mx: Skill for Claude Code

.agents/skills/mx-grill-me/SKILL.md

mx-grill-me is a skill for Claude Code from webern/mx. It costs 50 tokens per session (162 once invoked), scanned A, original, MIT.

A structured interview guide for examining a plan or design through its open decisions and dependencies. It asks one question at a time and recommends an answer while using the codebase when it can answer a question.

In plain words
What is it for?
Use it when you want a plan stress-tested, need to resolve design branches, or want a detailed design interview before building.
Why use it?
It exposes unclear assumptions and unresolved choices before implementation. This helps turn a broad design into shared, specific understanding.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is webern/mx's own configuration. It tells Claude Code how to work on mx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mx configures →

View source ↗ webern/mx
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/webern/mx/main/.agents/skills/mx-grill-me/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/webern/mx

Made for: Claude Code.

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.

agentmods badge for mx-grill-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/webern/mx/mx-grill-me/github.svg)](https://agentmods.dev/skills/webern/mx/mx-grill-me)
Your own site
<a href="https://agentmods.dev/skills/webern/mx/mx-grill-me"><img src="https://agentmods.dev/badge/skills/webern/mx/mx-grill-me/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.

agentmods 80×15 button for mx-grill-me

Your own site · 80×15
<a href="https://agentmods.dev/skills/webern/mx/mx-grill-me"><img src="https://agentmods.dev/badge/skills/webern/mx/mx-grill-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 162 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00050 $0.00162
Opus 5.5 $0.00020 $0.00065
Sonnet 5.5 $0.00010 $0.00032
Haiku 4.5 $0.00005 $0.00016

Measured 2mo ago against content hash c8eb62b20f68, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mx-grill-me 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.

.agents/skills/mx-grill-me/SKILL.md · 20 lines

What it actually says

Interview me about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree resolving dependencies between decisions one by one.

If a question can be answered by exploring the codebase, explore the codebase instead.

For each question, provide your recommended answer.

Use the /mx-questions skill to avoid sending more than one question at once.

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. 2mo ago First seen · 20 lines · 50 tokens per session scan A c8eb62b20f68

Subscribe to this mod's changes

mx-grill-me is a skill published in the GitHub repository webern/mx (93 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 162 once invoked, about $0.0002 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.

Related

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.

frankxai/agentic-music-producer-os · 72 tokens

songwriting-and-ai-music

Songwriting craft and Suno AI music prompts.

NousResearch/hermes-agent · 17 tokens

cli-anything-musescore

CLI for music notation — transpose, export PDF/audio/MIDI, extract parts, manage instruments.

HKUDS/CLI-Anything · 25 tokens

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.

nexu-io/html-anything · 38 tokens

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…

kennethreitz/pytheory · 138 tokens

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…

kennethreitz/pytheory · 132 tokens