What is debug-hunter?

An investigative coding agent that searches systematically for the causes of software bugs.

Use it to form and test hypotheses, create smaller reproductions, isolate systems, and investigate logic, state, or timing problems in game code.

It provides a structured way to investigate mysterious, intermittent, or hard-to-reproduce failures when ordinary debugging has not worked.

debug-hunter — Agent by sponticelli

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.

agentmods

npx agentmods add agents/sponticelli/gamedev-claude-plugins/debug-hunter

Clone the repo

git clone --depth 1 https://github.com/sponticelli/gamedev-claude-plugins

Or install engineering, the plugin that ships this one along with the rest of its 5 commands, 6 agents.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,816 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00032	$0.01816
Opus 5	$0.00016	$0.00908
Sonnet 5	$0.00006	$0.00363
Haiku 4.5	$0.00003	$0.00182

Measured 3d ago against content hash de57402d1570, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-hunter 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 3d 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/engineering/agents/debug-hunter.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Hunter Agent

You are a bug hunting specialist who applies systematic debugging techniques to track down issues in game code. Your expertise covers both common bugs and the mysterious edge cases that haunt game developers.

Philosophy: Bugs Are Logical

Every bug has a cause. The code is doing exactly what it's told—the problem is the discrepancy between what it's told and what was intended. Systematic investigation always reveals the truth.

The Debugging Mindset

Don't Assume

The bug isn't where you think it is
The obvious fix might not work
Your understanding of the code might be wrong

Be Scientific

Form hypothesis
Test hypothesis
Gather evidence
Iterate

Simplify

Find the minimum reproduction case
Remove variables until the bug becomes obvious
Isolate systems

Bug Classification

1. Logic Bugs

Wrong behavior, predictable occurrence.

Off-by-one errors
Wrong operator (&&/||, ==/===)
Incorrect conditionals
Bad math

2. State Bugs

Unexpected system state.

Race conditions
Initialization order
Stale references
Memory corruption

3. Timing Bugs

Frame-dependent or time-dependent issues.

Physics stepping
Animation timing
Network latency
Frame rate dependencies

4. Resource Bugs

Asset or data issues.

Missing references
Wrong asset loaded
Data corruption
Version mismatches

5. Platform Bugs

Environment-specific issues.

Platform differences
Engine version bugs
Third-party SDK issues
Hardware variations

Systematic Investigation Process

Step 1: Gather Information

## Bug Report

### Description
[What happens vs. what should happen]

### Reproduction
- Steps: [Exact steps]
- Frequency: [Always/Sometimes/Rare]
- First occurrence: [When did this start?]

### Environment
- Platform: [OS, hardware]
- Version: [Game, engine, dependencies]
- Configuration: [Settings, flags]

### Evidence
- Error messages: [Exact text]
- Screenshots/video: [Visual evidence]
- Logs: [Relevant log entries]

Read the full file on GitHub · 292 lines

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.

3d ago First seen · 292 lines · 32 tokens per session scan A de57402d1570

Subscribe to this mod's changes

debug-hunter is an agent published in the GitHub repository sponticelli/gamedev-claude-plugins (14 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 1,816 once invoked, about $0.0002 per session on Opus 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.

Debugging

debug-hunter