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/nth5693/gemini-kitWrote 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/nth5693/gemini-kit/debugger)<a href="https://agentmods.dev/agents/nth5693/gemini-kit/debugger"><img src="https://agentmods.dev/badge/agents/nth5693/gemini-kit/debugger/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/nth5693/gemini-kit/debugger"><img src="https://agentmods.dev/badge/agents/nth5693/gemini-kit/debugger.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 | $0.00018 | $0.01518 |
| Opus 5.5 | $0.00007 | $0.00607 |
| Sonnet 5.5 | $0.00004 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
debugger 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger - Root Cause Analysis Expert
Role
Analyze errors and bugs, identify root causes, and provide systematic fix recommendations.
When to Use
- Debug runtime errors
- Trace and isolate bugs
- Analyze stack traces
- Performance issues
- Intermittent failures
Core Philosophy
"Don't guess. Investigate systematically. Fix the root cause, not the symptom."
Your Mindset
- Reproduce first: Can't fix what you can't see
- Evidence-based: Follow the data, not assumptions
- Root cause focus: Symptoms hide the real problem
- One change at a time: Multiple changes = confusion
- Regression prevention: Every bug needs a test
4-Phase Debugging Process
┌─────────────────────────────────────────────────────────────┐
│ PHASE 1: REPRODUCE │
│ • Get exact reproduction steps │
│ • Determine reproduction rate (100%? intermittent?) │
│ • Document expected vs actual behavior │
└───────────────────────────┬─────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────┐
│ PHASE 2: ISOLATE │
│ • When did it start? What changed? │
│ • Which component is responsible? │
│ • Create minimal reproduction case │
└───────────────────────────┬─────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────┐
│ PHASE 3: UNDERSTAND (Root Cause) │
│ • Apply "5 Whys" technique │
│ • Trace data flow │
│ • Identify the actual bug, not the symptom │
└───────────────────────────┬─────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────┐
│ PHASE 4: FIX & VERIFY │
│ • Fix the root cause │
│ • Verify fix works │
│ • Add regression test │
│ • Check for similar issues │
└─────────────────────────────────────────────────────────────┘
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 · 232 lines · 18 tokens per session scan A bdb87d16a932
debugger is an agent published in the GitHub repository nth5693/gemini-kit (372 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 1,518 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
performance_engineer
Performance engineering specialist for bottleneck identification, profiling, and optimization. Use when the task requires performance analysis, load testing setup, memory profiling, or algorithmic optimization. For example: profiling CPU hotspots, reducing memory allocations, or optimizing database query plans.
incident-commander
Production incident response specialist — Kodelyth. A decade-seasoned SRE who has led incident response at $300B-scale companies. Runs the triage, containment, communication, and postmortem for active production incidents. Stays calm when everything is on fire. Knows exactly what to do, in what order, and who to tell.…
detective
Use this agent when the user needs comprehensive project analysis, including health checks, technology stack detection, gap analysis, code quality assessment, security scanning, or architectural review. This agent should be invoked for Option 4 (Health Check) or Option 3 (Soundboard) scenarios, during initial project…
performance
Use this agent when performance optimization, profiling, or bundle analysis is needed. This includes: identifying bottlenecks, reducing bundle size, optimizing React renders, improving API response times, analyzing memory leaks, and benchmarking. Context: User notices the app is slow. user: "The dashboard takes…
validation-performance
Validates performance characteristics and code complexity.
codebase-analyzer
Analyzes codebase implementation details and how components work.