superlinked-docs

A document-processing workflow that sends PDFs, Word files, PowerPoint files, spreadsheets, web pages, and scanned documents to a remote service and returns clean Markdown text. Markdown is plain text with simple formatting marks.

In plain words
What is it for?
It helps extract document content, run OCR on scans, describe images with captions and tags, and produce JSON that follows a specified structure.
Why use it?
It lets the agent work from a converted text version instead of directly loading every page and image from the original file.

Skill for Claude CodeCodex

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 skills/superlinked/sie/plugin
Any agent
npx skills add superlinked/sie --skill plugin
Clone the repo
git clone --depth 1 https://github.com/superlinked/sie

Made for: Claude Code, Codex.

Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,135 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.

ModelPer sessionOnce invoked
Fable 5 $0.00125 $0.02135
Opus 5 $0.00063 $0.01068
Sonnet 5 $0.00025 $0.00427
Haiku 4.5 $0.00013 $0.00214

Measured yesterday against content hash 27d3cdb066a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

superlinked-docs 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.

packages/sie_mcp/plugin/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Superlinked document offload

When the user gives you a document (PDF, DOCX, PPTX, XLSX, HTML, or a scan), do not open or attach the file into the conversation — that bills every page as text and a page-image. Convert it to markdown on the Superlinked cluster first, then work from the markdown.

docs → markdown

  1. Read the source file as raw bytes and base64-encode it. Do not view or attach it.
  2. Call the docs_to_markdown MCP tool with:
    • document_base64: the base64-encoded bytes
    • filename: the original filename (its extension hints the format)
    • engine: leave as auto (default) — it runs the standard converter and automatically falls back to a vision OCR model for scanned/image-only pages, so scanned PDFs need no extra flag. Force vl-ocr for scanned or complex-layout PDFs you want OCR'd page-by-page, or docling to pin the standard converter.
    • ocr: leave false. It only turns on the standard converter's built-in OCR under engine: docling; under auto the vision-OCR fallback handles scans, so ocr is ignored there.
  3. Write the returned markdown to a file named after the source, then read and reason over that file — never the original. Where to write it depends on the surface:
    • Cowork (connected folder): .superlinked/<original-name>.md (create .superlinked/ if absent).
    • claude.ai / Claude desktop app (code-execution sandbox): ./<original-name>.md in the working directory; offer to export it (Download, save to Google Drive, or add to a Project's knowledge to reuse it across chats).
    • Claude Code (local filesystem): alongside the source.
  4. From here on, read and reason over the saved .md — never the original.

The tool response also includes a metadata object with two distinct figures: a live per-call markdown_tokens_estimate (a rough ~4 chars/token count of this response — an estimate, not a billed figure) and token_reduction, the reference benchmark measurement of markdown vs direct document ingestion. Surface these if the user asks how much was saved; the exact percentages and measurement run are in the metadata. Its source is a stable, public-safe run label; issue is null because no public issue tracks that committed measurement.

Read the full file on GitHub · 167 lines

Files

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.

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.

  1. yesterday First seen · 167 lines · 125 tokens per session scan A 27d3cdb066a9

Subscribe to this mod's changes

superlinked-docs is a skill published in the GitHub repository superlinked/sie (2,863 stars, last pushed 4d ago), licensed Apache-2.0. It adds 125 tokens to every session and 2,135 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

esm

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…

synthetic-sciences/openscience · 86 tokens

vector-search-workflows

Vector search indexing and querying workflows using MCP Vector Search, including setup, reindexing, auto-index strategies, and MCP integration.

bobmatnyc/claude-mpm-skills · 31 tokens

locus

npx @sylphx/locus --root=/absolute/path/to/project.

SylphxAI/coderag · 0 tokens

RAG Chunking Strategy Advisor

Given a document type and retrieval goal, recommends the optimal chunking strategy for a RAG pipeline to minimize retrieval failures.

Notysoty/openagentskills · 31 tokens

check-memory-before-acting

Search this project's own memory before doing something it may already have opinions about. Use before running a build/test/deploy command, before choosing a library or approach, before changing configuration or CI, and before re-opening a decision that may already have been settled. Also use when a task resembles…

GiulioDER/RE-call · 66 tokens

keep-memory-current

Load this project's memory when you start, and write back what you learned before you stop. Use at the beginning of a work session, when finishing a task or about to end a session, after debugging something non-obvious, after a decision that took argument to reach, and whenever you catch yourself thinking "I should…

GiulioDER/RE-call · 77 tokens