A command that converts files or web addresses into Markdown, a plain-text format commonly used for documents and documentation.

Use it to convert a file or URL, inspect the conversion result, and identify when optional tools may be needed for better extraction.

It turns PDFs, web pages, images, and other inputs into text an agent can read and work with, while reporting possible extraction limits.

convert — Command by ojspace

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 commands/ojspace/md-anything/convert

Clone the repo

git clone --depth 1 https://github.com/ojspace/md-anything

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 385 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.

Model	Per session	Once invoked
Fable 5	$0.00011	$0.00385
Opus 5	$0.00005	$0.00192
Sonnet 5	$0.00002	$0.00077
Haiku 4.5	$0.00001	$0.00038

Measured yesterday against content hash add63a18af07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

convert 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 yesterday.

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-plugin/commands/convert.md · 39 lines

What it actually says

Convert the given input to Markdown using the mda CLI.

Usage: /md-anything:convert <input>

Where <input> is a file path or URL. Examples:

/md-anything:convert report.pdf
/md-anything:convert "https://example.com/article"
/md-anything:convert image.png

Steps

Run the conversion with JSON output for structured results:
```
mda convert "$ARGUMENTS" --json
```
Parse the JSON response:
- input — the original file path or URL
- markdown — the converted Markdown content
- kind — detected input type (pdf, url, image, epub, etc.)
- supportLevel — strong, best-effort, or optional
- metadata — extraction details including extraction_status and usefulness_score
- warnings — optional guidance when results are weak or uncertain
Display the Markdown to the user.
If supportLevel is best-effort or optional, or if extraction_status is not ok, inform the user that results may be limited and suggest running mda doctor to see if optional tools can improve results.

Notes

If mda is not installed, instruct the user to run: bun install -g md-anything
For PDFs, HTML, and plain URLs: expect strong results
For images: results improve with tesseract installed
For audio/video: whisper-cpp is preferred, whisper also works, and OPENROUTER_API_KEY is an opt-in remote fallback

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.

yesterday First seen · 39 lines · 11 tokens per session scan A add63a18af07

Subscribe to this mod's changes

convert is a command published in the GitHub repository ojspace/md-anything (49 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 385 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 2026-08-30.

Data and AI Documents Writing and docs ai-agents claude cursor document-processing markdown mcp

convert

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Steps

Notes

What this file has done since we first saw it

Other commands, from other repositories

crux-meditate

crux-compress

crux-test

crux-dream

crux-recall

crux-amnesia