What is terry-form-mcp-expert?

A project-specific reference skill for Terry-Form MCP, an MCP server that provides tools and information to AI assistants. It tells the assistant to load the project's instructions and inspect its recent repository state at the start of a session.

It is for starting work on the Terry-Form MCP project, checking its current Git state, and reviewing relevant project warnings. Git is the version-control system used to track the project's files and changes.

It gives the assistant the project's required background and operating rules before work begins. This can reduce mistakes caused by missing project context or overlooked known issues.

How aj-geddes/terry-form-mcp configures Claude Code

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/skills/terry-form-mcp-expert/SKILL.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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aj-geddes/terry-form-mcp/terry-form-mcp-expert/github.svg)](https://agentmods.dev/skills/aj-geddes/terry-form-mcp/terry-form-mcp-expert)

Your own site

<a href="https://agentmods.dev/skills/aj-geddes/terry-form-mcp/terry-form-mcp-expert"><img src="https://agentmods.dev/badge/skills/aj-geddes/terry-form-mcp/terry-form-mcp-expert/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aj-geddes/terry-form-mcp/terry-form-mcp-expert"><img src="https://agentmods.dev/badge/skills/aj-geddes/terry-form-mcp/terry-form-mcp-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,180 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.05180
Opus 5.5	$0.00000	$0.02072
Sonnet 5.5	$0.00000	$0.01036
Haiku 4.5	$0.00000	$0.00518

Measured 2mo ago against content hash 6bd4ef920210, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

terry-form-mcp-expert 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.

.claude/skills/terry-form-mcp-expert/SKILL.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

terry-form-mcp-expert Skill

Skill Metadata

Version: 1.0.0
Last Updated: 2026-03-04
Project: Terry-Form MCP
Skill Path: .claude/skills/terry-form-mcp-expert/SKILL.md

Purpose & Invocation

This skill makes the AI assistant an expert in everything about the Terry-Form MCP project. It should be loaded at the start of every session by referencing this file.

Trigger phrases (any of these should cause the AI to load this skill):

"start a session on terry-form-mcp"
"load project context"
"you are the terry-form-mcp expert"
"what do you know about this project"

Session Start Protocol

When this skill is invoked, the AI assistant MUST:

Read this file completely before responding to any task
State which version of the skill was loaded and the last-updated date
Summarize the project in 2-3 sentences to confirm context is loaded
Ask the developer what they are working on today
Check git status and git log --oneline -10 to understand current state
Flag any known issues from the Gotchas section relevant to today's work

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 (init, validate, fmt, plan), LSP-based code intelligence via terraform-ls, GitHub App integration, and Terraform Cloud connectivity. The server communicates via MCP stdio transport — there is no HTTP server, no web dashboard, and no exposed ports.

The project serves infrastructure teams that want to safely automate Terraform workflows through AI assistants like Claude Desktop. Security is the core design principle: destructive operations (apply, destroy) are permanently blocked, all file access is isolated to /mnt/workspace, inputs are sanitized against injection, and the container runs as a non-root user (UID 1001). Version 3.1.0 requires Python >= 3.10.

The documentation site at https://aj-geddes.github.io/terry-form-mcp is a Jekyll-based GitHub Pages site with a dark-first glassmorphism design, covering 10 guides, 6 tutorials, API reference for all 25 tools, and architecture documentation.

Read the full file on GitHub · 386 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.

2mo ago First seen · 386 lines · 0 tokens per session scan A 6bd4ef920210

Subscribe to this mod's changes

terry-form-mcp-expert is a skill published in the GitHub repository aj-geddes/terry-form-mcp (10 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,180 tokens. 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.

terry-form-mcp-expert next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
terry-form-mcp-expertaj-geddes/terry-form-mcp	Skill	10	7mo ago	MIT	A	0	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

terry-form-mcp: Skill for Claude Code