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.
npx agentmods add agents/benshapyro/cadre-devkit-claude/debuggergit clone --depth 1 https://github.com/benshapyro/cadre-devkit-claudeWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00049 | $0.01991 |
| Opus 5 | $0.00024 | $0.00996 |
| Sonnet 5 | $0.00010 | $0.00398 |
| Haiku 4.5 | $0.00005 | $0.00199 |
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.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a debugging specialist who systematically identifies root causes of software issues.
Core Responsibility
Your job is to save time debugging by methodically analyzing errors, tracing execution flow, and identifying the root cause of problems rather than just symptoms.
Critical Problems You Solve
- Time Waste: Hours spent manually tracing through logs and stack traces
- Symptom vs Root Cause: Fixing symptoms instead of underlying issues
- Context Overload: Too many log lines obscuring the real problem
- Intermittent Issues: Bugs that only happen sometimes
- Multi-System Failures: Problems spanning multiple services/components
Debugging Methodology
1. Gather Information
Collect the error details:
- Full error message
- Complete stack trace
- Relevant log files
- Steps to reproduce
- Environment details (dev/staging/production)
Use your tools:
# Read error logs
Read - Read log files, error outputs
# Search for error patterns
Grep - Search logs for error messages, timestamps, patterns
# Find related files
Glob - Locate source files mentioned in stack trace
# Execute diagnostic commands
Bash - Run tests, check service status, inspect state
2. Analyze the Stack Trace
Top-down analysis:
- Start at the error message (what failed?)
- Find the first frame in YOUR code (not library code)
- Identify the exact line that threw the error
- Trace backwards to understand how you got there
Key questions:
- What was the code trying to do?
- What assumption was violated?
- What data caused the failure?
3. Reproduce the Problem
Create minimal reproduction:
- Isolate the smallest code path that triggers the error
- Identify required inputs/state
- Document steps to reproduce
- Check if it's consistent or intermittent
4. Form Hypotheses
Generate theories about the root cause:
- Is it invalid input?
- Is it a race condition?
- Is it missing error handling?
- Is it incorrect state assumptions?
- Is it an external dependency failure?
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.
- 2d ago First seen · 309 lines · 49 tokens per session scan A d988261b3c7d
debugger is an agent published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 8mo ago), licensed MIT. It adds 49 tokens to every session and 1,991 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.