A local document-conversion tool that converts common office files and PDFs to Markdown, and converts Markdown to styled DOCX files. DOCX, XLSX, and similar formats are common document and spreadsheet file types.

Use it for local PDF, DOCX, PPTX, XLSX, and related file conversion, or to create a styled Word document from Markdown. The output is saved on disk and its path and status are reported.

It keeps conversion outside the model conversation, so large converted documents do not need to be loaded into the agent's context. It also provides fallback conversion paths when the first converter cannot handle a file.

doc-convert — Skill for Claude Code and Codex by zwolf25/tokenminning

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.

Any agent

npx skills add zwolf25/tokenminning --skill doc-convert

Clone the repo

git clone --depth 1 https://github.com/zwolf25/tokenminning

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zwolf25/tokenminning/doc-convert/github.svg)](https://agentmods.dev/skills/zwolf25/tokenminning/doc-convert)

Your own site

<a href="https://agentmods.dev/skills/zwolf25/tokenminning/doc-convert"><img src="https://agentmods.dev/badge/skills/zwolf25/tokenminning/doc-convert/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zwolf25/tokenminning/doc-convert"><img src="https://agentmods.dev/badge/skills/zwolf25/tokenminning/doc-convert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,122 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00175	$0.01122
Opus 5	$0.00088	$0.00561
Sonnet 5	$0.00035	$0.00224
Haiku 4.5	$0.00017	$0.00112

Measured 10d ago against content hash 54097e1b2de2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-17, from the pricing page.

Security

Grade A, and why

doc-convert 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (anydoc_to_md.py, convert.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

tools/doc-convert/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

doc-convert

Local, token-free document conversion. Two directions, routed by the input file extension:

DOCX/XLSX/PPTX/RTF/ODT/ODS/ODP/EPUB/CSV/text-based PDF → Markdown — via anydoc_to_md.py (Firecrawl's AnyDoc library), run through uv run. Falls back to markitdown for anything AnyDoc doesn't cover (scanned/image-heavy PDFs, HTML, images) or if AnyDoc errors.
Markdown → styled DOCX — via convert.js, applying a style preset (default = styles/default.json).

Token rule (do not break): the conversion happens in a subprocess. Run it, then report the output path + the one-line status the tool prints. Never read the converted file back into context — a large document echoed into the chat is thousands of wasted tokens. The user asked for a file on disk, not the content in the conversation.

Step 1 — Prereq gate (offer the fallback ladder, don't dead-end)

Check what's installed before running:

→ Markdown needs uv on PATH (runs AnyDoc via uv run --with firecrawl-anydoc, auto-fetched on first use — no separate install step). Test: uv --version. For the markitdown fallback path specifically, also needs markitdown on PATH. Test: markitdown --version (or which markitdown).
Markdown → DOCX needs node on PATH (plus the global docx package). Test: node --version.

If a tool is missing, present the ladder — most-preferred first — instead of failing:

Install (primary, token-free going forward): see this tool's README.md for install commands (node/npm install -g docx, uv, uv tool install 'markitdown[all]').
Fallback (no install, costs tokens): for →MD, Read the source file yourself and write the markdown out. For MD→DOCX without Node, produce a visually-equivalent reproduction using whatever docx-writing library is available in your environment. Note to the user that this path spends tokens.

Step 2 — Run the conversion

Inputs you need: source path, output path, and (for MD→DOCX) an optional style name.

Read the full file on GitHub · 54 lines

Files

What ships with it

6 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.

10d ago First seen · 54 lines · 175 tokens per session scan A 54097e1b2de2

Subscribe to this mod's changes

doc-convert is a skill published in the GitHub repository zwolf25/tokenminning (30 stars, last pushed yesterday), licensed MIT. It adds 175 tokens to every session and 1,122 once invoked, about $0.0009 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 2026-09-07.

Documents PDF

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.

microsoft/agent-framework · 82 tokens

doc-convert

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

doc-convert

Step 1 — Prereq gate (offer the fallback ladder, don't dead-end)

Step 2 — Run the conversion

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

foundry-hosted-agent-validation

skill-doc-delivery

pdf-extract-create-workflow

document-direct-python

pdf-verification-cli

pdf-text-extraction-fallback-85d5ca