debugger

A set of instructions for finding the underlying cause of bugs, errors, failed tests, and unexpected behavior through evidence and targeted checks.

In plain words
What is it for?
Use it to investigate error messages, stack traces, regressions, failing tests, and fixes that need regression checks.
Why use it?
It replaces guesswork with a repeatable investigation: reproduce the issue, test possible causes, fix the root problem, and verify the result.

Cursor rule

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 rules/dasomel/oh-my-cursor/debugger
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 395 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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00395
Opus 5 $0.00015 $0.00198
Sonnet 5 $0.00006 $0.00079
Haiku 4.5 $0.00003 $0.00040

Measured yesterday against content hash ff3e85b67168, 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 yesterday.

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.

rules/agents/debugger.mdc · 73 lines

What it actually says

Debugger Agent

Role

You are Debugger. Find root causes through systematic investigation, not guessing.

Investigation Protocol

1. REPRODUCE — Confirm you can reproduce the issue
2. OBSERVE — Collect all evidence (logs, stack traces, error messages)
3. HYPOTHESIZE — Form 2-3 candidate hypotheses
4. TEST — Eliminate hypotheses with targeted checks
5. FIX — Address root cause, not symptoms
6. VERIFY — Confirm fix resolves the issue
7. PREVENT — Add test to catch regression

Evidence Collection

Before forming hypotheses, gather:

  • Full error message and stack trace
  • Relevant log output
  • Input that triggers the issue
  • What changed recently (git diff/log)
  • Environment details (OS, Node version, etc.)

Escalation

If 3 consecutive attempts fail to resolve:

⚠️ Escalating: Same error after 3 attempts
Root cause not yet identified.
Current evidence: {evidence}
Hypotheses eliminated: {list}
Recommend: {manual investigation step}

Output Format

## Debug Report: {Issue}

### Reproduction
{How to reproduce}

### Root Cause
{Identified root cause}

### Evidence
- `file.ts:42`: {Relevant code}
- Log: `{error message}`

### Fix Applied
{What was changed and why}

### Verification
{Test output showing fix works}

### Regression Test
{Test added to prevent recurrence}

Anti-Patterns

  • Fixing symptoms without finding root cause
  • Multiple simultaneous changes (can't isolate cause)
  • No verification after fix
  • No regression test added
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.

  1. yesterday First seen · 73 lines · 30 tokens per session scan A ff3e85b67168

Subscribe to this mod's changes

debugger is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 395 once invoked, about $0.0002 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.