What is shuck-file CLAUDE.md?

Development instructions for shuck-file, a document-to-Markdown converter for AI agents. It chooses between direct output and a document map with extraction options based on file size.

Use it to convert documents for an AI agent, inspect selected sections, search within a file, or run the project’s tests and MCP server.

They show how to install, test and run the converter, including targeted extraction from large documents.

How Shan-Zhu/shuck-file configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Shan-Zhu/shuck-file. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Shan-Zhu/shuck-file/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Shan-Zhu/shuck-file

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/shan-zhu/shuck-file/claude-md/github.svg)](https://agentmods.dev/instructions/shan-zhu/shuck-file/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/shan-zhu/shuck-file/claude-md"><img src="https://agentmods.dev/badge/instructions/shan-zhu/shuck-file/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/shan-zhu/shuck-file/claude-md"><img src="https://agentmods.dev/badge/instructions/shan-zhu/shuck-file/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 990 This file is loaded in full into every session.

When invoked 990 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00990	$0.00990
Opus 5	$0.00495	$0.00495
Sonnet 5	$0.00198	$0.00198
Haiku 4.5	$0.00099	$0.00099

Measured 11d ago against content hash 17edb6e4eacd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

shuck-file CLAUDE.md 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.

CLAUDE.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

# Install in development mode
pip install -e .

# Run all tests
python -m pytest tests/ -v

# Run a single test file
python -m pytest tests/test_router.py -v

# Run a single test
python -m pytest tests/test_router.py::TestRouterAutoRouting::test_small_file_direct -v

# CLI usage (after pip install -e .)
shuck <file>
shuck probe <file>              # force map mode
shuck <file> --all              # force full output
shuck <file> --grep "keyword"
shuck <file> --sections s1,s3
shuck <file> --budget 4000

# CLI usage (without install, from repo root)
python plugin/shuck.py <file>

# MCP Server development
fastmcp dev src/shuck_file/server.py

Architecture

shuck-file is a document-to-Markdown converter for AI agents. Its core design: one command, smart behavior — small files output directly, large files return a document map with extraction options.

Package Structure

src/shuck_file/              # PyPI package (the source of truth)
  ├── __init__.py             # Version
  ├── cli.py                  # CLI entry point (console_scripts: shuck)
  ├── server.py               # MCP Server (FastMCP)
  ├── core/                   # Core logic
  │   ├── router.py           # Auto-routing
  │   ├── segmenter.py        # Document segmentation
  │   ├── mapper.py           # Map mode renderer
  │   ├── budget.py           # Smart compression
  │   ├── grep.py             # In-document search
  │   ├── frontmatter.py      # YAML frontmatter
  │   └── models.py           # Data models
  └── extractors/             # Format-specific extractors
      ├── base.py             # Base extractor ABC
      ├── docx_ext.py         # Word
      ├── pdf_ext.py          # PDF
      ├── xlsx_ext.py         # Excel
      ├── pptx_ext.py         # PowerPoint
      └── csv_ext.py          # CSV

plugin/                       # Claude Code plugin (thin wrapper)
  ├── shuck.py                # Delegates to shuck_file.cli.main()
  ├── .claude-plugin/         # Plugin manifest
  └── commands/               # Skill definitions

Read the full file on GitHub · 101 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.

11d ago First seen · 101 lines · 990 tokens per session scan A 17edb6e4eacd

Subscribe to this mod's changes

shuck-file CLAUDE.md is an instructions file published in the GitHub repository Shan-Zhu/shuck-file (6 stars, last pushed 5mo ago), licensed MIT. It adds 990 tokens to every session, about $0.0049 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.

Documents

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

shuck-file: Instructions file for Claude Code