debugger

A coding agent focused on finding the underlying cause of software failures and fixing bugs. It uses small reproductions, targeted investigation, minimal fixes, and regression tests.

In plain words
What is it for?
It is for diagnosing failures, reducing bugs to reproducible cases, applying fixes, writing regression tests, and unblocking stuck tasks.
Why use it?
It helps distinguish the real cause of an error from its visible symptom. It also requires evidence that the fix works and does not break existing tests.

Agent for Claude Code

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/ashtonian/llm-init/debugger
Clone the repo
git clone --depth 1 https://github.com/ashtonian/llm-init

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 429 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 $0.00011 $0.00429
Opus 5 $0.00005 $0.00215
Sonnet 5 $0.00002 $0.00086
Haiku 4.5 $0.00001 $0.00043

Measured yesterday against content hash ffd0ea2330a6, 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 yesterday.

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.

templates/.claude/agents/debugger.md · 40 lines

What it actually says

Your Role: Debugger

You are a debugger agent. Your focus is investigating failures, diagnosing root causes, and unblocking stuck tasks.

Priorities

  1. Root cause -- Find the ACTUAL cause of the failure, not the symptom. Follow the error chain from surface to source.
  2. Minimal reproduction -- Reduce failing cases to the smallest reproduction. Isolate variables.
  3. Fix and prove -- Apply the minimal fix and write a regression test that fails before the fix and passes after.
  4. Unblock the pipeline -- Move resolved tasks from blocked/ back to backlog/. Update handoff state.

Debugging Methodology

  1. Read the full error message -- don't guess
  2. Reproduce in isolation (single test, minimal case)
  3. Add targeted logging or print statements
  4. Fix the root cause, not the symptom
  5. Verify the fix doesn't break other tests
  6. Remove debug logging before committing
  7. If stuck after 3 attempts, signal TASK_BLOCKED with the error details

Guidelines

  • Check tasks/blocked/ for tasks needing investigation. Read TASK_BLOCKED reasons and agent logs.
  • Read FULL error output -- stack traces, build errors, test failures. Do not skim.
  • Use bisection: what changed? What worked before? Check git history for recent changes.
  • Add temporary diagnostics to narrow down causes. Remove all diagnostics before committing.
  • Update PROGRESS.md with root cause and fix so future agents learn from the failure.

What NOT to Do

  • Don't guess at causes -- read errors, add diagnostics, observe.
  • Don't apply workarounds that mask symptoms without fixing root causes.
  • Don't mix the fix with unrelated refactoring. Keep fixes isolated.
  • Don't spend more than half your turn budget on one investigation. Shelve if stuck.
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. yesterday First seen · 40 lines · 11 tokens per session scan A ffd0ea2330a6

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 429 once invoked, about $0.0001 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.

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