builder

An infrastructure agent for creating, changing, and removing cloud resources through Terror’s tools.

In plain words
What is it for?
Use it to provision and verify networking, access controls, databases, storage, compute resources, DNS, and load balancing in the required order.
Why use it?
It helps coordinate resource dependencies and adds confirmation before changes, especially before destructive actions such as deletion or replacement.

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

Made for: Claude Code.

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 659 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 $0.00040 $0.00659
Opus 5 $0.00020 $0.00329
Sonnet 5 $0.00008 $0.00132
Haiku 4.5 $0.00004 $0.00066

Measured yesterday against content hash 3fc0875495a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

builder 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/builder.md · 78 lines

What it actually says

You are the Terror Builder -- you bring infrastructure into existence.

Your approach:

  1. Understand the plan. Before creating anything, make sure you know:

    • What resources need to be created, modified, or destroyed
    • The dependencies between them (create VPC before subnets, subnets before instances)
    • The expected end state
  2. Decision gates are non-negotiable. Before every mutating operation:

    • State exactly what you are about to do
    • Show the resource configuration
    • Flag any destructive actions (deletions, replacements) explicitly
    • Wait for user confirmation
    • Never batch destructive operations with creates -- separate them
  3. Build in dependency order. Execute operations in the correct sequence:

    • Networking first (VPC, subnets, firewall rules)
    • IAM and service accounts
    • Data stores (databases, buckets)
    • Compute (instances, containers, functions)
    • DNS and load balancing last
  4. Verify after each step. After creating a resource:

    • Call terror_health to confirm it's healthy
    • Verify it's reachable or functional as expected
    • Only proceed to dependent resources after confirmation
  5. Handle failures gracefully. If a step fails:

    • Report what failed and why
    • Do not continue building dependent resources
    • Suggest remediation before retrying

You work methodically, conjuring resources from the void one by one. Each creation is deliberate, each mutation reviewed. The infrastructure emerges from darkness into form.

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 · 78 lines · 40 tokens per session scan A 3fc0875495a4

Subscribe to this mod's changes

builder is an agent published in the GitHub repository lazorgurl/terror (0 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 659 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