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 dyCuong03/unity-agent-team --skill memory-safetygit clone --depth 1 https://github.com/dyCuong03/unity-agent-teamWrote 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/dycuong03/unity-agent-team/memory-safety)<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/memory-safety"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/memory-safety/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/dycuong03/unity-agent-team/memory-safety"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/memory-safety.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 | $0.00061 | $0.01010 |
| Opus 5.5 | $0.00024 | $0.00404 |
| Sonnet 5.5 | $0.00012 | $0.00202 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
memory-safety 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 11d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Safety
This is a skill pack, not an agent.
Allocator Decision Tree
Lifetime ≤ this frame, this scope → Allocator.Temp
Lifetime ≤ this job → Allocator.TempJob (dispose in job)
Lifetime spans frames (system state) → Allocator.Persistent (Dispose in OnDestroy)
Job allocates output for main thread → Allocator.TempJob
Asset/blob (read-only, long-lived) → BlobAssetReference<T> (no allocator)
Rule: every Allocator.Persistent allocation must have a matching Dispose()
in OnDestroy (for ISystem use state.Dispose-bound NativeArray/Lookup
fields). Otherwise the Job Safety System will leak across domain reloads.
Native Container Rules
- Never store a
NativeArrayallocated insideOnCreatewithoutDisposingit inOnDestroy. - Never pass a
NativeArrayto a job and reuse it on the main thread the same frame unless the job is.Complete()d first (= sync point — requires approval). - Never resize a
NativeListfrom a parallel job. UseNativeList<T>.ParallelWriter. - Don't share writable native containers across two parallel jobs without
dependency chaining. The Safety System will flag it as
InvalidOperationExceptionin editor; in player builds it silently corrupts. NativeHashMap<K,V>is not parallel-safe for writes. UseNativeParallelHashMap<K,V>.ParallelWriterfor writes from multiple threads.
Managed Allocation Hotspots
These are silent GC bombs inside OnUpdate / hot paths. Audit before signaling
verifier:
| Anti-pattern | Replace with |
|---|---|
string.Format(...) / $"..." |
FixedString*N*Bytes or skip the log |
new List<T>() |
NativeList<T>(Allocator.Temp) |
LINQ (.Where, .Select, .ToList) |
manual loop or IJobEntity |
Enum.GetValues(typeof(...)) |
a cached static readonly array outside hot path |
Boxing (e.g. object o = someStruct;) |
keep the type concrete |
Dictionary<K,V>.Add in hot path |
NativeParallelHashMap<K,V> |
Debug.Log("…" + obj) |
guard with #if UNITY_EDITOR if needed at all |
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.
- 11d ago First seen · 92 lines · 61 tokens per session scan A ace4ab7c6f7c
memory-safety is a skill published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 1,010 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 2026-10-02.
Other skills, from other repositories
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.