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-addressablesnpx skills add TheArcForge/Hades --skill unity-addressablesgit clone --depth 1 https://github.com/TheArcForge/HadesWrote 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/thearcforge/hades/unity-addressables)<a href="https://agentmods.dev/skills/thearcforge/hades/unity-addressables"><img src="https://agentmods.dev/badge/skills/thearcforge/hades/unity-addressables.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.06111 |
| Opus 5 | $0.00015 | $0.03055 |
| Sonnet 5 | $0.00006 | $0.01222 |
| Haiku 4.5 | $0.00003 | $0.00611 |
Grade A, and why
unity-addressables 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 4d 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 — 740 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Addressables
Deep decision framework for asset loading and memory management in Unity. Covers when to adopt Addressables over Resources or direct references, group design, async loading with AsyncOperationHandle, memory lifecycle (load → use → release), ref-counting patterns, and content update workflows via CCD. Untracked handles are the most common source of memory leaks in Addressables projects.
When to Apply
Activate when the conversation involves:
- Deciding whether to use Addressables, Resources, or direct serialized references for an asset
- Loading or instantiating an asset at runtime from a path or label
- Tracking and releasing
AsyncOperationHandleinstances to avoid memory leaks - Designing Addressable groups (by scene, feature, update frequency)
- Preloading assets before a scene or gameplay segment begins
- Streaming downloadable content or supporting remote catalogs
- Diagnosing unexpectedly high memory from loaded-but-unreleased assets
Do NOT activate for in-scene prefab wire-up where the asset is always needed and always loaded — that belongs to hades:prefab-architecture. For questions about how scenes themselves are structured and loaded, see hades:scene-architecture.
Project Context Check
Before making recommendations, gather project-specific context so advice is calibrated to the actual codebase.
-
Check if Addressables is already in use:
- Call
search_by_name("*AddressableAsset*")— finds AddressableAssetSettings, AddressableAssetGroup, and AddressableAssetData files. If none exist, the project has not adopted Addressables yet; adjust the scope of advice accordingly. - Call
graph_query(edgeKind: "references", edgeTargetNamePattern: "AssetReference", edgeTargetKind: "Class")— locates MonoBehaviours withAssetReferencefields, indicating Addressables is already wired into gameplay code.
- Call
-
Assess project scale:
- Call
get_project_summary()— reveals total asset count, scene count, and build targets. Addressables provide the most value in large projects (many assets) or projects with remote content. Small prototypes rarely justify the setup cost.
- 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.
- 4d ago First seen · 740 lines · 29 tokens per session scan A 9113506533c7
unity-addressables is a skill published in the GitHub repository TheArcForge/Hades (27 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 6,111 once invoked, about $0.0001 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…
cgs-perf-profile
Use for perf profile tasks that profile frame time, memory, loading, assets, rendering, scripting, and platform constraints; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-soak-test
Use for soak test tasks that plan longer stability checks for memory, performance drift, save/load, networking, and live-ops loops; produce verification evidence, changed or proposed files, and handoff boundaries.
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.
load
Load a branch-specific CLAUDE.md memory file. Use when the user wants to load context from a different branch.
save
Save the current CLAUDE.md to branch-specific memory. Use when the user wants to save their current branch context.