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 skills add Lab94/frenchie-skill --skill frenchiegit clone --depth 1 https://github.com/Lab94/frenchie-skillWrote 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/skills/lab94/frenchie-skill/frenchie)<a href="https://agentmods.dev/skills/lab94/frenchie-skill/frenchie"><img src="https://agentmods.dev/badge/skills/lab94/frenchie-skill/frenchie/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.
<a href="https://agentmods.dev/skills/lab94/frenchie-skill/frenchie"><img src="https://agentmods.dev/badge/skills/lab94/frenchie-skill/frenchie.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00054 | $0.02514 |
| Opus 5.5 | $0.00022 | $0.01006 |
| Sonnet 5.5 | $0.00011 | $0.00503 |
| Haiku 4.5 | $0.00005 | $0.00251 |
Grade A, and why
frenchie 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. PUT the file to `upload_url` with the correct `Content-Type` header (e.g. via `curl -X PUT -H "Content-Type: application/pdf" -T file.pdf "<upload_url>"`) How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frenchie — Your Agent's Best Friend
Frenchie is an MCP-first multimodal utility that expands what agents can do. When installed via npx @lab94/frenchie install, Frenchie runs as a local stdio MCP server and results are auto-saved to .frenchie/<name>/. Hosted/web agents connect over HTTP at https://mcp.getfrenchie.dev — both transports are supported.
Shipping today: OCR for PDFs and images, transcription for audio and video, image generation from text prompts, and structured file extraction for Office/CSV files. Rolling out next: Markdown-to-file generation (Word, Excel). New tools appear in this skill as they launch.
MCP Tools
Use the Frenchie MCP server. Never call model provider APIs directly.
| Tool | Purpose | Input |
|---|---|---|
ocr_to_markdown |
PDF/Image to Markdown | file_path (stdio) or uploaded_file_reference (HTTP) |
transcribe_to_markdown |
Audio/Video to Markdown | file_path (stdio) or uploaded_file_reference (HTTP) |
extract_to_markdown |
Word/Excel/CSV/TSV/PowerPoint to Markdown | file_path (stdio) or uploaded_file_reference (HTTP) |
generate_image |
Text prompt to image | prompt, optional style/size/quality/format/background/output_dir |
get_job_result |
Poll async job result | job_id |
upload_file |
Get presigned upload URL (HTTP only) | filename, file_size, mime_type |
fetch_result_file |
Download result image (HTTP only) | object_key |
All tools accept optional api_key (only needed if FRENCHIE_API_KEY is not already set).
File Access by Transport Mode
- stdio (default when installed locally): the MCP server runs on the same machine, so
file_pathworks with absolute local paths. Results are auto-saved to.frenchie/<name>/next to the source file. - HTTP (hosted agents): the MCP server runs remotely, so local file paths do not exist on the server. NEVER send
file_pathover HTTP. Upload first, then useuploaded_file_reference.
What ships with it
5 files 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.
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.
- 1mo ago First seen · 151 lines · 54 tokens per session scan A 77632730220f
frenchie is a skill published in the GitHub repository Lab94/frenchie-skill (0 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 2,514 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…