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 mariolpantunes/crepe-mcp --skill crepegit clone --depth 1 https://github.com/mariolpantunes/crepe-mcpWrote 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/mariolpantunes/crepe-mcp/crepe)<a href="https://agentmods.dev/skills/mariolpantunes/crepe-mcp/crepe"><img src="https://agentmods.dev/badge/skills/mariolpantunes/crepe-mcp/crepe/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/mariolpantunes/crepe-mcp/crepe"><img src="https://agentmods.dev/badge/skills/mariolpantunes/crepe-mcp/crepe.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 | $0.00071 | $0.00891 |
| Opus 5.5 | $0.00028 | $0.00356 |
| Sonnet 5.5 | $0.00014 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
crepe 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 7d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
crepe
CREPE is six MCP servers, one per domain. Paths below are relative to this skill's folder.
Steps
- Pick the task in the table and read only its reference file (it starts with a
Read when:line). - Make sure the server's tools are available. If they are not listed, the server is disabled: enable it (Goose:
manage_extensions, actionenable, the server name) or search the tool by name if your host defers tool schemas. Still missing: readreferences/troubleshooting.md. - Follow the tool order. Call the
lint_*tool before every compile and fix every issue it returns. - Write compiled files where the user asked (absolute path), then call the
cleanup_*tool.
Tasks
| Task | Server | Tool order | Reference |
|---|---|---|---|
| Slide deck | crepe-presentations |
create_presentation, set_slide per slide, lint_presentation, compile_presentation, render_slides_as_pngs, cleanup_presentation |
references/presentations.md |
| A4 report or paper | crepe-documents |
create_document, set_chapter and set_section, lint_document, compile_document, render_document_as_pngs, cleanup_document |
references/documents.md |
| draw.io figure | crepe-diagrams |
write the .drawio (or scripts/dg.py), lint_drawio, export_drawio |
references/diagrams.md |
| Papers, web, Wikipedia | crepe-research |
academic_search or arxiv_search, web_search, wikipedia_search then wikipedia_read, fetch_webpage |
references/research.md |
| Read, review or cite an existing file (PDF, DOCX, Markdown, ...) | crepe-reader |
open_document, read_section / search_document / read_pages, list_assets, get_asset, list_changes (DOCX), render_page_image, document_to_markdown |
references/reader.md |
| Excel workbook | crepe-spreadsheets |
create_excel, update_excel_sheet, inspect_excel, markdown_table_to_excel |
references/spreadsheets.md |
Rules
- Slide and document text is Pandoc Markdown only. No raw LaTeX (
\includegraphics,\begin{center},\textbf): it vanishes in PPTX and DOCX. - Every image and output path is absolute, and the image exists before you compile.
- Decks and documents live in the server's memory under an id. A restarted server forgets them: keep the source with
export_presentation_sourceorexport_document_sourcewhen the work is long. - Look at rendered PNGs only if you can see images; otherwise trust a clean lint and a successful compile.
- API keys are never typed into a chat or a config.
web_searchneedsCREPE_TAVILY_API_KEYin the user's.env; without it the tool answers with awarningfield, so report that and use another source.
What ships with it
8 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.
- 7d ago First seen · 44 lines · 71 tokens per session scan A b6a83438f234
crepe is a skill published in the GitHub repository mariolpantunes/crepe-mcp (2 stars, last pushed 7d ago), licensed MIT. It adds 71 tokens to every session and 891 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-12.
Other skills, from other repositories
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
surfsense-documents
Make or change a Word document (.docx), a PDF, a PowerPoint deck (.pptx) or an Excel workbook (.xlsx) by writing a Python script that surfsenserenderdocument runs, optionally starting from a source's own Word or PowerPoint file. Load it whenever the user asks for one of these, or for a change to one you made.
xberg-extracting-tables
Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
report-generator
A report-generation tool for producing SEO and GEO analysis reports in formats such as Markdown, HTML, PDF, JSON, and Excel. It also supports charts, templates, data processing, and interactive report elements.
kordoc
A command-line and server tool for reading and creating Korean official documents, including HWP, HWPX, PDF, DOCX, and spreadsheet files. It can convert documents to Markdown and create or update HWPX files.