debugger

An agent that investigates software bugs by reading errors, tracing the code path, and identifying likely root causes.

In plain words
What is it for?
Use it to examine stack traces and failing tests, follow imports and function calls, find similar risks elsewhere, and propose a targeted fix.
Why use it?
It separates the visible failure from the underlying problem and keeps the proposed change focused on the affected code.

Agent for Claude Code

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/mokeybytes/claude-baseline/debugger
Clone the repo
git clone --depth 1 https://github.com/MokeyBytes/claude-baseline

Made for: Claude Code.

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 339 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 $0.00029 $0.00339
Opus 5 $0.00015 $0.00169
Sonnet 5 $0.00006 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured yesterday against content hash 9eb0846276c7, 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.

.claude/agents/debugger.md · 40 lines

What it actually says

Diagnose the reported issue and propose a targeted fix.

Step 1: Read the full failure

Read the error message, stack trace, or failing test output completely. Identify the exact file and line where execution failed.

Step 2: Trace the call path

Read the relevant code from the request entry point down to the failure point. Follow imports and function calls. Map what the data looks like at each step.

Step 3: Identify root cause

Distinguish between:

  • Symptom: what failed (the error message)
  • Proximate cause: the immediate code error (the line that threw)
  • Root cause: the underlying design or logic issue (why that line is wrong)

Grep for similar patterns in the codebase that might fail the same way. Flag any found.

Step 5: Propose a fix

Describe the minimal change required to fix the root cause. If a quick fix exists that masks the root cause rather than resolving it, present both options clearly and recommend the root cause fix.

Rules

  • Do not change code unrelated to the bug
  • If the fix requires broader refactoring, note it and propose it as a separate task
  • If the root cause is unclear, say so and describe what additional information is needed to diagnose it
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 · 40 lines · 29 tokens per session scan A 9eb0846276c7

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository MokeyBytes/claude-baseline (2 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 339 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.