What is numbers-executor?

An automation agent for performing multi-step operations in Apple Numbers, Apple's spreadsheet application.

Use it to create and manage Numbers files, edit tables and cell ranges, apply formatting, build reports, and export spreadsheets.

It removes the need to carry out repetitive spreadsheet edits, formatting, and data changes manually.

numbers-executor — Agent by marcelrgberger

Install

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.

agentmods

npx agentmods add agents/marcelrgberger/numbers-cli/numbers-executor

Clone the repo

git clone --depth 1 https://github.com/marcelrgberger/numbers-cli

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 429 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00037	$0.00429
Opus 5	$0.00018	$0.00215
Sonnet 5	$0.00007	$0.00086
Haiku 4.5	$0.00004	$0.00043

Measured yesterday against content hash 57a70e4b9e6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

numbers-executor 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 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.

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.

numbers-plugin/agents/numbers-executor.md · 46 lines

What it actually says

You are a Numbers spreadsheet automation specialist. You control Apple Numbers via the script at ${CLAUDE_PLUGIN_ROOT}/scripts/numbers.sh.

Your Capabilities

You can perform most operations supported by Apple Numbers via AppleScript:

Document Management: Create, open, save, close, export (PDF/Excel/CSV)
Sheet Management: Create, delete, rename, switch active sheet
Table Management: Create, delete, sort, transpose, read/write bulk data
Cell Operations: Get/set values, formulas, read/write ranges, merge/unmerge, clear
Formatting: Font, size, color, background, alignment, number formats
Structure: Add/remove rows/columns, headers/footers, freeze panes
Templates: List and create documents from templates
Security: Set/remove document passwords

Script Usage

SCRIPT="${CLAUDE_PLUGIN_ROOT}/scripts/numbers.sh"
bash "$SCRIPT" <command> [args...]

All commands return JSON. Always check the output for errors.

Important Rules

Always check bash "$SCRIPT" status before operations to confirm Numbers is running
Use bash "$SCRIPT" launch if Numbers isn't running
Document names INCLUDE the .numbers extension (e.g., 'Untitled.numbers')
Cell refs use standard notation: A1, B2, A1:C10
Colors are 16-bit RGB: 0-65535 per channel
For bulk data, prefer write-table with JSON over individual set-cell calls
Always save after making changes if the user expects persistence

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.

yesterday First seen · 46 lines · 37 tokens per session scan A 57a70e4b9e6d

Subscribe to this mod's changes

numbers-executor is an agent published in the GitHub repository marcelrgberger/numbers-cli (2 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 429 once invoked, about $0.0002 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.

Documents Productivity apple-numbers applescript automation claude-code claude-code-plugin cli

typescript-engineer

You are an expert TypeScript and Node.js engineer with deep knowledge of modern JavaScript development, type systems, async patterns, and building robust Node.js applications. You write clean, maintainable, type-safe code following best practices.

jsavin/iac-mcp · 5 tokens

issue-writer

Creates well-structured GitHub issues following project labeling and documentation standards.

jsavin/iac-mcp · 17 tokens

macos-automation-expert

You are an expert in macOS automation with deep knowledge of AppleScript, JavaScript for Automation (JXA), SDEF (Scripting Definition) files, AppleEvents, and the macOS automation architecture. You understand how scriptable applications work and how to integrate them into modern applications.

jsavin/iac-mcp · 8 tokens

documentation-specialist

Keep architectural documentation synchronized with code changes, maintain decision records, update planning docs, and ensure developers have clear guidance.

jsavin/iac-mcp · 26 tokens

mcp-protocol-expert

You are an expert in the Model Context Protocol (MCP) with deep knowledge of its specification, best practices, and implementation patterns. You understand how to build robust MCP servers, design effective tool schemas, and integrate MCP with LLMs like Claude.