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.
npx agentmods add instructions/bowenliang123/markdown-exporter/agents-mdgit clone --depth 1 https://github.com/bowenliang123/markdown-exporterWrote 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.
[](https://agentmods.dev/instructions/bowenliang123/markdown-exporter/agents-md)<a href="https://agentmods.dev/instructions/bowenliang123/markdown-exporter/agents-md"><img src="https://agentmods.dev/badge/instructions/bowenliang123/markdown-exporter/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01274 | $0.01274 |
| Opus 5 | $0.00637 | $0.00637 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
markdown-exporter AGENTS.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 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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Coding Guidelines for md-exporter
This document provides essential information for agentic coding agents working in the md-exporter repository.
🔧 Build, Lint, and Test Commands
Package Management
- Primary:
uvpackage manager is used for dependency management - Fallback:
pipifuvis not available - Python Requirement: Python 3.11 or higher required
Code Quality and Formatting
Lint and Format Code
# Alternative: Run from project root using provided script
./dev.reformat.sh
Run Tests
# Run all tests
test/bin/run_all_tests.sh
# Run specific test file
test/bin/test_md_to_docx.sh
or
uv run pytest test/skills/test_md_to_docx.py
Development Scripts
- Test Scripts: Individual test scripts in
test/bin/
📝 Code Style Guidelines
Formatting and Style
- Line Length: 120 characters maximum
- Line Ending: LF (Unix-style)
- Indentation: 4 spaces (not tabs)
- Quotes: Use double quotes for strings unless single quotes are preferred for specific cases
- End of File: All files must end with newline character
Python Style Standards
Import Organization
# Standard library imports
from pathlib import Path
from tempfile import NamedTemporaryFile
# Third-party imports
from pypandoc import convert_file
# Local imports (relative paths)
from scripts.utils.markdown_utils import get_md_text
Type Hints and Annotations
- Use Python 3.11+ union syntax:
Path | None(notOptional[Path]) - All function parameters and return values should have type hints
- Use pathlib.Path for file paths, not strings
Function Documentation
def convert_md_to_docx(
md_text: str, output_path: Path, template_path: Path | None = None, is_strip_wrapper: bool = False
) -> None:
"""
Convert Markdown text to DOCX format
Args:
md_text: Markdown text to convert
output_path: Path to save the output DOCX file
template_path: Optional path to DOCX template file
is_strip_wrapper: Whether to remove code block wrapper if present
Raises:
ValueError: If input processing fails
Exception: If conversion fails
"""
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.
- 5d ago First seen · 172 lines · 1,274 tokens per session scan A d9ec1552ba3b
markdown-exporter AGENTS.md is an instructions file published in the GitHub repository bowenliang123/markdown-exporter (267 stars, last pushed 22d ago), licensed Apache-2.0. It adds 1,274 tokens to every session, about $0.0064 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.
Other instructions, from other repositories
claude-chat-exporter CLAUDE.md
Instructions for agarwalvishal/claude-chat-exporter, covering claude.md, what this is, core design decision, how the export works and the install page & bookmarklet (docs/index.html).
markitdown-mcp AGENTS.md
Instructions for trsdn/markitdown-mcp, covering ai agents integration guide, 🤖 quick reference for ai agents, primary use cases, available tools and 🛠️ tool usage guide.
go-docs-mcp CLAUDE.md
Instructions for drolosoft/go-docs-mcp, covering go-docs-mcp, build & run, architecture, key decisions and tools.
vkr-builder CLAUDE.md
Claude Code instructions for maxbarsukov/vkr-builder, covering vkr-builder, как себя вести and основные команды.
docsift CLAUDE.md
Instructions for anishmoncivarghese/docsift, covering docsift, key documents (read before making product decisions), commands, architecture (src layout, package docsift) and hard rules.
webdown CLAUDE.md
Claude Code instructions for kelp/webdown, covering webdown development guide, working with claude, version management (semantic versioning), modern python development setup (python 3.10+) and build & testing commands.