file-ops

file-ops is a skill for Claude Code, Codex from wowyuarm/file-ops-skill. It costs 108 tokens per session (595 once invoked), scanned A, original, MIT.

A local file utility for converting, inspecting, archiving, and extracting text from common files such as PDFs, Word documents, spreadsheets, HTML, Markdown, and images.

In plain words
What is it for?
Use it to convert formats, inspect file details, create or unpack ZIP archives, and extract readable text or image metadata.
Why use it?
It brings common file-handling jobs into one command-line workflow and reports missing dependencies when an operation cannot run.

Skill for Claude CodeCodex

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

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/wowyuarm/file-ops-skill/file-ops
Any agent
npx skills add wowyuarm/file-ops-skill --skill file-ops
Clone the repo
git clone --depth 1 https://github.com/wowyuarm/file-ops-skill

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 file-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/wowyuarm/file-ops-skill/file-ops.svg)](https://agentmods.dev/skills/wowyuarm/file-ops-skill/file-ops)
Your own site
<a href="https://agentmods.dev/skills/wowyuarm/file-ops-skill/file-ops"><img src="https://agentmods.dev/badge/skills/wowyuarm/file-ops-skill/file-ops.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 595 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 5.1 $0.00108 $0.00595
Opus 5 $0.00054 $0.00298
Sonnet 5 $0.00022 $0.00119
Haiku 4.5 $0.00011 $0.00060

Measured 6d ago against content hash 14d05dde7828, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

file-ops 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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/file_ops.py, scripts/setup.sh), 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.

skills/file-ops/SKILL.md · 55 lines

What it actually says

File Ops

Workflow

  1. Run health check to discover available operations and missing dependencies:
    .venv/bin/python <SKILL_DIR>/scripts/file_ops.py health
    
  2. Run the appropriate command with explicit paths:
    .venv/bin/python <SKILL_DIR>/scripts/file_ops.py <command> --input /path/to/file [options]
    
  3. Read the JSON result and report the output path, metadata, or extracted text to the user.
  4. If a dependency is missing, surface the exact gap from the health report or error message.

Replace <SKILL_DIR> with the absolute path to this skill directory. The script must be invoked with the Python interpreter from the skill's own .venv (located at <SKILL_DIR>/.venv). Run <SKILL_DIR>/scripts/setup.sh if the .venv does not exist.

Commands

Command Purpose Key flags
health Report runtime capabilities (none)
convert Convert file format --input, --to, --output, --sheet, --overwrite
inspect Return file metadata as JSON --input
archive Create or extract zip --input (multi), --output, --extract
extract-text Extract readable text --input

Supported Conversions

  • Image formats: png, jpg, jpeg, webp, gif, bmp, tiff
  • pdf -> docx
  • xlsx -> csv
  • xls -> csv (requires xlrd, not installed by default)
  • docx -> pdf (requires LibreOffice)
  • html/md/markdown -> pdf (requires wkhtmltopdf)

Notes

  • All operations are path-based. Do not wrap file content in base64 unless the user explicitly asks.
  • Run health before promising support for optional conversions or operations.
  • For Excel conversion, --sheet accepts a sheet name or zero-based index.
  • If a conversion or operation is unavailable, surface the exact dependency gap instead of falling back silently.
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 55 lines · 108 tokens per session scan A 14d05dde7828

Subscribe to this mod's changes

file-ops is a skill published in the GitHub repository wowyuarm/file-ops-skill (24 stars, last pushed 5mo ago), licensed MIT. It adds 108 tokens to every session and 595 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 2026-08-30.