spreadsheets

spreadsheets is a skill for Claude Code, Codex from brightwave-inc/tidebreak. It costs 45 tokens per session (1,656 once invoked), scanned A, original, Apache-2.0.

A workflow for creating and safely inspecting Excel spreadsheet files. It uses Python for new workbooks and LibreOffice Calc for editing existing ones so formulas, formatting, charts, and other workbook parts can be preserved.

In plain words
What is it for?
It helps create XLSX workbooks, inspect existing files, edit them without rebuilding them destructively, recalculate formulas, and verify the final result.
Why use it?
Editing an existing Excel file with the wrong method can silently remove formulas, charts, styles, macros, and other data. The workflow adds checks before delivery.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .tidebreak/exec-scripts/calc_uno.py inspect input/model.xlsx.

Good fit It helps create XLSX workbooks, inspect existing files, edit them without rebuilding them destructively, recalculate formulas, and verify the final result.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/brightwave-inc/tidebreak
agentmods
npx agentmods add skills/brightwave-inc/tidebreak/spreadsheets

Made for: Claude Code, Codex.

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 spreadsheets

README.md
[![agentmods](https://agentmods.dev/badge/skills/brightwave-inc/tidebreak/spreadsheets/github.svg)](https://agentmods.dev/skills/brightwave-inc/tidebreak/spreadsheets)
Your own site
<a href="https://agentmods.dev/skills/brightwave-inc/tidebreak/spreadsheets"><img src="https://agentmods.dev/badge/skills/brightwave-inc/tidebreak/spreadsheets/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 spreadsheets

Your own site · 80×15
<a href="https://agentmods.dev/skills/brightwave-inc/tidebreak/spreadsheets"><img src="https://agentmods.dev/badge/skills/brightwave-inc/tidebreak/spreadsheets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,656 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00045 $0.01656
Opus 5.5 $0.00018 $0.00662
Sonnet 5.5 $0.00009 $0.00331
Haiku 4.5 $0.00005 $0.00166

Measured 1mo ago against content hash 6233e4f7eaf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spreadsheets 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 1mo 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.

skills/spreadsheets/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spreadsheets

Produce XLSX deliverables with openpyxl, and edit workbooks that already exist with LibreOffice Calc. Follow every section below before declaring a workbook done.

Never round-trip an existing workbook with openpyxl

openpyxl writes new workbooks. It never touches a file that already exists — not to change one number, not for a "quick value edit".

load_workbook(path) followed by .save(path) does not edit the file; it rebuilds it from the parts openpyxl models, and everything else is gone. In practice that means silently losing:

  • formula results the engine computed — openpyxl drops the cached values, so every formula reads as empty until someone opens the file in Excel
  • named ranges, pivot tables and their caches
  • charts, images, and shapes
  • conditional formatting and data validation
  • macros, custom styles, and sheet protection

None of this raises an error. The file saves, looks plausible in an inspection script, and hands the user a gutted copy of their own workbook.

Read-only inspection is fine and expected: load_workbook(path, read_only=True) or data_only=True, with no .save() anywhere near it. The bundled analyze_xlsx.py does exactly this.

Installing the library

Install the pinned dependency with its own exec call — commands have a bounded wall clock, and one pip invocation per package stays inside it:

python3 -m pip install --user openpyxl==3.1.5

Installs work only when this chat's network policy allows package managers, and they persist for the rest of the conversation. If an install is refused by policy, do not retry: tell the user to enable the package-manager network policy for this chat, and offer the closest format you can produce without the library (CSV) — only with their knowledge, never as a silent substitution. If a dependency cannot be installed at all, say so plainly instead of quietly delivering a lesser format.

Creating a new workbook

A workbook built from scratch is openpyxl's job, with the formula and layout rules below. Nothing in this section changes because of the edit path.

Read the full file on GitHub · 155 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. 1mo ago First seen · 155 lines · 45 tokens per session scan A 6233e4f7eaf9

Subscribe to this mod's changes

spreadsheets is a skill published in the GitHub repository brightwave-inc/tidebreak (32 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 1,656 once invoked, about $0.0002 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 2026-08-30.