Root Cause Debugger

What it does

Root Cause Debugger is a Cursor agent playbook named debugger. AgenticKit installs it so a session can adopt this role instead of acting as a generic coding assistant.

The debugger agent takes stack traces, failing CI logs, or unexpected runtime behaviors and traces them through the codebase to pinpoint root causes. It creates minimal reproduction test cases and verifies fixes before concluding.

Specializes in troubleshooting memory leaks, concurrency bugs, and stack traces. Root cause debugger for Cursor that isolates broken test suites, solves runtime exceptions, and eliminates hard-to-reproduce edge case bugs.

Why it exists

A pile of agent files is not a team. debugger exists so one job, root cause debugger, has a written brief, required skills, and a stop condition.

It ships in the Engineering Kit. Skills it must read: Resilient Error Handling & Fault Tolerance; Vitest Unit & Integration Testing; Strict TypeScript Standards & Type Safety. Commands that adopt this role: /fix: Automated Bug & Exception Debugger; /audit: Codebase Quality & Security Auditor; /sre-incident: SRE Incident Responder & Root Cause Analysis.

When to use it

• Fixing complex TypeScript errors and async promises bugs
• Resolving Next.js hydration failures and React render loops
• Debugging silent API failures and uncaught exceptions

When not to use it

• Do not ask debugger to do a different role's job. If you need a launch post, switch agents.
• Do not keep the same chat after this agent has finished its artifact. Start a reviewer in a new thread.
• Do not invoke every agent in the kit for a small change.

Example workflow

1. Install the Engineering Kit so .cursor/agents/debugger is on disk.
2. Run /fix: Automated Bug & Exception Debugger, or start a chat and tell Cursor to adopt the debugger role.
3. The agent should read: Resilient Error Handling & Fault Tolerance; Vitest Unit & Integration Testing; Strict TypeScript Standards & Type Safety.
4. It produces the artifact for this role only, then stops.
5. A different agent or you review. Same-chat self-review is not a review.

Example usage

Example: "You are debugger. Fixing complex TypeScript errors and async promises bugs. Read error-handling before you edit."

Or let the pipeline invoke it: /fix: Automated Bug & Exception Debugger.

Capabilities you should actually see: Stack trace analysis and source map error mapping

Example output

• debugger should leave files or a written verdict, not a vibe check. Stack trace analysis and source map error mapping Memory leak and async race condition diagnostics
• Engineering agents should touch the slice they were given (schema, route, test, or review note) and nothing else.

Best practices

• Stack trace analysis and source map error mapping
• Memory leak and async race condition diagnostics
• Automated test failure reproduction and regression tests
• Clean, minimal bug fixes that do not introduce side effects
• One role per chat unless a command is explicitly orchestrating a sequence.

Common mistakes

• Using debugger as a synonym for 'the Cursor agent'. It is a brief, not the product.
• Skipping the required skills and hoping the role name is enough.
• Letting the writer approve its own PR.
• Invoking this agent and three unrelated ones in the same prompt.