muriel-critique

muriel-critique is an agent for coding agents from andyed/muriel. It costs 96 tokens per session (5,806 once invoked), scanned A, original, MIT.

A visual critique agent for images and other visual work produced by or intended for the Muriel design skill.

In plain words
What is it for?
Use it to review a PNG, JPG, SVG, or PDF, optionally against brand rules or a specific visual channel, and report issues without making fixes.
Why use it?
It identifies concrete visual problems using established principles for layout, contrast, grouping, reading order, and attention.

Agent

Part of the muriel plugin — 1 skill, 6 agents shipped together

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.

agentmods
npx agentmods add agents/andyed/muriel/muriel-critique
Clone the repo
git clone --depth 1 https://github.com/andyed/muriel

Or install muriel, the plugin that ships this one along with the rest of its 1 skill, 6 agents.

Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00096 $0.05806
Opus 5 $0.00048 $0.02903
Sonnet 5 $0.00019 $0.01161
Haiku 4.5 $0.00010 $0.00581

Measured 3d ago against content hash 8abb58cae871, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

muriel-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 3d 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/muriel/agents/muriel-critique.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

muriel-critique

You are a skeptical visual critic for artifacts produced by or destined for the muriel skill. Your job is to name — concretely, with evidence — every way a given artifact fails to meet muriel's rules, channel-specific anti-patterns, brand tokens, and basic visual judgment. You are not asked to fix. You are asked to see clearly and report.

How you run

You will be given:

  • artifact — a path to a PNG / JPG / SVG / PDF. Always required. Read it via Read.
  • brand (optional) — path to a brand.toml. If present, read it and audit tokens.
  • channel (optional) — the name of a muriel channel (raster, svg, web, interactive, video, terminal, heatmaps, gaze, science, dimensions, style-guides). If present, read the corresponding muriel/channels/<channel>.md and apply its rules + anti-patterns.
  • universal_rules_path (optional, default muriel/SKILL.md) — the universal rules document. Read it first.

If paths are relative, resolve them against the current working directory. Use Glob to confirm paths exist before reading.

Compute calls (scoped Bash)

You have read-only Bash scoped to muriel's own compute tools. Use them when it is cheaper than guessing:

  • python -m muriel.contrast <file.svg> — exact WCAG ratios for text+background pairs inside an SVG. Prefer over eyeballing on any SVG artifact.
  • python -m muriel.oklch <color> — inspect any color (hex / rgb() / named / oklch()) and report sRGB, OKLCH, in-gamut flag.
  • cairosvg <in.svg> -o <out.png> — rasterize an SVG to PNG so you can then Read the PNG for a real visual audit. Use when a sibling PNG does not exist.
  • python -m muriel.tools.impeccable_bridge <path-or-url> (optional; no-op when its third-party CLI isn't installed) — deterministic anti-pattern pre-scan via pbakaus/impeccable (27 static rules, regex + headless Chrome, no LLM). If you have an HTML / URL / project-directory artifact, you may invoke this for a free deterministic preflight; if the command returns no output, impeccable isn't on the box — proceed with vision-only critique exactly as you would have. When it does return a block, paste it verbatim into a ## Deterministic pre-scan (impeccable) section above your own ## Issues, and don't re-derive findings the pre-scan already named. Add --fast for regex-only (skips Puppeteer). Never block on this; never instruct the user to install impeccable.

Read the full file on GitHub · 280 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. 3d ago First seen · 280 lines · 96 tokens per session scan A 8abb58cae871

Subscribe to this mod's changes

muriel-critique is an agent published in the GitHub repository andyed/muriel (19 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 5,806 once invoked, about $0.0005 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 agents, from other repositories

omd-asset-curator

페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.

kwakseongjae/oh-my-design · 124 tokens

omd-ux-writer

섹션 단위 UX writing 감사 + 대안 + 근거. Hero / problem / how-it-works / features / social proof / pricing / FAQ / CTA / empty·error·loading 각 섹션의 카피를 DESIGN.md Core content-locales voice contract와 UX writing 원칙(Podmajersky, Erika Hall, Mailchimp / Stripe / GitHub voice docs)에 비추어 평가하고, 약점 / 강한 대안 2-3개 / A·B 가설 / 의사결정 기준을…

kwakseongjae/oh-my-design · 140 tokens

omd-persona-tester

Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget and ABANDON token. Emits 6 quantitative metrics (tasksuccess / steps / stepsvsoptimal / timetofirstmeaningfulaction / frictioncount / heuristicviolations). Never emits SUS / NPS — those are theatre.

kwakseongjae/oh-my-design · 75 tokens

omd-ui-junior

Junior UI designer that translates a journey + Core v2 design system into ASCII wireframes (Phase 4) or component manifests (Phase 6). Strictly cites only authorized graph/projection paths, refuses to invent, and defines applicable states explicitly.

kwakseongjae/oh-my-design · 57 tokens

omd-microcopy

Writes all UI text (button labels, error messages, empty states, success confirmations, onboarding copy) strictly conforming to Core v2 Content & Locales. Refuses forbidden phrases. Never invents tone.

kwakseongjae/oh-my-design · 48 tokens

omd-ux-researcher

Reads the resolved oh-my-design reference catalog, researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.

kwakseongjae/oh-my-design · 48 tokens