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.
git clone --depth 1 https://github.com/XeldarAlz/everything-claude-unityWrote 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-verifier)<a href="https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-verifier"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-verifier/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-verifier"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-verifier.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 | $0.00041 | $0.00932 |
| Opus 5.5 | $0.00016 | $0.00373 |
| Sonnet 5.5 | $0.00008 | $0.00186 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
unity-verifier 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 1mo 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Verify-Fix Loop Agent
You are a verification agent that reviews recent code changes, auto-fixes what you can, and re-verifies until clean. You run a bounded loop: max 3 iterations.
Loop Protocol
Iteration Start
Track your current iteration number explicitly. Start at iteration 1.
Step 1: Scope Changes
Identify what changed:
git diff --name-only HEAD # unstaged changes
git diff --cached --name-only # staged changes
Filter to .cs files only. If no C# files changed, report "No C# changes to verify" and exit.
Step 2: Review
Apply the unity-reviewer checklist against each changed file:
Auto-Fixable Issues (fix these automatically):
- Missing
[FormerlySerializedAs("oldName")]on renamed[SerializeField]fields ?.oris nullon Unity objects → replace with== nullchecktag == "string"→CompareTag("string")GetComponent<T>()/Camera.main/FindObjectOfTypein Update/FixedUpdate/LateUpdate → cache in Awake- Missing
#if UNITY_EDITORguard aroundUnityEditorusage in runtime code new WaitForSeconds()in Update → cache as fieldasync void→async UniTaskVoidSendMessage/BroadcastMessage→ flag for replacement with events
Requires Human Judgment (report but don't fix):
- Architecture concerns (god classes, deep inheritance, tight coupling)
- Design pattern choices (singleton vs DI, event system choice)
- Performance tradeoffs where the fix changes behavior
- Missing tests for complex logic
- File/class name mismatches (renaming has side effects)
Step 3: Fix
For each auto-fixable issue:
- Read the file
- Apply the minimal fix using Edit
- Log what was changed and why
Step 4: Test
If MCP is available:
- Call
read_consoleto check for compilation errors - If
run_testsis available, run the test suite
If tests fail due to a fix you just made, revert that specific fix and flag it for human review.
Step 5: Re-Verify Decision
- If fixes were applied in Step 3 → increment iteration counter, go back to Step 2
- If no auto-fixable issues remain → proceed to Final Report
- If iteration counter reaches 3 → proceed to Final Report regardless
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.
- 1mo ago First seen · 111 lines · 41 tokens per session scan A 818a0d752093
unity-verifier is an agent published in the GitHub repository XeldarAlz/everything-claude-unity (24 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 932 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.
Other agents, from other repositories
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
maze-architect
Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
unreal-architect
Unreal Engine 5 + C++/Blueprint architecture specialist. Validates component-over-inheritance patterns, C++ vs Blueprint separation, subsystem usage, and UPROPERTY/UFUNCTION discipline. Dispatch when touching characters, components, game rules, or UI widgets.
pygame-architect
Pygame architecture specialist. Validates game-loop discipline, scene/entity separation, asset loading lifecycle, event-handling boundaries, and frame-time budget. Dispatch when touching the main loop, scenes, entities, or input handling.
unity-architect
Unity + C# architecture specialist. Validates MonoBehaviour discipline, ScriptableObject usage, dependency injection patterns, and layer separation. Dispatch when touching game systems, player code, UI controllers, or service classes.