office-doc

office-doc is a skill for Claude Code, Codex from fisker086/AIOps. It costs 26 tokens per session (506 once invoked), scanned A, original, Apache-2.0.

A document and data reader for PDFs, spreadsheets, CSV files, Word documents, and common configuration formats such as YAML and JSON.

In plain words
What is it for?
Use it to extract or search PDF and Word text, inspect spreadsheet columns and rows, calculate statistics, filter data, and read configuration values.
Why use it?
It removes the need to manually open files or write separate parsing code for each format.

Skill for Claude CodeCodex

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 skills/fisker086/aiops/office_doc
Any agent
npx skills add fisker086/AIOps --skill office_doc
Clone the repo
git clone --depth 1 https://github.com/fisker086/AIOps

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 office-doc

README.md
[![agentmods](https://agentmods.dev/badge/skills/fisker086/aiops/office_doc.svg)](https://agentmods.dev/skills/fisker086/aiops/office_doc)
Your own site
<a href="https://agentmods.dev/skills/fisker086/aiops/office_doc"><img src="https://agentmods.dev/badge/skills/fisker086/aiops/office_doc.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 506 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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00506
Opus 5 $0.00013 $0.00253
Sonnet 5 $0.00005 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 5d ago against content hash 7cf7ad818e09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

office-doc 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 5d 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/office_doc/SKILL.md · 62 lines

What it actually says

Office Doc Skill

All-in-one office document processing tool. Use builtin_office_doc tool with the following operations:

Supported Formats

1. PDF

  • extract: Extract text from PDF pages
  • metadata: Get PDF info (pages, size, author)
  • search: Search text in PDF

2. Excel / CSV

  • parse: Parse spreadsheet data
  • info: Show columns and types
  • stats: Calculate statistics
  • head/tail: Show rows
  • filter: Filter by column value

3. Word (.docx)

  • extract: Extract text from Word document

4. Config Files

  • yaml/yml: Parse YAML to JSON
  • json: Parse JSON, get keys
  • ini: Parse INI sections
  • toml: Parse TOML config
  • xml: Parse XML elements

Parameters

  • format: File type (pdf, excel, csv, docx, yaml, json, ini, toml, xml)
  • operation: Operation (parse, extract, info, stats, head, tail, filter, search, metadata)
  • content: File content or data
  • file_path: Path to file (for PDF)
  • page: Page number (for PDF)
  • query: Search query
  • column: Column name
  • value: Filter value
  • key: Key path (dot notation)

Examples

# Parse CSV
format: csv, content: "name,age\nAlice,30\nBob,25", operation: stats

# Extract from PDF
format: pdf, file_path: "/path/to/file.pdf", operation: extract, page: 1

# Parse YAML
format: yaml, content: "name: test\nvalue: 123", operation: to_json

# Filter CSV
format: csv, content: "name,age\nAlice,30\nBob,25", operation: filter, column: name, value: Alice
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. 5d ago First seen · 62 lines · 26 tokens per session scan A 7cf7ad818e09

Subscribe to this mod's changes

office-doc is a skill published in the GitHub repository fisker086/AIOps (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 506 once invoked, about $0.0001 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 2026-08-30.