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/musingfox/cc-plugins/markitdown-readnpx skills add musingfox/cc-plugins --skill markitdown-readgit clone --depth 1 https://github.com/musingfox/cc-pluginsWhat 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 | $0.00060 | $0.00599 |
| Opus 5 | $0.00030 | $0.00300 |
| Sonnet 5 | $0.00012 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
MarkItDown Read 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MarkItDown Read
Convert non-plain-text files to Markdown for reading and analysis using Microsoft's markitdown CLI.
Supported Formats
| Category | Extensions |
|---|---|
| Documents | .pdf, .docx, .pptx, .xlsx, .xls |
| Web | .html, .htm |
| Images | .jpg, .jpeg, .png, .gif, .bmp, .tiff, .webp |
| Audio | .mp3, .wav, .m4a, .ogg, .flac |
| Data | .csv, .json, .xml |
| Other | .epub, .zip |
Workflow
Step 1: Check Installation
Before converting, verify markitdown is available:
command -v markitdown
If not installed, inform the user and offer installation options:
- Recommended:
uv tool install 'markitdown[all]'(isolated install, no virtual env pollution) - Alternative:
pip install 'markitdown[all]'
Ask the user which method they prefer before installing. Do NOT install without confirmation.
Step 2: Convert and Read
Run markitdown on the target file and capture stdout:
markitdown <file-path>
The output is Markdown text printed to stdout. Read the output directly — do not save to a file unless the user explicitly asks.
Step 3: Present Content
After conversion, work with the Markdown output as if the file had been read natively:
- Answer questions about the content
- Summarize, extract, or analyze as requested
- Reference specific sections, tables, or data points
Important Notes
- For large files, the output may be extensive. Summarize first, then dive into specifics if asked.
- Image conversion requires OCR capabilities — results depend on image quality and content.
- Audio conversion requires speech recognition — results may vary by audio quality.
- If
markitdownfails on a specific file, report the error and suggest alternative approaches. - When the user asks to "read" or "open" a supported file type, prefer this skill over the Read tool for binary formats (PDF, DOCX, PPTX, XLSX, images, audio, EPUB, ZIP). For plain-text formats (HTML, CSV, JSON, XML), use this skill only when the user specifically wants Markdown conversion or when the Read tool output is insufficient.
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.
- yesterday First seen · 65 lines · 60 tokens per session scan A ecc81136d70a
MarkItDown Read is a skill published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 599 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.