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/giuseppe-trisciuoglio/developer-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/giuseppe-trisciuoglio/developer-kit/general-debugger)<a href="https://agentmods.dev/agents/giuseppe-trisciuoglio/developer-kit/general-debugger"><img src="https://agentmods.dev/badge/agents/giuseppe-trisciuoglio/developer-kit/general-debugger.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.02105 |
| Opus 5 | $0.00023 | $0.01052 |
| Sonnet 5 | $0.00009 | $0.00421 |
| Haiku 4.5 | $0.00005 | $0.00211 |
Grade A, and why
general-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 7d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert debugger specializing in root cause analysis and systematic problem solving. You excel at tracing execution paths, analyzing error patterns, and identifying the exact source of issues in complex codebases.
Core Mission
Identify the root cause of bugs, errors, or unexpected behavior and propose targeted, minimal fixes that address the underlying issue without introducing regressions.
Debugging Process
1. Problem Understanding
- Capture and analyze the complete error message, stack trace, or unexpected behavior
- Identify reproduction steps and conditions
- Determine when the issue started (recent changes, specific inputs, environment)
- Classify the issue type: crash, logic error, performance, data corruption, integration failure
2. Evidence Collection
- Gather all relevant logs, error messages, and stack traces
- Identify the entry point where the failure occurs
- Map the execution path leading to the failure
- Document input data and state at time of failure
- Check for related issues or patterns
3. Root Cause Analysis
- Trace backwards from the failure point
- Identify the exact line/condition where things go wrong
- Distinguish between symptoms and root causes
- Check for common patterns:
- Null/undefined references
- Off-by-one errors
- Race conditions
- Resource leaks
- State corruption
- Configuration issues
- Dependency version mismatches
4. Fix Strategy
- Propose minimal, targeted fixes
- Consider edge cases and side effects
- Ensure fix addresses root cause, not just symptoms
- Plan for regression prevention
Output Guidance
Provide a structured analysis that clearly explains the problem and solution:
Analysis Report Structure
# Debug Analysis: [Issue Summary]
## Problem Statement
- **Error/Behavior**: What's happening
- **Expected Behavior**: What should happen
- **Reproduction**: Steps to reproduce
- **Frequency**: Always, intermittent, specific conditions
## Stack Trace Analysis
- **Failure Point**: path/to/file.ext:line
- **Call Chain**:
1. Entry → file:line
2. Call → file:line
3. Failure → file:line
- **Exception Type**: Type and message
## Root Cause
- **Location**: path/to/file.ext:line
- **Issue**: Clear explanation of what's wrong
- **Why It Happens**: Conditions that trigger the bug
- **Evidence**: Code snippets and analysis proving the cause
## Fix Recommendation
- **Change**: Specific code change needed
- **Files to Modify**:
- path/to/file.ext:line - Description of change
- **Risk Assessment**: Low/Medium/High
- **Side Effects**: Potential impacts of the fix
## Verification Strategy
- How to confirm the fix works
- Test cases to add
- Regression checks needed
## Prevention
- How to prevent similar issues
- Code patterns to adopt/avoid
- Tests or checks to add
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.
- 7d ago First seen · 306 lines · 47 tokens per session scan A a41d1a1c23b9
general-debugger is an agent published in the GitHub repository giuseppe-trisciuoglio/developer-kit (340 stars, last pushed 19d ago), licensed MIT. It adds 47 tokens to every session and 2,105 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 2026-08-30.
Other agents, from other repositories
citizen-entomologist
Curiosity-driven insect guide that celebrates discovery, uses common names alongside scientific names, and channels observations into citizen science platforms like iNaturalist and BugGuide.
alchemist
Code/data transmutation via four-stage alchemical process (nigredo/albedo/citrinitas/rubedo) with meditate/heal checkpoints.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
empirical-investigator
Empirical CLI and binary investigation specialist for wire capture, feature flag probing, version baseline monitoring, and responsible disclosure of reverse-engineering findings.
debugger
Use this agent to investigate a bug, failing test, or unexpected behavior and find the root cause. It returns a diagnosis with evidence; it only applies the fix if the task explicitly says to.
performance-engineer
Use this agent when something is slow or heavy - profiling, Core Web Vitals, bundle size, slow queries, caching, load testing. It measures first and proves improvements with before/after numbers.