Borrowing it
Nothing to install: this file belongs to lazorgurl/terror. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lazorgurl/terror/main/CLAUDE.mdgit clone --depth 1 https://github.com/lazorgurl/terrorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/lazorgurl/terror/claude-md)<a href="https://agentmods.dev/instructions/lazorgurl/terror/claude-md"><img src="https://agentmods.dev/badge/instructions/lazorgurl/terror/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/lazorgurl/terror/claude-md"><img src="https://agentmods.dev/badge/instructions/lazorgurl/terror/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01008 | $0.01008 |
| Opus 5.5 | $0.00403 | $0.00403 |
| Sonnet 5.5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
terror CLAUDE.md 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Terror — Agentic Terraform. An MCP tool for agent-native cloud infrastructure management. Open source under MIT.
Agents provision and manage cloud resources through MCP tools instead of CLI commands or HCL files. Terror is stateless — cloud provider APIs are the source of truth. There are no local or remote state files.
Tech Stack
TypeScript, Node.js, bun monorepo, vitest, eslint + prettier.
Package Structure
| Package | Path | Purpose |
|---|---|---|
@terror/core |
packages/core |
MCP server, provider registry, plan engine (action list + rollback), OAuth broker, shared types |
@terror/gcp |
packages/gcp |
GCP provider (MVP). Full CRUD: Compute Engine, Cloud Storage, VPC/Firewalls, IAM, Cloud Run, Cloud Functions, Cloud SQL, Pub/Sub |
Post-MVP providers: AWS, Cloudflare, DigitalOcean.
Architecture
- Stateless — no state files. Always query cloud APIs for current state.
- Plan-then-apply — build action list, validate state before each action, execute, validate after. Auto mode skips user review.
- Decision Gate — before executing any plan, the agent must evaluate its own decision. Risk is scored from action/resource weights (IAM delete = critical, storage create = low). High-risk plans require justification and alternatives; critical plans escalate to the human.
- Transactional rollback — on validation failure mid-plan, halt and rollback completed actions in reverse order. Every mutation must have a rollback handler.
- Token-efficient responses — list operations return summaries by default (id, name, status, one-line description). Agents request full details per-resource. Supports delta responses (only changes since last query), field filtering, and pagination. Meta-params:
_fields,_page,_pageSize,_delta. - TUI status — real-time MCP notifications (
terror/status) for plan progress, auth status, resource changes, cost estimates, and provider health. Purple-themed ANSI output viaStatusEmitter+TuiFormatter. - Two-layer tools — low-level CRUD per resource type + high-level intent-based composite operations (e.g. "deploy a static site").
- Provider plugin system — each provider is a separate npm package implementing the
Providerinterface from core. Provider packages depend on@terror/coreviaworkspace:*protocol. - OAuth broker — local HTTP server handles OAuth callbacks for unified auth UX across providers.
- MCP stdio transport — runs as a standard MCP server. Entrypoint is
packages/core/dist/bin.js. Must be run withbun(notnode) — dependencies are in Bun's module store.
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.
- 2mo ago First seen · 85 lines · 1,008 tokens per session scan A 4a0fb1768ed2
terror CLAUDE.md is an instructions file published in the GitHub repository lazorgurl/terror (0 stars, last pushed 7mo ago), licensed MIT. It adds 1,008 tokens to every session, about $0.0040 per session on Opus 5.5. 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.
terror CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| terror CLAUDE.mdlazorgurl/terror | Instructions file | 0 | 7mo ago | MIT | A | 1,008 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |