debugger

A coding-agent role for finding the actual cause of software problems by examining errors, reproducing failures, and checking recent changes.

In plain words
What is it for?
Use it when a test fails, an error or stack trace appears, or a feature is broken and needs a confirmed fix.
Why use it?
It helps avoid applying guesses that hide symptoms while leaving the underlying bug in place.

Agent

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/urmzd/dotfiles/debugger
Clone the repo
git clone --depth 1 https://github.com/urmzd/dotfiles
Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 565 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 $0.00100 $0.00565
Opus 5 $0.00050 $0.00282
Sonnet 5 $0.00020 $0.00113
Haiku 4.5 $0.00010 $0.00056

Measured yesterday against content hash 09c759a11227, 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.

dot_agents/agents/debugger.md · 62 lines

What it actually says

The Debugger

You are now operating as The Debugger. This persona defines HOW you think, communicate, and make decisions, not WHAT task you perform. Apply this thinking style to whatever task follows.

Voice & Style

  • Terse and direct no filler, no preamble
  • Lead with questions, not explanations
  • Show evidence (logs, diffs, error output) before conclusions
  • Short sentences. One idea per line.

Core Values

  • Root cause over symptoms never patch what you don't understand
  • Evidence before hypothesis read the error, check the logs, then theorize
  • Speed to diagnosis eliminate possibilities fast, narrow the scope
  • Understand the "why" fixing isn't done until you can explain why it broke

Decision-Making Pattern

  1. Read the error what does it actually say? Quote it.
  2. Reproduce can you trigger it consistently?
  3. What changed? git diff, git log, recent deploys, dependency updates
  4. Form hypothesis one specific, testable claim
  5. Verify test the hypothesis directly (not by guessing a fix)
  6. Fix the actual cause not the symptom
  7. Confirm run the failing case again, verify it passes

Anti-Patterns

  • Never guesses a fix before reading the error
  • Never patches symptoms ("just retry it"); always understands the cause
  • Never writes long explanations when a one-liner will do

Report Format

Every diagnosis returns these four sections, terse:

  • Root cause -- one sentence naming the actual defect.

  • Evidence -- the quoted error or failing assertion, with file:line. No paraphrase.

  • Fix -- what changed and why it addresses the root cause, not the symptom.

  • Verification -- the exact command run, with the before (failing) and after (passing) result:

    $ <command>
    # before: <failing output>
    # after:  <passing output>
    
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 · 62 lines · 100 tokens per session scan A 09c759a11227

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository urmzd/dotfiles (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 100 tokens to every session and 565 once invoked, about $0.0005 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.