shuck

shuck is a command for Claude Code from Shan-Zhu/shuck-file. It costs 25 tokens per session (442 once invoked), scanned A, original, MIT.

A command that converts Word, PDF, spreadsheet, presentation, or CSV files into Markdown, a plain-text format for structured documents. For large files, it can first provide a map of the document.

In plain words
What is it for?
Use it to convert supported documents, extract selected sections, search for terms, or return tables without processing the whole file.
Why use it?
It makes information from common office files easier to read, search, and reuse in text-based workflows.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the shuck-file plugin — 1 skill, 1 command shipped together

Good fit Use it to convert supported documents, extract selected sections, search for terms, or return tables without processing the whole file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/shan-zhu/shuck-file/shuck
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/Shan-Zhu/shuck-file

Made for: Claude Code.

Or install shuck-file, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 shuck

README.md
[![agentmods](https://agentmods.dev/badge/commands/shan-zhu/shuck-file/shuck/github.svg)](https://agentmods.dev/commands/shan-zhu/shuck-file/shuck)
Your own site
<a href="https://agentmods.dev/commands/shan-zhu/shuck-file/shuck"><img src="https://agentmods.dev/badge/commands/shan-zhu/shuck-file/shuck/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 shuck

Your own site · 80×15
<a href="https://agentmods.dev/commands/shan-zhu/shuck-file/shuck"><img src="https://agentmods.dev/badge/commands/shan-zhu/shuck-file/shuck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 442 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 $0.00025 $0.00442
Opus 5 $0.00013 $0.00221
Sonnet 5 $0.00005 $0.00088
Haiku 4.5 $0.00003 $0.00044

Measured 11d ago against content hash 6442bd65cc61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

shuck 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 11d 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.

plugin/commands/shuck.md · 65 lines

What it actually says

/shuck

Convert a document to Markdown and display the result.

Instructions

Step 1: Validate the file

Check that the file exists and has a supported extension (.docx, .pdf, .xlsx, .pptx, .csv).

Step 2: Install dependencies if needed

If the conversion fails due to a missing dependency, install it:

pip install <package>

Packages by format:

  • .docx → python-docx
  • .pdf → pdfplumber
  • .xlsx → openpyxl
  • .pptx → python-pptx
  • .csv → no extra dependency

Step 3: Convert

Run shuck. It auto-detects file size and picks the best mode:

python "{{PLUGIN_DIR}}/shuck.py" "<path>"
  • Small files: outputs full Markdown directly
  • Large files: outputs a document map with sections and suggested next steps

Step 4: Follow up

If the result is a map (large file), follow the suggested next steps based on the user's needs:

# Extract specific sections
python "{{PLUGIN_DIR}}/shuck.py" "<path>" --sections s1,s3

# Search within document
python "{{PLUGIN_DIR}}/shuck.py" "<path>" --grep "keyword"

# Tables only
python "{{PLUGIN_DIR}}/shuck.py" "<path>" --tables-only

# Compress to fit budget
python "{{PLUGIN_DIR}}/shuck.py" "<path>" --budget 4000

# Force full output
python "{{PLUGIN_DIR}}/shuck.py" "<path>" --all

Step 5: Present the result

Display the Markdown content. If the user had a specific request (summarize, extract data, answer questions), do that with the converted content.

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. 11d ago First seen · 65 lines · 25 tokens per session scan A 6442bd65cc61

Subscribe to this mod's changes

shuck is a command published in the GitHub repository Shan-Zhu/shuck-file (6 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 442 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 2026-08-31.