marker

marker is a skill for Claude Code, Codex from benchflow-ai/skillsbench. It costs 45 tokens per session (490 once invoked), scanned A, original, Apache-2.0.

A converter that turns PDF files into Markdown while preserving document structure and mathematical formulas as LaTeX. Markdown is plain text with formatting symbols, and LaTeX is a notation system for equations.

In plain words
What is it for?
Use it to convert papers and other PDFs from the command line or Python, with options for time limits and temporary output files.
Why use it?
It makes academic and technical PDFs easier to edit, search, and reuse as structured text without losing equations.

Skill for Claude CodeCodex

About the project

SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.

benchflow-ai/skillsbench · 1,747 stars · on GitHub

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/benchflow-ai/skillsbench/marker
Any agent
npx skills add benchflow-ai/skillsbench --skill marker
Clone the repo
git clone --depth 1 https://github.com/benchflow-ai/skillsbench

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 marker

README.md
[![agentmods](https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/marker.svg)](https://agentmods.dev/skills/benchflow-ai/skillsbench/marker)
Your own site
<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/marker"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/marker.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 490 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 $0.00045 $0.00490
Opus 5 $0.00023 $0.00245
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00005 $0.00049

Measured 2d ago against content hash c931b6398d4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

marker 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/marker_to_markdown.py), 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • marker — 100% identical, 0 lines differ
tasks/latex-formula-extraction/environment/skills/marker/SKILL.md · 52 lines

What it actually says

Marker PDF-to-Markdown Converter

Convert PDFs to Markdown while preserving LaTeX formulas and document structure. Uses the marker_single CLI from the marker-pdf package.

Dependencies

  • marker_single on PATH (pip install marker-pdf if missing)
  • Python 3.10+ (available in the task image)

Quick Start

from scripts.marker_to_markdown import pdf_to_markdown

markdown_text = pdf_to_markdown("paper.pdf")
print(markdown_text)

Python API

  • pdf_to_markdown(pdf_path, *, timeout=600, cleanup=True) -> str
    • Runs marker_single --output_format markdown --disable_image_extraction
    • cleanup=True: use a temp directory and delete after reading the Markdown
    • cleanup=False: keep outputs in <pdf_stem>_marker/ next to the PDF
    • Exceptions: FileNotFoundError if the PDF is missing, RuntimeError for marker failures, TimeoutError if it exceeds the timeout
  • Tips: bump timeout for large PDFs; set cleanup=False to inspect intermediate files

Command-Line Usage

# Basic conversion (prints markdown to stdout)
python scripts/marker_to_markdown.py paper.pdf

# Keep temporary files
python scripts/marker_to_markdown.py paper.pdf --keep-temp

# Custom timeout
python scripts/marker_to_markdown.py paper.pdf --timeout 600

Output Locations

  • cleanup=True: outputs stored in a temporary directory and removed automatically
  • cleanup=False: outputs saved to <pdf_stem>_marker/; markdown lives at <pdf_stem>_marker/<pdf_stem>/<pdf_stem>.md when present (otherwise the first .md file is used)

Troubleshooting

  • marker_single not found: install marker-pdf or ensure the CLI is on PATH
  • No Markdown output: re-run with --keep-temp/cleanup=False and check stdout/stderr saved in the output folder
Files

What ships with it

1 file 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. 2d ago First seen · 52 lines · 45 tokens per session scan A c931b6398d4a

Subscribe to this mod's changes

marker is a skill published in the GitHub repository benchflow-ai/skillsbench (1,747 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 490 once invoked, about $0.0002 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 2026-09-03.