agentmods.dev

excel-digest

excel-digest is an agent for Claude Code from gonzalezpazmonica/savia. It costs 78 tokens per session (1,022 once invoked), scanned A, original, MIT.

A spreadsheet analysis agent for Excel and CSV files. It extracts sheet structure, formulas, validations, formatting rules, and embedded business logic without extracting full transaction data.

In plain words
What is it for?
Use it to inspect workbook sheets, translate formulas into plain language, list macros without running them, and compare the workbook with project documentation.
Why use it?
It makes complex spreadsheets easier to understand while avoiding a dump of all their underlying records. It can also highlight unclear columns, complex formulas, and broken references.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; mentions OpenCode.

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

not rated 50repo today A scan 78 tokens original MIT

Good fit Use it to inspect workbook sheets, translate formulas into plain language, list macros without running them, and compare the workbook with project documentation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gonzalezpazmonica/savia/excel-digest
View source ↗ gonzalezpazmonica/savia
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.

Clone the repo
git clone --depth 1 https://github.com/gonzalezpazmonica/savia

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 agents.

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 excel-digest

README.md
[![agentmods](https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/excel-digest/github.svg)](https://agentmods.dev/agents/gonzalezpazmonica/savia/excel-digest)
Your own site
<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/excel-digest"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/excel-digest/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 excel-digest

Your own site · 80×15
<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/excel-digest"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/excel-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,022 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.
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 $0.00078 $0.01022
Opus 5 $0.00039 $0.00511
Sonnet 5 $0.00016 $0.00204
Haiku 4.5 $0.00008 $0.00102

Measured 3d ago against content hash 5758649164a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

excel-digest 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/excel-digest.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

excel-digest — Digestion Contextual de Excel en 4 Fases

Extrae estructura, reglas de negocio y patrones de datos de hojas de calculo. NO extrae datos transaccionales — solo estructura, formulas, validaciones y logica de negocio embebida.

Dependencia: pip install openpyxl (instalar automaticamente si falta)

Fase 1 — Extraccion bruta (sin contexto)

  1. Enumerar hojas: nombre, filas x columnas con datos
  2. Para cada hoja relevante:
    • Cabeceras (fila 1 o primera con datos)
    • Muestra de 5-10 filas (estructura, no datos completos)
    • Columnas con formulas (cargar data_only=False para comparar)
  3. Extraer formulas unicas (sin repetir por fila):
    • Clasificar: calculo, validacion, referencia cruzada, condicional
    • Traducir a lenguaje natural: "columna G = suma de D a F"
  4. Detectar validaciones de datos (dropdowns, restricciones)
  5. Detectar formato condicional (reglas de color, umbrales)
  6. Detectar macros (.xlsm): listar nombres sin ejecutar
  7. Marcar [?] columnas sin cabecera, formulas complejas, referencias rotas

Fase 2 — Carga de contexto y resolucion

Leer ficheros del proyecto:

  • CLAUDE.md, README.md, RULES.md, GLOSSARY.md (si existen)
  • business-rules/DATA-MODEL.md (si existe)

Resolver: nombres de columnas vs entidades del dominio, acronimos vs glosario, formulas vs reglas de negocio conocidas, referencias entre hojas vs flujos.

Fase 3 — Analisis y sintesis

  1. Clasificar: operacional | reporte | plantilla | configuracion | calculo
  2. Extraer reglas de negocio de formulas:
    • IF/SWITCH → reglas condicionales
    • VLOOKUP/INDEX-MATCH → relaciones entre entidades
    • SUMIF/COUNTIF → agregaciones con criterios
  3. Detectar antipatrones: datos hardcodeados, logica que deberia estar en el sistema, referencias circulares, hojas ocultas con datos criticos
  4. Cruzar: campos vs DATA-MODEL.md, formulas vs RULES.md, datos vs STATUS.md

Fase 4 — Actualizacion de contexto (OBLIGATORIA)

Protocolo identico a pdf-digest Fase 4. Ademas:

  • Reglas de negocio descubiertas → actualizar RULES.md
  • Entidades no mapeadas → actualizar DATA-MODEL.md
  • Terminos nuevos → actualizar GLOSSARY.md
  • Registrar en _digest-log.md

Read the full file on GitHub · 103 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. 3d ago First seen · 103 lines · 78 tokens per session scan A 5758649164a8

Subscribe to this mod's changes

excel-digest is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,022 once invoked, about $0.0004 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.

Claude CodeDocumentsSpreadsheetscodexharnessopencode
Related

Other agents, from other repositories

china-model-builder

Builds DCF, LBO, 3-statement, and comps models for Chinese equities using AkShare-sourced financial data. Use when a user requests a full financial model for an A-share stock. Not for one-off calculations.

jwangkun/claude-for-financial-services-cn · 52 tokens

china-model-builder

A financial-modeling agent for Chinese mainland stock-market companies. It builds linked Excel workbooks for discounted cash flow valuation, comparable-company analysis, and forecasts of the income statement, balance sheet, and cash-flow statement.

cyijun/china-financial-services · 51 tokens

sheet-agent

XLSX creation, editing, and analysis using openpyxl and pandas.

benbrastmckie/nvim · 18 tokens

chart-designer

A spreadsheet chart and visualisation assistant. It chooses or creates charts such as bar, line, pie, scatter, and combination charts, and can apply visual formatting.

claude-office-skills/claude-office-plugin · 87 tokens

cell-engine-builder

A builder for a spreadsheet engine, the software that stores cells and sheets and calculates formulas. It also implements built-in spreadsheet functions.

revfactory/claude-code-harness · 0 tokens

study-screener

A literature-screening assistant for reviewing search results against predefined inclusion and exclusion rules. It helps organize screening decisions and prepare data for a PRISMA flow diagram, which shows how studies were selected for a systematic review.

johnson7788/meta-analysis-assistant · 422 tokens