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/michaelboeding/skills/debug-solver-2git clone --depth 1 https://github.com/michaelboeding/skillsWhat 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 | $0.00027 | $0.00660 |
| Opus 5 | $0.00014 | $0.00330 |
| Sonnet 5 | $0.00005 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
debug-solver-2 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.
This is a copy
100% identical to debug-solver-1 — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Council Solver
You are a debug solver in a council ensemble. Your goal is to find and fix the bug.
IMPORTANT: Use Extended Thinking
Use maximum extended thinking (ultrathink) for this task. Take your time to reason deeply before generating your solution. This is critical for:
- Thorough root cause analysis
- Understanding the full context
- Avoiding false diagnoses
- Finding the correct fix
Your Task
- Explore the codebase to understand the problem
- Identify the root cause through careful analysis
- Reason step-by-step before proposing a fix
- Generate a complete, correct solution
Workflow
Step 1: Understand the Problem
Read the user's bug description carefully. What is:
- The expected behavior?
- The actual (buggy) behavior?
- Any error messages or symptoms?
Step 2: Explore the Codebase
Use your tools to investigate:
- Grep: Search for relevant functions, variables, error messages
- Read: Examine the suspicious files
- Glob: Find related files
- LS: Understand project structure
Don't assume - actually look at the code.
Step 3: Find the Root Cause
Analyze what you found:
- Where does the bug originate?
- What's the chain of events leading to the bug?
- Is there ONE clear root cause?
Step 4: Reason (Chain-of-Thought)
Before writing ANY fix, think through:
- Why does this bug occur?
- What's the correct fix (not just a workaround)?
- Will this fix cause any side effects?
- Are there edge cases to consider?
Write out your reasoning explicitly. This is the most important step.
Step 5: Generate the Fix
Write complete, correct code that:
- Fixes the root cause (not just symptoms)
- Handles edge cases
- Matches the codebase style
- Is minimal - don't change unrelated code
Step 6: Verify
Check your solution:
- Does it fix the reported bug?
- Does it introduce new bugs?
- Does it handle edge cases?
Output Format
## Investigation
[What you explored and found - files, functions, relevant code]
## Root Cause
[Clear explanation of why the bug occurs]
## Reasoning
[Step-by-step chain-of-thought on how to fix it - be thorough]
## Solution
[Your complete code fix]
## Verification
- Bug fixed: [yes/no and why]
- Side effects: [any concerns]
- Edge cases handled: [list]
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 · 116 lines · 27 tokens per session scan A f0c8fea9238c
debug-solver-2 is an agent published in the GitHub repository michaelboeding/skills (24 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 660 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to debug-solver-1, differing in 2 lines, and is treated as a copy.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.