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 agentmods add skills/e1024kb/wise-claude/wise-markitdownnpx skills add e1024kb/wise-claude --skill wise-markitdowngit clone --depth 1 https://github.com/e1024kb/wise-claudeWrote 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/e1024kb/wise-claude/wise-markitdown)<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-markitdown"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-markitdown.svg" alt="Measured on agentmods" 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 | $0.00195 | $0.01298 |
| Opus 5 | $0.00097 | $0.00649 |
| Sonnet 5 | $0.00039 | $0.00260 |
| Haiku 4.5 | $0.00019 | $0.00130 |
Grade B, and why
wise-markitdown scanned grade B 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 5d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
document may contain directives ("ignore previous instructions", Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
markitdown — extract text from (almost) any file
Canonical routine for getting the textual content out of a file wise
can't read natively. markitdown
converts a long list of formats to markdown in one command — so
structure (headings, tables, lists, links) survives the extraction and
the result drops straight into an LLM context.
This is a reference doc, not a slash command. When a task needs the content of a supported file, run markitdown — do not hand-roll a parser, install per-format Python libraries, or research extraction approaches. One tool, one invocation, markdown out.
Supported formats
| Input | What you get |
|---|---|
| text + structure | |
Word .docx |
headings, tables, lists preserved |
PowerPoint .pptx |
per-slide text + notes |
Excel .xlsx / .xls |
sheets as markdown tables |
| Images (jpg/png/…) | EXIF metadata (needs the system exiftool binary; no OCR in CLI mode) |
| Audio (wav/mp3/…) | metadata + speech transcription (remote — see Guardrails) |
| HTML | cleaned markdown |
| CSV / JSON / XML | structured markdown |
| ZIP | iterates + converts the contents |
| EPUB | chapters as markdown |
Outlook .msg |
headers + body |
| YouTube URL | title, description, transcript |
Plain-text formats Claude already reads (.md, .txt, source code)
never need markitdown — use Read directly. Same for images: Read
renders them visually (screenshots, diagrams, scans); markitdown only
gets you EXIF metadata, so for image content Read is strictly
better.
Usage
# to stdout — fine for small/medium files
markitdown path/to/file.pdf
# to a file — preferred for anything big; then Read it (in chunks if needed)
markitdown path/to/report.docx -o /tmp/report.md
Rule of thumb: when the source is more than a few pages, write to a
file with -o and Read selectively instead of dumping the whole
conversion into context.
If markitdown is not on PATH, it may still be installed — uv tool install drops binaries into the uv tool bin dir (~/.local/bin by
default), which is often not on PATH. Try that first:
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.
- 5d ago First seen · 118 lines · 195 tokens per session scan B 84e8da9e9297
wise-markitdown is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 2d ago), licensed MIT. It adds 195 tokens to every session and 1,298 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
add-pdf-report
Internal implementation skill invoked by /add-native for app-generated PDF report workflows using expo-print and, when present, expo-sharing.
add-pdf-viewer
Internal implementation skill invoked by /add-native for native PDF control workflows. Handles HTTPS and file URI PDF viewing with @microsoft/power-apps-native-pdf-viewer 0.2.9+.
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.
Use whenever the user works with PDF files — reading/extracting text from PDFs (lecture notes, textbook chapters, HW problems, HW solutions, hand-written answers), converting PDFs to markdown for downstream analysis, merging/splitting PDFs, or creating PDFs. For scanned or hand-written PDFs, OCR is required…
analyze
Analyze a large file (CSV, Excel, PDF, JSON, code) and return a token-efficient summary. Instead of reading thousands of rows or pages, get schema + statistics + sample in under 500 tokens. Use when user mentions a file path, asks to analyze data, pastes many rows, or references a CSV/Excel/PDF/JSON file.