superdocs

A skill for working with formatted documents such as Word files, PDFs, HTML, Markdown, and plain text through the SuperDocs service. It is intended for AI coding assistants and includes workflows for editing, creating, restructuring, and exporting documents.

In plain words
What is it for?
Use it to draft or edit formatted documents, restructure existing files, and export them while retaining their visual styling.
Why use it?
It helps preserve document layout details such as tables, borders, shading, fonts, and inline formatting while documents are changed or exported.

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

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,455 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.

ModelPer sessionOnce invoked
Fable 5 $0.00105 $0.05455
Opus 5 $0.00053 $0.02728
Sonnet 5 $0.00021 $0.01091
Haiku 4.5 $0.00011 $0.00545

Measured yesterday against content hash 69b5ea67f812, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

superdocs 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.

not paste the curl command back to the user expecting them to run it
skills/superdocs/SKILL.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SuperDocs Skill

A skill for AI agents (Claude Code, Cursor, Claude Desktop, Windsurf, VS Code Copilot, etc.) connecting to the SuperDocs MCP server at https://api.superdocs.app/mcp/.

This skill encodes the workflows that work well with SuperDocs and the pitfalls to avoid. Read the section that matches what the user is asking for; you don't need the whole file.


Setup check — run this ONCE at session start

Before reading the rest of this skill, check whether SuperDocs MCP tools are accessible. Look for tools prefixed with mcp__superdocs__, mcp__plugin_superdocs_superdocs__, or just superdocs__ (depending on your client).

If yes → MCP server is connected. Skip to "When to use" below.

If no → MCP server isn't connected yet. Add it now using the command appropriate for your tool. You only need to do this ONCE — after the first add, the server stays connected for the session and future sessions. Do NOT re-run this check on every tool call; if you've already verified MCP is accessible OR have already added it this session, skip directly to using the tools.

Tool Command
Claude Code claude mcp add --transport http superdocs https://api.superdocs.app/mcp/ --header "Authorization: Bearer sk_YOUR_KEY" (or just install the plugin which bundles MCP + skill + 4 prompts: claude plugin marketplace add superdocsapp/superdocs-plugin && claude plugin install superdocs@superdocs-plugin)
Cursor Add to .cursor/mcp.json: {"mcpServers":{"superdocs":{"url":"https://api.superdocs.app/mcp/","headers":{"Authorization":"Bearer sk_YOUR_KEY"}}}}
VS Code Add to workspace .vscode/mcp.json (or the user-level mcp.json via MCP: Open User Configuration): {"servers":{"superdocs":{"type":"http","url":"https://api.superdocs.app/mcp/","headers":{"Authorization":"Bearer sk_YOUR_KEY"}}}}
Cline / Continue / Goose / Gemini CLI / others See client-specific docs at https://docs.superdocs.app/mcp/setup — config file format varies.

Read the full file on GitHub · 399 lines

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 · 399 lines · 105 tokens per session scan A 69b5ea67f812

Subscribe to this mod's changes

superdocs is a skill published in the GitHub repository superdocsapp/superdocs-plugin (1 stars, last pushed 10d ago), licensed MIT. It adds 105 tokens to every session and 5,455 once invoked, about $0.0005 per session on Opus 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.

Related

Other skills, from other repositories

docx-mcp

Use when creating or editing Word (.docx) documents — from scratch, from markdown, or from templates. Triggers: creating documents, converting markdown to docx, reviewing contracts, marking up reports, adding revision comments, validating document structure, removing watermarks, auditing OOXML integrity, bulk text…

SecurityRonin/docx-mcp · 89 tokens

office-artifacts

Use when creating, opening, reading, or editing Office artifacts such as LibreOffice-native ODT/ODS/ODP files and compatibility DOCX/XLSX/PPTX files with the officeartifact tool.

agent0ai/agent-zero · 47 tokens

run-tests

Run Portwood's test suites — the one-command QA harness, the anonymous-Apex e2e scripts, Apex unit tests, prettier, and Code Analyzer. Use before opening a PR, when verifying a fix, or when a test fails and you need to know whether it's your change or the harness.

Portwood-Global-Solutions/Portwood · 64 tokens

triage-report

Decide whether a Portwood bug report is a real code defect or a template-authoring problem, before any code is written. Use when a user reports "the PDF looks wrong", a merge tag didn't resolve, an image is missing, a chart is distorted, or output doesn't match the template. Most reports are template issues.

Portwood-Global-Solutions/Portwood · 70 tokens

dev-setup

Get from a fresh clone of Portwood to a working, fully-tested Salesforce org. Use when setting up a development environment, creating a scratch org, onboarding to the project, or when org setup fails with permission or "No such column" errors.

Portwood-Global-Solutions/Portwood · 54 tokens

writer-documents

Use when creating, opening, or editing LibreOffice Writer ODT documents, or DOCX documents only when Microsoft Word compatibility is explicitly required.

agent0ai/agent-zero · 32 tokens