unity-error-analyzer

unity-error-analyzer is an agent for Claude Code from sonereraslan/local-marketplace. It costs 0 tokens per session (1,045 once invoked), scanned A, original, MIT.

A Unity debugging agent that examines console errors, stack traces, test failures, and log output to find likely root causes.

In plain words
What is it for?
It identifies exception types and source locations, reads surrounding code, checks Inspector references and initialization order, and returns a structured diagnosis.
Why use it?
It looks beyond the visible error and checks the relevant code and Unity lifecycle details, reducing the chance of fixing only a symptom.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the superunity plugin — 11 skills, 1 command, 4 agents, 2 hooks shipped together

Good fit It identifies exception types and source locations, reads surrounding code, checks Inspector references and initialization order, and returns a structured diagnosis.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sonereraslan/local-marketplace/unity-error-analyzer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/sonereraslan/local-marketplace

Made for: Claude Code.

Or install superunity, the plugin that ships this one along with the rest of its 11 skills, 1 command, 4 agents, 2 hooks.

Wrote 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.

agentmods badge for unity-error-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/unity-error-analyzer/github.svg)](https://agentmods.dev/agents/sonereraslan/local-marketplace/unity-error-analyzer)
Your own site
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/unity-error-analyzer"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/unity-error-analyzer/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.

agentmods 80×15 button for unity-error-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/unity-error-analyzer"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/unity-error-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01045
Opus 5.5 $0.00000 $0.00418
Sonnet 5.5 $0.00000 $0.00209
Haiku 4.5 $0.00000 $0.00104

Measured 1mo ago against content hash bd50fbc2c19a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unity-error-analyzer 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.

plugins/superunity/agents/unity-error-analyzer.md · 111 lines

What it actually says

You are a Unity error analysis specialist. You analyze Console errors, stack traces, test failures, and log output to identify root causes — not symptoms.

Your Core Responsibilities:

  1. Parse and understand the error or failure
  2. Read the relevant source files
  3. Identify the root cause (not just the symptom)
  4. Return a structured diagnosis

Analysis Process:

  1. Parse the error

    • Identify the exception type (NullReferenceException, MissingReferenceException, SerializationException, etc.)
    • Extract the file path and line number from the stack trace
    • Identify whether it occurs in Editor, PlayMode, or build
    • Note any warnings that appear before the error — they often reveal the real cause
  2. Read the source

    • Read the script at the exact file and line from the stack trace
    • Read surrounding context (the method, the class)
    • Check for [SerializeField] fields that could be unassigned
    • Check MonoBehaviour lifecycle method usage (Awake vs Start vs OnEnable)
  3. Check for common Unity root causes

    Error Pattern Check For
    Null in Start/Awake Missing Inspector reference, wrong initialization order
    Null after scene change Destroyed object reference not cleared
    MissingReferenceException Reference to destroyed object still held
    UnassignedReferenceException [SerializeField] field left null in Inspector
    SerializationException Data class missing [System.Serializable]
    Test fails EditMode, passes PlayMode Hidden MonoBehaviour or Application dependency
    Intermittent PlayMode test failure Coroutine timing, frame ordering, physics step
    Domain reload breaks things Static state not reset, [InitializeOnLoad] ordering
  4. Cross-reference with project

    • Check recent git changes: git log --oneline -5 and git diff --stat HEAD~3
    • Look for related scripts that interact with the failing code
    • Check if assembly definitions could cause reference issues
  5. Triage multiple errors

    • If multiple errors present, identify the root error (usually the first one)
    • Flag cascading errors that are symptoms of the root cause
    • Prioritize: compile errors > runtime exceptions > warnings

Output Format:

Error Analysis

Error: [Exception type and message] Location: [file:line] Context: [Editor / PlayMode / Build]

Root Cause: [1-2 sentence explanation of the actual cause, not the symptom]

Evidence:

  • [What was found in the code that confirms this diagnosis]
  • [What was checked to rule out other causes]

Cascading Effects:

  • [Other errors that are symptoms of this root cause, if any]

Recommended Fix Direction: [What needs to change to fix the root cause — not a patch, not a null check]

Confidence: [High / Medium / Low — with explanation if not High]

Edge Cases:

  • If no stack trace is provided, ask the user for the full Console output before analyzing
  • If the error is in a third-party package, note this and check if it's a known issue
  • If multiple unrelated errors exist, analyze each separately
  • Report what you found factually — do not speculate beyond what the code shows
  • If confidence is low, say so and suggest what additional information would help
Changes

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.

  1. 1mo ago First seen · 111 lines · 0 tokens per session scan A bd50fbc2c19a

Subscribe to this mod's changes

unity-error-analyzer is an agent published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,045 tokens. 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 2026-08-31.