5 | $0.00006 | $0.01635 |
| Haiku 4.5 | $0.00003 | $0.00817 |
Grade A, and why
unity-ai-behavior 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.
How it starts
The opening of the file, as written. The whole thing — 1,111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity AI Behavior
Guidance for designing and implementing NPC and AI systems in Unity 6+: choosing the right architecture for the complexity of the agent, wiring NavMesh navigation, building detection and sensing pipelines, and avoiding common performance and design traps.
When to Apply
Activate when the conversation involves:
- Choosing an AI architecture (state machine vs behavior tree vs GOAP vs utility AI)
- Implementing NPC patrol, chase, attack, or idle behaviors
- Setting up NavMeshAgent navigation, obstacles, or off-mesh links
- Building sensing systems (sight, hearing, trigger-based awareness)
- Designing steering or movement behaviors (seek, flee, flocking)
- Reviewing AI code that has grown large, tangled, or hard to extend
- Animating NPCs whose animation state is driven by AI state
Do NOT activate for purely cosmetic NPC animation, dialogue systems, or cutscene scripting — those go to hades:animation-workflow or the scene-authoring skill.
Project Context Check
Before making recommendations:
-
Check existing patterns in the graph:
- Call
graph_query(edgeKind: "references", edgeTargetNamePattern: "NavMeshAgent", edgeTargetKind: "Class")— reveals whether NavMesh navigation is already used and how agents are configured - Call
search_by_name("*AI*")orsearch_by_name("*State*")— discovers existing AI scripts and naming conventions - Call
graph_query(edgeKind: "references", edgeTargetNamePattern: "Animator", edgeTargetKind: "Class")— AI and animation state are often coupled; understand the existing linkage before recommending a new architecture - Call
search_by_name("*BehaviorTree*")orsearch_by_name("*GOAP*")— detects whether a third-party AI framework is already in use
- Call
-
Check team decisions in memory:
- Call
recall_memory("AI behavior state machine")to find documented AI patterns or previously chosen architecture - Call
recall_memory("NavMesh navigation patrol")to find navigation conventions - Check validation status — if a recalled decision shows
warning, surface the conflict before proceeding
- Call
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 · 1,111 lines · 32 tokens per session scan A 5bb43cdf0751
unity-ai-behavior is a skill published in the GitHub repository TheArcForge/Hades (27 stars, last pushed 7d ago), licensed MIT. It adds 32 tokens to every session and 8,174 once invoked, about $0.0002 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 skills, from other repositories
octocode-mannequin
Use when posing, animating, or explaining a 3D human skeleton/manikin: anatomical joints, ROM clamps, walk/run/dance/backflip sequences, Three.js viewer, or agent-driven WebMCP figure control (reach/lookat). Phrases like pose the manikin, skeleton scheme, animate a walk cycle. Not for general 3D scenes…
unity-reviewer
Use after implementation to review code changes for Unity anti-patterns, performance issues, and correctness problems. Also use when superpowers:requesting-code-review is active to provide Unity-specific review criteria.
component-design
Use when you need detailed decision frameworks for MonoBehaviour composition, inter-component communication, single responsibility, and execution order.
data-modeling
Use when you need detailed decision frameworks for ScriptableObject patterns, runtime data management, serialization strategies, and data-driven architecture.
prefab-architecture
Use when you need detailed decision frameworks for prefab vs variant vs ScriptableObject, nested prefab design, override strategies, and prefab editing workflows.
scene-architecture
Use when you need detailed decision frameworks for scene structure, additive loading, scene management, transitions, and persistent managers.