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/sponticelli/gamedev-claude-pluginsWrote 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/sponticelli/gamedev-claude-plugins/debug-hunter)<a href="https://agentmods.dev/agents/sponticelli/gamedev-claude-plugins/debug-hunter"><img src="https://agentmods.dev/badge/agents/sponticelli/gamedev-claude-plugins/debug-hunter/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/sponticelli/gamedev-claude-plugins/debug-hunter"><img src="https://agentmods.dev/badge/agents/sponticelli/gamedev-claude-plugins/debug-hunter.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 | $0.00032 | $0.01816 |
| Opus 5.5 | $0.00013 | $0.00726 |
| Sonnet 5.5 | $0.00006 | $0.00363 |
| Haiku 4.5 | $0.00003 | $0.00182 |
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 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 — 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]
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 · 292 lines · 32 tokens per session scan A de57402d1570
debug-hunter is an agent published in the GitHub repository sponticelli/gamedev-claude-plugins (17 stars, last pushed 9mo ago), licensed MIT. It adds 32 tokens to every session and 1,816 once invoked, about $0.0001 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
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.