terry-form-mcp: Instructions file for Claude Code

CLAUDE.md

terry-form-mcp CLAUDE.md is an instructions file for Claude Code from aj-geddes/terry-form-mcp. It costs 948 tokens per session, scanned A, original, MIT.

A project instruction file for Terry-Form MCP, a server that lets AI assistants run Terraform inside Docker containers. Terraform is a tool for defining and managing infrastructure with configuration files.

In plain words
What is it for?
Use it when building the Docker image, running the verification checks, starting the server, or running its core module and integration tests.
Why use it?
It gives contributors the project’s setup, build, test, and run instructions in one place. This reduces guesswork when working on or checking the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is aj-geddes/terry-form-mcp's own configuration. It tells Claude Code how to work on terry-form-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything terry-form-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aj-geddes/terry-form-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aj-geddes/terry-form-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/aj-geddes/terry-form-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for terry-form-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aj-geddes/terry-form-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/aj-geddes/terry-form-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aj-geddes/terry-form-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aj-geddes/terry-form-mcp/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.

agentmods 80×15 button for terry-form-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aj-geddes/terry-form-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aj-geddes/terry-form-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 948 This file is loaded in full into every session.
When invoked 948 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00948 $0.00948
Opus 5 $0.00474 $0.00474
Sonnet 5 $0.00190 $0.00190
Haiku 4.5 $0.00095 $0.00095

Measured 10d ago against content hash db142ccd4c06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

terry-form-mcp 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 10d 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.

CLAUDE.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

AI Skill: Load .claude/skills/terry-form-mcp-expert/SKILL.md at the start of each session.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Terry-Form MCP is a production-ready Model Context Protocol (MCP) server that provides AI-powered Terraform execution within Docker containers. It exposes 25 MCP tools for Terraform operations, LSP-based intelligence, GitHub integration, and Terraform Cloud connectivity. Version 3.1.0. Requires Python >= 3.10.

Build & Run Commands

# Build Docker image
scripts/build.sh              # Linux/macOS
scripts\build.bat             # Windows
docker build -t terry-form-mcp .

# Run verification suite (8 checks: Docker, image size, Terraform, terraform-ls, Python, files, tools, startup)
scripts/verify.sh

# Run the server directly (requires dependencies)
pip install -r requirements.txt
python3 src/server_enhanced_with_lsp.py

# Run core module standalone
python3 src/terry-form-mcp.py < tests/fixtures/test.json

# Integration test via Docker
docker run -i --rm -v "$(pwd):/mnt/workspace" terry-form-mcp:latest python3 terry-form-mcp.py < test.json

# Code quality
black .                       # Format (88 char line limit)
flake8 .                      # Lint
mypy src/*.py                 # Type check

Architecture

Entry Point & Server

src/server_enhanced_with_lsp.py is the single entry point — a FastMCP async server that registers all 25 tools via @mcp.tool() decorators. It consolidates what were previously 3 separate server variants.

Module Responsibilities

  • src/terry-form-mcp.py — Core Terraform subprocess execution. Handles init, validate, fmt, plan (never apply/destroy). Manages workspace isolation at /mnt/workspace.
  • src/terraform_lsp_client.py — Async LSP client wrapping terraform-ls. Provides hover info, completions, diagnostics, and formatting. First call may take ~1-2s for LSP initialization.
  • src/mcp_request_validator.py — Input sanitization and security validation. Prevents path traversal, enforces JSON schema, applies rate limiting (20 req/min Terraform, 30 req/min GitHub, 100 req/min default).
  • src/github_repo_handler.py — Clone repos and extract Terraform files from GitHub.
  • src/github_app_auth.py — GitHub App OAuth with JWT/PyJWT authentication.

Read the full file on GitHub · 84 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. 10d ago First seen · 84 lines · 948 tokens per session scan A db142ccd4c06

Subscribe to this mod's changes

terry-form-mcp CLAUDE.md is an instructions file published in the GitHub repository aj-geddes/terry-form-mcp (10 stars, last pushed 5mo ago), licensed MIT. It adds 948 tokens to every session, about $0.0047 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens