A command that converts a file into Markdown using the Frenchie service’s optical character recognition, or OCR. OCR reads text from images and scanned documents.

Use it to extract written content from scanned documents and image-based files into editable Markdown.

It removes the need to retype text from PDFs, scans, or images. The workflow also handles file uploading and saving the resulting Markdown in the required location.

ocr — Command by Lab94

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/lab94/frenchie-skill/ocr

Clone the repo

git clone --depth 1 https://github.com/Lab94/frenchie-skill

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 501 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00000	$0.00501
Opus 5	$0.00000	$0.00251
Sonnet 5	$0.00000	$0.00100
Haiku 4.5	$0.00000	$0.00050

Measured yesterday against content hash d0da3b4e93d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ocr scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

PUT the file to `upload_url` (e.g. `curl -X PUT -H "Content-Type: application/pdf" -T file.pdf "<upload_url>"`).

skills/frenchie/commands/ocr.md · 21 lines

What it actually says

Convert the file at $ARGUMENTS into Markdown using the Frenchie MCP server.

Hard rule: in HTTP mode, MUST persist the final Markdown to .frenchie/{name}/result.md before concluding the task. This rule does not apply to stdio mode because the local MCP server already writes .frenchie/... automatically.

Determine transport mode:
- HTTP (MCP configured with url/serverUrl): NEVER send file_path. Call upload_file with filename, file_size (bytes), mime_type → get upload_url and object_key. PUT the file to upload_url (e.g. curl -X PUT -H "Content-Type: application/pdf" -T file.pdf "<upload_url>"). Then call ocr_to_markdown with uploaded_file_reference set to object_key.
- stdio (MCP configured with command/args): call ocr_to_markdown with file_path set to the absolute path
If status is "done":
- stdio mode → the response is metadata-only (savedTo, wordCount, imageCount). Read the file at savedTo with your own file tool if the task needs the content; do not re-run the OCR job expecting inline markdown
- HTTP mode → continue to step 5 to save results locally before concluding the task
If status is "processing", poll with get_job_result using the returned jobId until done
If the result has expired, inform the user that the payload is no longer available
If the result contains frenchie-result: image references (HTTP mode), call fetch_result_file for each object_key and save to .frenchie/{name}/ where name is the source filename without extension (e.g. report.pdf → .frenchie/report/)
In HTTP mode, rewrite any frenchie-result: references to local filenames and write the final Markdown to .frenchie/{name}/result.md
If there are no frenchie-result: references, still write the returned Markdown to .frenchie/{name}/result.md

Supported formats: PDF, PNG, JPG/JPEG, WebP

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 · 21 lines · 0 tokens per session scan A d0da3b4e93d1

Subscribe to this mod's changes

ocr is a command published in the GitHub repository Lab94/frenchie-skill (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 501 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Writing and docs

ocr

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement