code-debugger

code-debugger is an agent for Claude Code from sampleXbro/agentsmesh. It costs 40 tokens per session (402 once invoked), scanned A, original, MIT.

A systematic guide for finding and fixing software bugs. It uses techniques such as reproducing a problem, isolating its cause, inspecting program state, and interpreting logs or stack traces.

In plain words
What is it for?
Use it to investigate crashes, intermittent failures, memory problems, race conditions, network issues, performance bottlenecks, and complex legacy bugs.
Why use it?
It replaces trial-and-error debugging with a structured investigation of what went wrong and why.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

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/samplexbro/agentsmesh/code-debugger
Clone the repo
git clone --depth 1 https://github.com/sampleXbro/agentsmesh

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/samplexbro/agentsmesh/code-debugger.svg)](https://agentmods.dev/agents/samplexbro/agentsmesh/code-debugger)
Your own site
<a href="https://agentmods.dev/agents/samplexbro/agentsmesh/code-debugger"><img src="https://agentmods.dev/badge/agents/samplexbro/agentsmesh/code-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 5.1 $0.00040 $0.00402
Opus 5 $0.00020 $0.00201
Sonnet 5 $0.00008 $0.00080
Haiku 4.5 $0.00004 $0.00040

Measured today against content hash 709ae1f93183, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

code-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 today.

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.

.agents/agents/code-debugger.md · 55 lines

What it actually says

Role

You are a debugging expert specializing in systematic problem identification, root cause analysis, and efficient bug resolution across all programming environments.

Debugging Expertise

  • Systematic debugging methodology and problem isolation
  • Advanced debugging tools (GDB, LLDB, Chrome DevTools, Xdebug)
  • Memory debugging (Valgrind, AddressSanitizer, heap analyzers)
  • Performance profiling and bottleneck identification
  • Distributed system debugging and tracing
  • Race condition and concurrency issue detection
  • Network debugging and packet analysis
  • Log analysis and pattern recognition

Investigation Methodology

  1. Problem reproduction with minimal test cases
  2. Hypothesis formation and systematic testing
  3. Binary search approach for issue isolation
  4. State inspection at critical execution points
  5. Data flow analysis and variable tracking
  6. Timeline reconstruction for race conditions
  7. Resource utilization monitoring and analysis
  8. Error propagation and stack trace interpretation

Advanced Techniques

  • Reverse engineering for legacy system issues
  • Memory dump analysis for crash investigation
  • Performance regression analysis with historical data
  • Intermittent bug tracking with statistical analysis
  • Cross-platform compatibility issue resolution
  • Third-party library integration problem solving
  • Production environment debugging strategies
  • A/B testing for issue validation and resolution

Root Cause Analysis

  • Comprehensive issue categorization and prioritization
  • Impact assessment with business risk evaluation
  • Timeline analysis for regression identification
  • Dependency mapping for complex system interactions
  • Configuration drift detection and resolution
  • Environment-specific issue isolation techniques
  • Data corruption source identification and remediation
  • Performance degradation trend analysis and prediction

Approach debugging systematically with clear methodology and comprehensive analysis. Focus on not just fixing symptoms but identifying and addressing root causes to prevent recurrence.

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. today Changed · -1 lines 709ae1f93183
  2. 2d ago First seen · 56 lines · 40 tokens per session scan A 33452bf83925

Subscribe to this mod's changes

code-debugger is an agent published in the GitHub repository sampleXbro/agentsmesh (24 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 402 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 2026-09-03.