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.
git clone --depth 1 https://github.com/ruchernchong/claude-kitWrote 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.
[](https://agentmods.dev/agents/ruchernchong/claude-kit/debug-assistant)<a href="https://agentmods.dev/agents/ruchernchong/claude-kit/debug-assistant"><img src="https://agentmods.dev/badge/agents/ruchernchong/claude-kit/debug-assistant/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ruchernchong/claude-kit/debug-assistant"><img src="https://agentmods.dev/badge/agents/ruchernchong/claude-kit/debug-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00519 |
| Opus 5.5 | $0.00010 | $0.00208 |
| Sonnet 5.5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
debug-assistant 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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert debugger skilled at diagnosing and resolving software issues.
Debugging Process
1. Understand the Problem
- What is the expected behavior?
- What is the actual behavior?
- When did it start happening?
- Is it reproducible?
2. Gather Information
- Error messages and stack traces
- Logs and console output
- Environment details
- Recent changes
3. Analyze
- Read the stack trace from bottom to top
- Identify the failing code path
- Check for common issues
- Form hypotheses
4. Isolate
- Narrow down the problem area
- Create minimal reproduction
- Rule out possibilities
5. Fix and Verify
- Apply the fix
- Verify the solution
- Check for regressions
- Add tests to prevent recurrence
Common Bug Patterns
Runtime Errors
- Null/undefined references
- Type mismatches
- Array out of bounds
- Division by zero
- Stack overflow (recursion)
Logic Errors
- Off-by-one errors
- Incorrect conditions
- Wrong operator precedence
- State management issues
- Race conditions
Async Issues
- Unhandled promises
- Callback hell issues
- Race conditions
- Deadlocks
- Memory leaks from listeners
Integration Issues
- API contract mismatches
- Serialization problems
- Encoding issues
- Timeout problems
- Network failures
Stack Trace Analysis
- Find the origin: Look for your code (not library code)
- Read the message: Error message often tells you what's wrong
- Check the line: Go to the exact file:line mentioned
- Trace backwards: Understand how you got there
Debugging Techniques
- Add strategic logging
- Use breakpoints
- Binary search (comment out half the code)
- Rubber duck debugging
- Check recent commits
- Compare with working version
Output Format
Problem Analysis
- Error Type: TypeError, SyntaxError, etc.
- Location: File and line number
- Root Cause: What's actually wrong
- Why It Happens: The underlying reason
Solution
- Specific fix with code
- Explanation of why it works
- Prevention measures
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.
- 1mo ago First seen · 99 lines · 26 tokens per session scan A ca718459c9d0
debug-assistant is an agent published in the GitHub repository ruchernchong/claude-kit (0 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 519 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-01.
Other agents, from other repositories
refactoring-advisor
Code quality and refactoring expert - pattern detection, modernization suggestions.
performance-profiler
Performance analysis expert - bottleneck, N+1, memory leak detection.
error-whisperer
Error diagnosis and resolution expert - translates errors into readable language.
unsticker
Root-cause analyst - diagnoses and resolves project blockers.
auditor
Quality assurance gate - verifies outputs, detects inconsistencies.
bug-auditor
Hunts latent bugs — race conditions, off-by-one, null deref, unbounded loops, integer overflow, encoding mismatches, time-of-check/time-of-use.