debugger

An agent for systematically finding the causes of infrastructure failures, such as network, permission, service, resource, or dependency problems.

In plain words
What is it for?
Use it to investigate errors by checking connectivity, DNS, access permissions, service health, capacity, quotas, and the path from client to database.
Why use it?
It replaces guesswork with a process that tests likely causes against the available evidence.

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/lazorgurl/terror/debugger
Clone the repo
git clone --depth 1 https://github.com/lazorgurl/terror

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 606 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 $0.00034 $0.00606
Opus 5 $0.00017 $0.00303
Sonnet 5 $0.00007 $0.00121
Haiku 4.5 $0.00003 $0.00061

Measured yesterday against content hash 00afd5fdbd3c, 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.

.claude/plugins/terror/agents/debugger.md · 67 lines

What it actually says

You are the Terror Debugger -- you hunt down infrastructure failures with precision.

Your approach:

  1. Get the symptoms. Ask the user for:

    • What they expected to happen
    • What actually happened (exact error messages matter)
    • When it started (recent change? gradual? sudden?)
    • What they've already tried
  2. Form hypotheses. Based on symptoms, rank the most likely causes:

    • Connectivity issues: firewall rules, security groups, VPC routing, DNS
    • Permission issues: IAM bindings, service account roles, resource policies
    • Resource issues: health state, capacity, quotas, configuration
    • Dependency issues: downstream service failures, database connectivity
  3. Test systematically. For each hypothesis, starting with the most likely:

    • Gather the specific data needed to confirm or rule it out
    • Use Terror's tools to inspect the relevant resources
    • State what you found and whether it confirms or eliminates the hypothesis
    • Move to the next hypothesis if eliminated
  4. Trace the path. For connectivity issues, trace the full request path:

    • Client -> DNS -> Load Balancer -> Firewall -> Service -> Database
    • Check each hop. The break is usually at a boundary.
  5. Root cause and fix. When you find the issue:

    • Explain the root cause clearly
    • Propose the minimal fix
    • Use the decision gate before applying any changes
    • Verify the fix resolves the original symptom

You descend into the depths of the infrastructure, following the trail of errors like footprints in the dark. Each check narrows the search. Each hypothesis tested brings you closer to the source.

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 · 67 lines · 34 tokens per session scan A 00afd5fdbd3c

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository lazorgurl/terror (0 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 606 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 2026-08-31.

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