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/input-system)<a href="https://agentmods.dev/commands/hermeticormus/claude-code-game-development/input-system"><img src="https://agentmods.dev/badge/commands/hermeticormus/claude-code-game-development/input-system/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/input-system"><img src="https://agentmods.dev/badge/commands/hermeticormus/claude-code-game-development/input-system.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 | $0.00013 | $0.00754 |
| Opus 5.5 | $0.00005 | $0.00302 |
| Sonnet 5.5 | $0.00003 | $0.00151 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
input-system 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:
- input-system — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/input-system
Input mapping, deadzone configuration, rebinding, input buffering, and multi-platform input support.
Trigger
/input-system [action] [target]
Actions
configure
Set up InputMap actions with keyboard and gamepad bindings.
/input-system configure "third-person action game: move, jump, attack, dodge, interact, camera"
/input-system configure "RTS: select, multi-select, move, attack-move, camera pan/zoom"
/input-system configure "menu navigation with keyboard and gamepad d-pad"
Output: InputMap action list, default keyboard and gamepad bindings, GDScript configuration code.
rebind
Implement input rebinding UI and serialization.
/input-system rebind "in-game keybinding menu with conflict detection"
/input-system rebind "save and load custom bindings to user:// directory"
/input-system rebind "reset to defaults button"
Output: InputRebinder GDScript, serialization format, conflict detection logic.
test
Input buffering and game feel improvements.
/input-system test "jump feels unresponsive on controller"
/input-system test "attack combo drops inputs at high animation speed"
/input-system test "movement feels floaty on gamepad analog stick"
Output: Root cause analysis, buffer/coyote implementation, deadzone correction.
polish
Platform-specific input polish: rumble, prompts, mobile touch.
/input-system polish "show correct button prompts for connected device (keyboard vs controller)"
/input-system polish "haptic rumble for player damage and attacks"
/input-system polish "mobile virtual joystick for movement"
Output: Device detection code, prompt switching system, rumble pattern library, or VirtualJoystick Control.
Examples
Implementing jump buffer + coyote time:
/input-system test "platformer jump feels inconsistent on gamepad"
Produces: PlatformerInput node with 8-frame jump buffer and 6-frame coyote time, consume_jump() interface for CharacterBody3D.
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 · 103 lines · 13 tokens per session scan A 86f3e384e7f7
input-system is a command published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 13 tokens to every session and 754 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.