What is iac-mcp CLAUDE.md?

Repository instructions for Claude Code in an open-source project that connects AI assistants with installed desktop applications. The project uses a system called Just-In-Time Discovery to find and control available apps when needed.

Use them when installing dependencies, building the TypeScript project, running tests, developing with file watching, or starting the MCP server.

They give Claude Code the project context, development commands, and design direction needed to make consistent changes.

How jsavin/iac-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jsavin/iac-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/jsavin/iac-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jsavin/iac-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/instructions/jsavin/iac-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/jsavin/iac-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jsavin/iac-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jsavin/iac-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jsavin/iac-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jsavin/iac-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,300 This file is loaded in full into every session.

When invoked 7,300 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.

Model	Per session	Once invoked
Fable 5.1	$0.07300	$0.07300
Opus 5.5	$0.02920	$0.02920
Sonnet 5.5	$0.01460	$0.01460
Haiku 4.5	$0.00730	$0.00730

Measured 2mo ago against content hash 47ce53237279, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

iac-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 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.md · 942 lines

How it starts

The opening of the file, as written. The whole thing — 942 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 Vision

Building a universal bridge between AI/LLMs and native applications using Just-In-Time Discovery (JITD) to dynamically discover and orchestrate any installed app without pre-built integrations.

Core philosophy: Interoperability above all. Make everything work with everything else. Local-first, user control, no vendor lock-in.

Strategy: Bootstrap (no VCs), sustainable growth, open source core + proprietary UI.

Platform Strategy:

Phase 1: macOS (AppleScript/JXA, SDEF parsing)
Phase 5+: Multi-platform (Windows VBA/COM, Linux D-Bus, cross-platform)
JITD architecture designed for any platform's native automation

Read the complete vision: planning/VISION.md and planning/ideas/the-complete-vision.md

Quick Reference

Essential Commands

# Development
npm install            # Install dependencies
npm run build          # Compile TypeScript
npm run dev            # Development mode with watch
npm test               # Run tests
npm start              # Start MCP server

# Testing (use queued versions in agents to prevent memory exhaustion)
npm run test:unit           # Unit tests only
npm run test:integration    # Integration tests
npm run test:queued         # ⚠️ AGENTS MUST USE THIS - queued test run
npm run test:queued:unit    # ⚠️ AGENTS MUST USE THIS - queued unit tests
npm run test:queued:coverage # ⚠️ AGENTS MUST USE THIS - queued coverage
npx @modelcontextprotocol/inspector node dist/index.js  # MCP Inspector

# Git workflow
git worktree add ../iac-mcp-<feature> -b feature/<name>  # Create worktree
git push origin feature/<name>  # Push feature branch (NEVER push to origin/main)

Documentation Quick Links

Code Quality Standards - MANDATORY testing and DRY principles
Vision - Complete project vision
Roadmap - 18-month plan with phases
Start Here - New contributor guide
Decisions - All key decisions documented
MVP Plan - Current phase implementation

Read the full file on GitHub · 942 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 · 942 lines · 7,300 tokens per session scan A 47ce53237279

Subscribe to this mod's changes

iac-mcp CLAUDE.md is an instructions file published in the GitHub repository jsavin/iac-mcp (3 stars, last pushed 7mo ago), licensed MIT. It adds 7,300 tokens to every session, about $0.0292 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.

Building agents applescript automation cross-platform dynamic-discovery jxa macos

iac-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
iac-mcp CLAUDE.mdjsavin/iac-mcp	Instructions file	3	7mo ago	MIT	A	7,300	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

iac-mcp: Instructions file for Claude Code