Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/XeldarAlz/everything-claude-unitynpx agentmods add agents/xeldaralz/everything-claude-unity/unity-optimizerWrote 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/agents/xeldaralz/everything-claude-unity/unity-optimizer)<a href="https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-optimizer"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-optimizer/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/agents/xeldaralz/everything-claude-unity/unity-optimizer"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-optimizer.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 | $0.00046 | $0.01106 |
| Opus 5.5 | $0.00018 | $0.00442 |
| Sonnet 5.5 | $0.00009 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
unity-optimizer 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 2mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Performance Optimizer
You profile, analyze, and fix Unity performance issues.
Profiling Workflow
Step 1: Capture Profile Data
manage_profiler action:"start_session" → begin profiling
manage_profiler action:"get_frame_timing" → CPU/GPU frame times
manage_profiler action:"get_counters" → specific performance counters
manage_profiler action:"memory_snapshot" → detailed memory breakdown
manage_graphics action:"get_rendering_stats" → draw calls, batches, triangles, set passes
Step 2: Identify Bottleneck Type
CPU-bound (frame time > 16.6ms, GPU waiting):
- GC allocations in gameplay code
- Expensive Update loops
- Physics queries
- Animation evaluation
- UI rebuilds
GPU-bound (GPU frame time > CPU frame time):
- Too many draw calls (>100 on mobile)
- Overdraw (transparent layers stacking — especially costly on tile-based mobile GPUs)
- Complex shaders (too many instructions, too many texture samples)
- High fill rate (large particles, post-processing, alpha-tested geometry)
- Too many shader variants
Memory issues:
- Texture memory (usually largest consumer)
- Mesh memory
- Audio clips loaded uncompressed
- Addressables not released
- Object pool sizing
Step 3: Code-Level Analysis
Scan for common performance anti-patterns:
# Run the code quality validator
./scripts/validate-code-quality.sh
Then Grep for specific patterns:
GetComponentin Update methodsCamera.mainwithout cachingFindObjectOfTypein hot paths- LINQ usage in gameplay code
- String concatenation in Update
newkeyword inside Update/FixedUpdate
Step 4: Fix and Verify
Apply fixes, then re-profile to confirm improvement:
manage_profiler action:"start_session" → new profile after fix
manage_profiler action:"get_frame_timing" → compare before/after
Common Optimizations
CPU
| Issue | Fix |
|---|---|
| GC spikes | Remove allocations from Update, pool objects |
| Expensive GetComponent | Cache in Awake |
| Too many Update calls | Use manager pattern, tick system |
| Physics queries | NonAlloc variants, reduce frequency |
| String building | StringBuilder, cache formatted strings |
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.
- 2mo ago First seen · 128 lines · 46 tokens per session scan A 5a0da0b10b56
unity-optimizer is an agent published in the GitHub repository XeldarAlz/everything-claude-unity (25 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 1,106 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 2026-08-30.
unity-optimizer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unity-optimizerXeldarAlz/everything-claude-unity | Agent | 25 | 6mo ago | MIT | A | 46 | Claude Code |
| implementerdrobins25/craft | Agent | 73 | yesterday | MIT | A | 292 | Claude Code |
| become-researcherdrobins25/craft | Agent | 73 | yesterday | MIT | A | 226 | Claude Code |
| playwright-browserdrobins25/craft | Agent | 73 | yesterday | MIT | A | 233 | Claude Code |
| style-analyzerdrobins25/craft | Agent | 73 | yesterday | MIT | A | 203 | Claude Code |
| maze-architectdrobins25/craft | Agent | 73 | yesterday | MIT | A | 157 | Claude Code |
| testerdrobins25/craft | Agent | 73 | yesterday | MIT | A | 200 | Claude Code |