critique

critique is a skill for Claude Code from enjalot/moonshine. It costs 66 tokens per session (2,945 once invoked), scanned A, original, MIT.

A review guide for checking a Moonshine article against its writing, visual, and teaching standards. Moonshine articles are either project-based sites or single self-contained HTML files.

In plain words
What is it for?
Use it to identify the article format, load the matching standards, and perform an adversarial pre-publication critique.
Why use it?
It helps find unclear writing, weak explanations, visual problems, and low-quality content before publication.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the moonshine plugin — 5 skills, 1 hook shipped together

Good fit Use it to identify the article format, load the matching standards, and perform an adversarial pre-publication critique.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/enjalot/moonshine/critique
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 enjalot/moonshine --skill critique
Clone the repo
git clone --depth 1 https://github.com/enjalot/moonshine

Made for: Claude Code.

Or install moonshine, the plugin that ships this one along with the rest of its 5 skills, 1 hook.

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 critique

README.md
[![agentmods](https://agentmods.dev/badge/skills/enjalot/moonshine/critique/github.svg)](https://agentmods.dev/skills/enjalot/moonshine/critique)
Your own site
<a href="https://agentmods.dev/skills/enjalot/moonshine/critique"><img src="https://agentmods.dev/badge/skills/enjalot/moonshine/critique/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 critique

Your own site · 80×15
<a href="https://agentmods.dev/skills/enjalot/moonshine/critique"><img src="https://agentmods.dev/badge/skills/enjalot/moonshine/critique.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,945 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 $0.00066 $0.02945
Opus 5 $0.00033 $0.01473
Sonnet 5 $0.00013 $0.00589
Haiku 4.5 $0.00007 $0.00295

Measured 10d ago against content hash bc829d7dbbb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

critique 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.

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.

plugins/moonshine/skills/critique/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critique — Adversarially Review a Moonshine Article

Load the moonshine skill's reference standards, then perform an adversarial critique of the article the user names. Most moonshine articles are still projects (Vite + React + Velite); a shine article is a single self-contained HTML file. Figure out which one you're grading before you start — the standards you load and the checks you run depend on it.

Setup

  1. Identify the substrate.

    • still — a project directory: package.json + content/*.md prose + src/figures/registry.ts. This is the common case.
    • shine — a single index.html with inline JS and D3 from a CDN.
  2. Load the standards for that substrate. These are the bar you grade against; don't grade a substrate against rules you haven't read.

    • Always: ../moonshine/SKILL.md (editorial process, anti-slop, editing pass) and ../moonshine/VISUALS.md (visualization patterns; its "In a still project" preamble covers the substrate differences).
    • still also: ../moonshine/STILL.md (project structure, the three directives, figure registry, DEFAULTS/knobs, diagrams, series, publishing). Read ../moonshine/FEEDBACK.md too if the article carries a .feedback/ directory or the authorship loop is in scope.
    • shine also: ../moonshine/ARTICLE.md (single-file HTML scaffold, CSS foundation, layout, series). Do not grade a shine article against STILL.md, or a still project against ARTICLE.md's scaffold — they describe different substrates.
  3. Find the article. Anything after $critique is the path to critique. If no path is given, look under ~/.agent/moonshine/ for the most recently modified article — a still project (a directory with package.json) or a shine index.html. When it's ambiguous, ask which one.

You are a critic, not a fixer. Do not rewrite the article. Do not generate code. Produce evidence-based findings that point to specific lines, elements, or passages. Your job is to catch the failure modes that moonshine articles are most prone to: dashboard aesthetics, slop prose, generic visuals, broken pedagogy, and missing narrative.

Read the full file on GitHub · 129 lines

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. 10d ago First seen · 129 lines · 66 tokens per session scan A bc829d7dbbb9

Subscribe to this mod's changes

critique is a skill published in the GitHub repository enjalot/moonshine (52 stars, last pushed 23d ago), licensed MIT. It adds 66 tokens to every session and 2,945 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 2026-08-30.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens