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 skills add HermeticOrmus/claude-code-game-development --skill game-ai-patternsgit 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/skills/hermeticormus/claude-code-game-development/game-ai-patterns)<a href="https://agentmods.dev/skills/hermeticormus/claude-code-game-development/game-ai-patterns"><img src="https://agentmods.dev/badge/skills/hermeticormus/claude-code-game-development/game-ai-patterns/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/skills/hermeticormus/claude-code-game-development/game-ai-patterns"><img src="https://agentmods.dev/badge/skills/hermeticormus/claude-code-game-development/game-ai-patterns.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 | $0.00058 | $0.02654 |
| Opus 5.5 | $0.00023 | $0.01062 |
| Sonnet 5.5 | $0.00012 | $0.00531 |
| Haiku 4.5 | $0.00006 | $0.00265 |
Grade A, and why
game-ai-patterns 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.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game AI Patterns
Behavior Tree Node Types
Composite Nodes
# Sequence: all children must succeed (AND)
# Returns FAILURE on first child failure, SUCCESS if all succeed
class_name BTSequence extends BTComposite
func _tick(delta: float) -> Status:
for child in children:
var status := child.tick(delta)
if status != Status.SUCCESS:
return status # FAILURE or RUNNING propagates up
return Status.SUCCESS
# Selector: first child to succeed wins (OR)
# Returns SUCCESS on first child success, FAILURE if all fail
class_name BTSelector extends BTComposite
func _tick(delta: float) -> Status:
for child in children:
var status := child.tick(delta)
if status != Status.FAILURE:
return status # SUCCESS or RUNNING propagates up
return Status.FAILURE
# Parallel: runs all children simultaneously
# succeeds when N children succeed (default: all)
class_name BTParallel extends BTComposite
@export var success_threshold: int = -1 # -1 = all children
func _tick(delta: float) -> Status:
var success_count := 0
var threshold := success_threshold if success_threshold > 0 else children.size()
for child in children:
var status := child.tick(delta)
if status == Status.SUCCESS:
success_count += 1
return Status.SUCCESS if success_count >= threshold else Status.RUNNING
Decorator Nodes
# Inverter: flips SUCCESS <-> FAILURE
class_name BTInverter extends BTDecorator
func _tick(delta: float) -> Status:
match child.tick(delta):
Status.SUCCESS: return Status.FAILURE
Status.FAILURE: return Status.SUCCESS
_: return Status.RUNNING
# Cooldown: prevents child from running more than once per interval
class_name BTCooldown extends BTDecorator
@export var cooldown_time: float = 2.0
var _last_success_time: float = -INF
func _tick(delta: float) -> Status:
if Time.get_ticks_msec() / 1000.0 - _last_success_time < cooldown_time:
return Status.FAILURE
var status := child.tick(delta)
if status == Status.SUCCESS:
_last_success_time = Time.get_ticks_msec() / 1000.0
return status
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 · 290 lines · 58 tokens per session scan A 4aed3cdac461
game-ai-patterns is a skill published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 58 tokens to every session and 2,654 once invoked, about $0.0002 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 skills, from other repositories
pygame-core
Structure a pygame (pygame-ce) game in Python: the init/event/update/draw loop, delta-time movement, Surface/Rect blitting, keyboard/mouse input, and Sprite/Group management with collision. Use when building or debugging a pygame game — when the user mentions pygame, pygame-ce, the game loop, blit, Surface, Rect…
cgs-adopt
Use for adopt tasks that inventory existing source, assets, docs, and tests before mapping work into CGS structure; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-architecture-decision
Use for architecture decision tasks that write an ADR with context, options, decision, consequences, validation, and rollback; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-architecture-review
Use for architecture review tasks that review architecture for layer violations, scalability risks, engine misuse, testing seams, and production readiness; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-art-bible
Use for art bible tasks that define visual identity, shape language, palette, camera, animation, UI style, and asset constraints; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-asset-audit
Use for asset audit tasks that audit game assets for completeness, naming, import settings, ownership, licensing, and production risk; produce verification evidence, changed or proposed files, and handoff boundaries.