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.
npx agentmods add instructions/frouaix/mcpapplescript/copilot-instructionsgit clone --depth 1 https://github.com/frouaix/MCPAppleScriptWhat 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 | $0.01108 | $0.01108 |
| Opus 5 | $0.00554 | $0.00554 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
MCPAppleScript copilot-instructions.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
The executor uses `child_process.execFile('osascript', ['-e', script])` — no shell involved. Error classification maps osascript stderr patterns to error codes: How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP-AppleScript — Copilot Instructions
Build & Test Commands
pnpm install # Install all dependencies
pnpm build # Build TypeScript
pnpm test:unit # ~150 TypeScript unit tests
pnpm test:integration # Integration tests (requires macOS + TCC permissions)
pnpm lint # ESLint
pnpm format # Prettier
# Single test file
cd packages/mcp-server && npx tsx --test test/unit/policy.test.ts
# Standalone binary
pnpm build:sea # Node.js SEA binary
pnpm build:dmg # Package as .dmg
Architecture
Single-process TypeScript architecture using osascript for AppleScript execution:
MCP Client → TypeScript MCP Server → osascript → macOS Apps (via Apple Events)
(protocol, policy, (CLI tool)
adapters, templates)
Transports: stdio (default) or Streamable HTTP (--http flag).
Data flow for a tool call: MCP request → Zod validation → policy check → mode gate → ResourceAdapter maps to {templateId, parameters} → TypeScript template builder generates AppleScript → executed via osascript → JSON result returned.
ResourceAdapter Pattern
The core abstraction. Each of the 10 Apple apps has a TypeScript adapter (packages/mcp-server/src/adapters/) and a TypeScript template module (packages/mcp-server/src/templates/{app}.ts).
The adapter maps generic CRUD operations (list, get, search, create, update, delete, action) to {templateId, parameters} pairs. The template dispatcher routes by template ID prefix (e.g. notes.create_note → notes.build()).
Apps that don't support an operation throw UnsupportedOperationError.
Three Operation Modes
Modes are cumulative and configurable via config.modes. Tool-to-mode mapping can be overridden to promote/restrict tools.
- readonly (default):
ping,get_mode,set_mode,app.list_containers,app.list,app.get,app.search - create: +
app.create,app.action,applescript.run_template - full: +
app.update,app.delete,applescript.run_script(all require user confirmation via MCP elicitation or confirmation token)
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.
- yesterday First seen · 93 lines · 1,108 tokens per session scan A 4fb8e9f0d364
MCPAppleScript copilot-instructions.md is an instructions file published in the GitHub repository frouaix/MCPAppleScript (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,108 tokens to every session, about $0.0055 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit 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.
langchain 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.