xlsx-official

xlsx-official is a skill for Claude Code, Codex from evoelsewhere/evoflux. It costs 109 tokens per session (3,683 once invoked), scanned A, original, Apache-2.0.

A toolkit for building, editing, cleaning, and inspecting spreadsheet files such as Excel workbooks, CSV files, and tab-separated files. It supports formula-based models, summaries, template filling, and data repair.

In plain words
What is it for?
Use it to create or update financial and operating models, patch cells or rows, repair messy data, fill templates, and export sheets to CSV.
Why use it?
It provides a structured process for checking the source data, planning the workbook, recalculating it, and verifying the result before handoff.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to create or update financial and operating models, patch cells or rows, repair messy data, fill templates, and export sheets to CSV.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evoelsewhere/evoflux/xlsx-official
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.

Any agent
npx skills add evoelsewhere/evoflux --skill xlsx-official
Clone the repo
git clone --depth 1 https://github.com/evoelsewhere/evoflux

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 xlsx-official

README.md
[![agentmods](https://agentmods.dev/badge/skills/evoelsewhere/evoflux/xlsx-official.svg)](https://agentmods.dev/skills/evoelsewhere/evoflux/xlsx-official)
Your own site
<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/xlsx-official"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/xlsx-official.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,683 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 $0.00109 $0.03683
Opus 5 $0.00055 $0.01842
Sonnet 5 $0.00022 $0.00737
Haiku 4.5 $0.00011 $0.00368

Measured yesterday against content hash e8fc7d8edc2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

xlsx-official 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.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/assemble.py, scripts/audit.py, scripts/bake.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

app/agent/builtin_skills/xlsx-official/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XLSX Skill

An Apache-2.0 toolkit for producing, editing, and reading Microsoft Excel (.xlsx) files. Written from scratch against the public ECMA-376 / ISO/IEC 29500 (SpreadsheetML) specification and built on permissively-licensed tooling (openpyxl MIT, pandas BSD-3-Clause, lxml BSD-3-Clause, optional xlsxwriter BSD-2-Clause, optional external binary soffice MPL 2.0) so it can be reused in commercial projects without restriction.

Pipeline

Run these phases in order. Two are gates: do not pass a gate on your own judgement.

Phase 0  Inspect the data and the workspace
Phase 1  Settle the brief            ← ask once, bounded
Phase 2  Sheet plan + grain          ← GATE: user approves before building
Phase 3  Build
Phase 4  Recalculate and reconcile
Phase 5  Verify and repair           ← loop until it passes
Phase 6  Hand off

Phase 0 — Inspect. Row counts, columns, types, keys, duplicates, nulls, period, and any existing workbook's conventions. Never ask about something the data states.

Phase 1 — Settle the brief. Grain, drivers, and the output decide what the workbook is. Ask what context cannot answer, in one ask_user call — at most three questions with a marked recommendation. Skip for a mechanical transform or a local cell change. Read interview.md.

Phase 2 — Sheet plan and grain, then stop. Sheets and their purpose, what one row means, which cells become labelled inputs, the formulas that carry the result, the reconciliation target, and every transformation you will apply to the source data with its reason. Wait for approval. Silent cleaning is how an irreproducible number reaches a decision.

Phase 3 — Build. Drivers as labelled input cells, results as formulas, one grain per sheet, palette and number formats as the conventions below.

Phase 4 — Recalculate and reconcile. openpyxl never evaluates formulas. Recalculate, then check the totals against the target agreed in Phase 2. With no calculation engine available, say the values are uncomputed.

Read the full file on GitHub · 263 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. yesterday First seen · 263 lines · 109 tokens per session scan A e8fc7d8edc2d

Subscribe to this mod's changes

xlsx-official is a skill published in the GitHub repository evoelsewhere/evoflux (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 109 tokens to every session and 3,683 once invoked, about $0.0005 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 2026-09-06.