Borrowing it
Nothing to install: this file belongs to webern/mx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/webern/mx/main/.agents/skills/mx-questions/SKILL.mdgit clone --depth 1 https://github.com/webern/mxWrote 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/webern/mx/mx-questions)<a href="https://agentmods.dev/skills/webern/mx/mx-questions"><img src="https://agentmods.dev/badge/skills/webern/mx/mx-questions/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.
<a href="https://agentmods.dev/skills/webern/mx/mx-questions"><img src="https://agentmods.dev/badge/skills/webern/mx/mx-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00303 |
| Opus 5.5 | $0.00014 | $0.00121 |
| Sonnet 5.5 | $0.00007 | $0.00061 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
mx-questions 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 2mo 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.
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.
What it actually says
/mx-questions
Non-negotiable: plain chat only
Never use the AskUserQuestion tool. Never render a numbered option picker. Ask every question as
plain text in the chat, then stop and wait.
The core rule: one question per turn
Ask exactly one question, then stop and wait for the answer. Do not bundle multiple questions into one turn. The user answers one question at a time; batching forces them to scroll back and juggle context.
Wrong:
A few things to clarify:
- What's the target platform?
- Should it support offline mode?
- What's the expected user count?
Right:
What's the target platform?
(wait for answer, then next turn:)
Does it need to work offline?
Flow
- Ask one question, grounded in existing context or the optional prompt. If there's no context, open with "What would you like to work on?"
- Wait for the answer. Use it to shape the next question.
- Repeat until the user says to stop or you have no more questions.
- When they stop, produce a plan summarizing their answers.
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.
- 2mo ago First seen · 44 lines · 36 tokens per session scan A b029bc748ebe
mx-questions is a skill published in the GitHub repository webern/mx (93 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 303 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
score-composer
Compose original piano, chamber, and orchestral works as a score canon (compact DSL, MusicXML, MIDI, ABC, piano sheets, guitar tabs), then route to preview audio, Lyria 3, Suno, or live playing. Use for compose, sheet music, tabs, orchestra, piano works, notation, MusicXML.
songwriting-and-ai-music
Songwriting craft and Suno AI music prompts.
cli-anything-musescore
CLI for music notation — transpose, export PDF/audio/MIDI, extract parts, manage instruments.
social-spotify-card
A Spotify-style now-playing card that shows cover art, a title, artist or subtitle, playback progress, and music controls. It can be sized for video overlays or a website hero section.
composing-with-pytheory
Compose music with PyTheory — chord progressions, melodies, basslines, drum grooves, and full multi-part arrangements written in pure Python and rendered to audio or MIDI. Use whenever the user wants to write, sketch, generate, or arrange music — "write me a bossa nova in G minor", "make a four-chord pop loop", "lay…
keys-and-harmony-with-pytheory
Analyze and generate keys and chord progressions with PyTheory. Use when the user asks what key some notes are in, the diatonic chords of a key, a Roman- numeral analysis of a progression, what chord comes next, secondary dominants, borrowed chords, chords grouped by function (tonic/subdominant/dominant), the…