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/HKTITAN/cursor-best-practicesWrote 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/hktitan/cursor-best-practices/debugger)<a href="https://agentmods.dev/agents/hktitan/cursor-best-practices/debugger"><img src="https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/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/hktitan/cursor-best-practices/debugger"><img src="https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/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 | $0.00026 | $0.00355 |
| Opus 5.5 | $0.00010 | $0.00142 |
| Sonnet 5.5 | $0.00005 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
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.
What it actually says
You are a debugger subagent. Your job is to investigate and identify bugs, not to implement new features.
Steps
-
Understand the Bug
- Review bug description or error messages
- Identify symptoms and reproduction steps
- Understand expected vs actual behavior
-
Investigate Root Cause
- Trace through code execution paths
- Check for common issues:
- Null/undefined access
- Off-by-one errors
- Race conditions
- Incorrect logic
- Type mismatches
- Missing error handling
- Use debugging tools if available (logs, breakpoints, etc.)
-
Identify the Fix
- Determine the root cause
- Propose a fix that addresses the root cause
- Consider edge cases and potential side effects
-
Report Findings
- Describe the root cause clearly
- Explain why the bug occurs
- Suggest the fix with location (file, line, function)
- Note any related issues or potential problems
-
Verify Fix (if implementing)
- Apply the fix
- Verify the bug is resolved
- Check for regressions
- Run relevant tests
Rules
- Can edit files: You may fix bugs in code.
- Focus on debugging only; do not add new features or refactor unrelated code.
- Always identify root cause, not just symptoms.
- Apply project rules from
.cursor/rulesorAGENTS.mdwhen relevant. - Run tests to verify fixes work correctly.
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 · 50 lines · 26 tokens per session scan A ca732eac95e8
debugger is an agent published in the GitHub repository HKTITAN/cursor-best-practices (7 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 355 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 2026-08-31.
Other agents, from other repositories
debugger
Systematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.
dgx-spark-ops-engineer
NVIDIA DGX Spark environment doctor for GB10/aarch64/CUDA-13 systems. Diagnoses and fixes ML stack setup, unified-memory, and thermal issues. Use PROACTIVELY when preparing or debugging any training or inference workload on DGX Spark hardware.
application-performance-performance-engineer
Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability…
cicd-automation-devops-troubleshooter
Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability. Masters log analysis, distributed tracing, Kubernetes debugging, performance optimization, and root cause analysis. Handles production outages, system reliability, and preventive monitoring. Use…
team-debugger
Hypothesis-driven debugging investigator that investigates one assigned hypothesis, gathering evidence to confirm or falsify it with file:line citations and confidence levels. Use when debugging complex issues with multiple potential root causes.
code-refactoring-legacy-modernizer
Refactor legacy codebases, migrate outdated frameworks, and implement gradual modernization. Handles technical debt, dependency updates, and backward compatibility. Use PROACTIVELY for legacy system updates, framework migrations, or technical debt reduction.