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 jame581/GodotPrompter --skill ability-systemgit clone --depth 1 https://github.com/jame581/GodotPrompterWrote 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/jame581/godotprompter/ability-system)<a href="https://agentmods.dev/skills/jame581/godotprompter/ability-system"><img src="https://agentmods.dev/badge/skills/jame581/godotprompter/ability-system.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.02816 |
| Opus 5 | $0.00017 | $0.01408 |
| Sonnet 5 | $0.00007 | $0.00563 |
| Haiku 4.5 | $0.00003 | $0.00282 |
Grade A, and why
ability-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 8d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ability System
Build a data-driven ability system from Godot-native parts: abilities are Resources, an AbilityComponent node owns and runs them, and effects/stats/tags compose on top. No third-party addon required.
Related skills: resource-pattern for the
Resourcedata containers, component-system for the component node pattern, event-bus for cross-system ability events, state-machine for caster states (e.g. casting/stunned), hud-system for cooldown UI.
1. Architecture overview
An ability system in Godot 4.x is built from three collaborating layers:
-
Data layer —
Ability(Resource): Each ability is aResourcesubclass with exported fields (ability_name,cost,cooldown,cast_time) and two methods:can_activate(caster) -> boolto validate preconditions, andactivate(caster) -> voidto execute the effect. Storing abilities as Resources lets designers create and balance them in the Godot editor without touching code. -
Behaviour layer —
AbilityComponent(Node): A single node added to any entity that should use abilities. It holds the granted ability set, enforces cost/cooldown, and drives theAbility.activate()call. Four signals keep the rest of the game informed without coupling:ability_activated(ability),ability_failed(ability, reason),cooldown_started(ability, duration), andcooldown_finished(ability). Grant new abilities at runtime withgrant(ability)and trigger them withtry_activate(ability_name). -
Effects layer — stat modifiers, buffs/debuffs, and gameplay tags: Abilities can read from and write to a caster's
StatSet(a Resource that owns a dictionary of namedStatModifierentries) to apply temporary or permanent stat changes. AGameplayTagContainernode (a child of the caster) gates activation — for example, a "stunned" tag can prevent any ability from firing. These three deep-dives are covered in the reference documents:
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 329 lines · 34 tokens per session scan A f90fe4121a56
ability-system is a skill published in the GitHub repository jame581/GodotPrompter (677 stars, last pushed 25d ago), licensed MIT. It adds 34 tokens to every session and 2,816 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
roblox-audio
Use when implementing Roblox audio playback, spatial sound, music, sound effects, SoundGroups, or dynamic audio effects.
roblox-camera
Use when scripting Roblox camera behavior, CFrame placement, screen raycasts, first or third-person views, or cutscenes.
roblox-input
Use when handling Roblox keyboard, mouse, gamepad, touch, motion input, or cross-platform action binding.
roblox-lighting
Use for Roblox lighting, atmosphere, day/night, or post-processing effects.
roblox-localization
Use when implementing Roblox multi-language support, translation tables, auto-translation, locale-specific content, or region detection.
roblox-luau-core
Use for Luau language semantics, tables, control flow, string patterns, scope, closures, and cross-language translation errors.