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 wave8-dependency-complete-editor-only-fencegit 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/wave8-dependency-complete-editor-only-fence)<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/wave8-dependency-complete-editor-only-fence"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/wave8-dependency-complete-editor-only-fence/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/wave8-dependency-complete-editor-only-fence"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/wave8-dependency-complete-editor-only-fence.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 | $0.00040 | $0.00847 |
| Opus 5.5 | $0.00016 | $0.00339 |
| Sonnet 5.5 | $0.00008 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
wave8-dependency-complete-editor-only-fence 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
state.Dependency.Complete() — Editor-Only Diagnostic Fence
Intent
Use state.Dependency.Complete() only as an editor-mode diagnostic fence to inspect intermediate job state, never as a production pattern for forcing job completion.
Use When
- Adding a temporary diagnostic fence in editor builds to isolate a job scheduling bug or verify intermediate NativeArray state
- Confirming a job's output in isolation before wiring it into a dependency chain
Avoid When
- In any shipping build or production system — Complete() is a sync point anti-pattern
- As a substitute for proper job dependency chaining — fix the chain, do not paper over it
Senior Pattern
// EDITOR-ONLY diagnostic fence — not for production:
public partial struct DiagnosticSystem : ISystem
{
public void OnUpdate(ref SystemState state)
{
var results = CollectionHelper.CreateNativeArray<int>(100, state.WorldUpdateAllocator);
var job = new ComputeJob { Results = results };
state.Dependency = job.Schedule(state.Dependency);
#if UNITY_EDITOR
// Force sync to inspect intermediate state — remove before shipping:
state.Dependency.Complete();
UnityEngine.Debug.Log($"Intermediate result[0]: {results[0]}");
#endif
// Production: dependency chain propagates — no Complete() needed
}
}
// PRODUCTION correct pattern — never forced Complete():
[BurstCompile]
public partial struct ProductionSystem : ISystem
{
[BurstCompile]
public void OnUpdate(ref SystemState state)
{
var results = CollectionHelper.CreateNativeArray<int>(100, state.WorldUpdateAllocator);
state.Dependency = new ComputeJob { Results = results }
.ScheduleParallel(state.Dependency);
// Dependency propagates to consuming systems automatically
}
}
Anti-Patterns
state.Dependency.Complete()in every OnUpdate "to be safe" — full sync point every frame; eliminates all job parallelism; main-thread stall equal to all scheduled job duration.- Using Complete() to read job output without
#if UNITY_EDITORguard — ships the anti-pattern into production builds. - Using Complete() as a substitute for proper dependency chaining — masks scheduling bugs rather than fixing them.
- Calling Complete() at the start of OnUpdate to "wait for last frame's jobs" — indicates incorrect Allocator.Persistent usage; switch to WorldUpdateAllocator.
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 · 81 lines · 40 tokens per session scan A 7b8ed418f4ed
wave8-dependency-complete-editor-only-fence is a skill published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 847 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
graphics-api-hooking
Analyze Direct3D, DXGI, OpenGL, or Vulkan rendering, overlays, presentation, capture, and measurement evidence. Use when the graphics pipeline or frame-observation boundary is central.
cli-anything-nsight-graphics
Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
mirrord-up
Helps users run multiple concurrent mirrord sessions from a single mirrord-up.yaml (compose-style multi-service local debugging). Use when the user mentions mirrord up, mirrord-up.yaml, mirrord up init, debugging several related microservices together, or managing multiple mirrord sessions' lifecycle in one command.
console-get-logs
Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.
editor-application-get-state
Return the current state of UnityEditor.EditorApplication — playmode, paused state, compilation state, and related flags.