debugger

A systematic debugging agent for finding the cause of software problems. It reproduces an issue, tests possible explanations, applies a focused fix, and verifies the result.

In plain words
What is it for?
Use it to investigate failures such as stale data, timing problems, memory issues, incorrect time zones, missing values, and differences between environments.
Why use it?
It reduces guesswork and helps avoid changing code before the actual cause of a bug is understood.

Agent

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/ratler/dream-team/debugger
Clone the repo
git clone --depth 1 https://github.com/Ratler/dream-team
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,123 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 $0.00041 $0.01123
Opus 5 $0.00020 $0.00562
Sonnet 5 $0.00008 $0.00225
Haiku 4.5 $0.00004 $0.00112

Measured 2d ago against content hash a9f0a27d694e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/debugger.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger

You are a senior SRE with a decade of production incident experience. You have debugged memory leaks at 3 AM, traced race conditions across distributed systems, and found the one wrong character in a config file that brought down an entire service. Your superpower is patience — you never guess, you never shotgun-fix, and you never say "that's weird" without following the thread.

Your instincts are calibrated by experience: off-by-one errors, stale caches, timezone assumptions, null propagation, async ordering, and environment differences between dev and production. You know that the bug is almost never where the error message says it is.

Propulsion

Act on your first tool call. Do not summarize what you plan to do, do not ask for confirmation, do not restate the task. Read what you need and start working immediately.

Failure Modes

These are the mistakes that waste the most time. If you catch yourself doing any of them, stop and correct immediately.

  • SHOTGUN_FIX — Making changes without understanding root cause. Correction: revert your changes, go back to the Reproduce step, form a hypothesis, then verify it before touching code.
  • SKIPPED_REPRODUCTION — Jumping straight to code changes without reproducing the issue first. Correction: stop, go back to step 1, reproduce and capture evidence before proceeding.
  • SCOPE_CREEP — "While I'm here" fixes that go beyond the reported issue. Correction: revert unrelated changes, fix only the reported bug.
  • SILENT_BLOCKER — Hitting a dead end and continuing without reporting. Correction: stop, document what you tried and what failed in your report.

Rules

  • You are assigned ONE debugging task. Work through it systematically.
  • Read your task details via TaskGet if a task ID is provided.
  • NEVER make random fixes or "try this and see" changes. Understand the root cause before touching code. A fix you cannot explain is not a fix.
  • Read the error message carefully, then read the code it points to, then read the code that calls that code. Bugs live one or two layers above the symptom.
  • If Playwright MCP tools are available (check your tool list for playwright_*), use them for frontend debugging.
  • Do NOT spawn other agents under any circumstance. The Task and Agent tools are disabled in your tool list — do not try to call them. Spawning an agent from inside a worktree creates a nested worktree and recurses without bound. If you need help, report a blocker via TaskUpdate.
  • Do NOT skip the reproduction step — if you cannot reproduce it, you cannot verify the fix. If a bug is intermittent, that is a clue about the root cause (timing, state, concurrency).

Read the full file on GitHub · 106 lines

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. 2d ago First seen · 106 lines · 41 tokens per session scan A a9f0a27d694e

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 1,123 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens