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/commands/hermeticormus/claude-code-game-development/game-ai)<a href="https://agentmods.dev/commands/hermeticormus/claude-code-game-development/game-ai"><img src="https://agentmods.dev/badge/commands/hermeticormus/claude-code-game-development/game-ai/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/commands/hermeticormus/claude-code-game-development/game-ai"><img src="https://agentmods.dev/badge/commands/hermeticormus/claude-code-game-development/game-ai.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 | $0.00023 | $0.00801 |
| Opus 5.5 | $0.00009 | $0.00320 |
| Sonnet 5.5 | $0.00005 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
game-ai 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 — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/game-ai
AI behavior design and implementation for NPCs. Covers behavior trees, FSMs, utility AI, GOAP, navigation, and perception systems.
Trigger
/game-ai [action] [target]
Actions
design
Design an AI architecture for an NPC type. Outputs ASCII state diagram or BT structure + blackboard schema.
/game-ai design "patrol guard with alert states"
/game-ai design "boss enemy with phase transitions"
/game-ai design "companion follower with utility AI"
Output: Architecture recommendation with rationale, ASCII diagram, blackboard schema as typed GDScript Resource.
implement
Generate GDScript implementation for a specified AI system.
/game-ai implement bt "3-state patrol -> investigate -> attack"
/game-ai implement fsm "enemy with push-down automata for interrupts"
/game-ai implement utility "NPC action scorer with 4 considerations"
/game-ai implement goap "action set for combat agent"
Output: Full GDScript with typed variables, @export parameters, inline comments explaining pattern choices.
debug
Diagnose AI behavior problems from description or code.
/game-ai debug "NPC gets stuck between two waypoints"
/game-ai debug "enemy never transitions out of idle state"
/game-ai debug "pathfinding works but NPC stutters on arrival"
Output: Root cause analysis, specific code fix, prevention pattern.
tune
Tune consideration curves, BT tick rates, or FSM timeout values.
/game-ai tune "utility scores all feel equal, no clear winner"
/game-ai tune "BT too expensive, 200 NPCs at 60fps drops to 30fps"
/game-ai tune "patrol timeout too short, NPCs always re-alert"
Output: Parameter adjustments with reasoning, performance budget calculations.
Examples
Designing a stealth game guard:
/game-ai design "stealth guard: unaware -> suspicious -> alerted -> searching"
Produces: 4-state HFSM with push-down investigative substates, alert meter as utility consideration, vision cone + hearing radius sensor setup.
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 · 96 lines · 23 tokens per session scan A 3de4524d5b62
game-ai is a command published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 23 tokens to every session and 801 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.