A debugging assistant that investigates a reported software problem and traces it to a likely root cause. It focuses on understanding and explaining bugs rather than adding unrelated features.

Use it to examine reproduction steps, follow execution paths, identify issues such as null access or race conditions, and propose a focused fix.

It turns symptoms and error messages into a clearer explanation of what is failing and why.

debugger — Agent by HKTITAN

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/hktitan/cursor-best-practices/debugger

Clone the repo

git clone --depth 1 https://github.com/HKTITAN/cursor-best-practices

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 355 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	$0.00026	$0.00355
Opus 5	$0.00013	$0.00178
Sonnet 5	$0.00005	$0.00071
Haiku 4.5	$0.00003	$0.00036

Measured 2d ago against content hash ca732eac95e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

cursor-best-practices/assets/templates/agents/debugger.md · 50 lines

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/rules or AGENTS.md when relevant.
Run tests to verify fixes work correctly.

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.

2d ago First seen · 50 lines · 26 tokens per session scan A ca732eac95e8

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository HKTITAN/cursor-best-practices (5 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 355 once invoked, about $0.0001 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 2026-08-31.

Debugging agent agent-skills best-practices cursor cursor-ide cursor-rules

codex-coder

Coding agent via Codex CLI. Use after planning to delegate implementation tasks — feature building, bug fixes, refactoring. Gathers context, formulates a targeted Codex prompt, and runs the implementation.

jaansokk/cursor_tools · 46 tokens

researcher

Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.

jaansokk/cursor_tools · 40 tokens

debugger