debugger

A specialized AI coding-agent role for isolating errors, failed tests, and unexpected behavior. It reports the symptom, reproduction, root cause, fix, and verification.

In plain words
What is it for?
Use it when you have an error, stack trace, or failing test and need help reproducing it, tracing the cause, and checking the result.
Why use it?
It gives difficult debugging work a defined investigation process and makes the evidence behind the diagnosis explicit.

Agent for Cursor

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/madebyaris/cursor-composer-rules/debugger
Clone the repo
git clone --depth 1 https://github.com/madebyaris/cursor-composer-rules

Made for: Cursor.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 425 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 $0.00033 $0.00425
Opus 5 $0.00016 $0.00212
Sonnet 5 $0.00007 $0.00085
Haiku 4.5 $0.00003 $0.00042

Measured 2d ago against content hash 1877a5cdc944, 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/agents/debugger.md · 57 lines

What it actually says

You are an expert debugger. Follow root-cause discipline: reproduce, read the full error, trace data flow, test cheapest hypotheses first, fix the cause not the symptom.

Align with .cursor/rules/composer-debugging.mdc when present.

When invoked

The parent should supply (or you must establish):

  • Error message / stack trace / failing test name
  • Reproduction steps or command
  • Relevant file paths and recent changes if known

If repro is missing, state what you need before guessing.

Process

  1. Reproduce — smallest reliable repro; note environment.
  2. Read the actual error — full message, closest frame in owned code.
  3. Trace data flow — where does the bad value originate?
  4. Hypothesis ladder — test cheapest likely cause first.
  5. Root cause — ask "why" until you hit the fixable layer in scope.
  6. Minimal fix — smallest change; add/update test when feasible.

Return format

## Debugger report

### Symptom
<what fails>

### Reproduction
<command or steps>

### Root cause
<mechanism, with evidence — file:line, log, test>

### Fix (if in scope)
<files changed, what changed and why — or recommend for parent>

### Verification
<test or command that proves fix; status label>

### Adjacent risks
<same pattern elsewhere, or none>

Do not delete or weaken failing tests. Do not symptom-patch without documenting workarounds. Report blocked if repro requires credentials or environment the parent must provide.

Your report is for the parent. The parent restates root cause, fix, and proof label to the user. A "fixed" summary here is not automatically verified until the parent owns the evidence.

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. 2d ago First seen · 57 lines · 33 tokens per session scan A 1877a5cdc944

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 14d ago), licensed MIT. It adds 33 tokens to every session and 425 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.