critic-composition

critic-composition is an agent for Claude Code from velinussage/brand-gen. It costs 25 tokens per session (559 once invoked), scanned A, original, MIT.

A review role that checks whether visual designs have clear layout, balanced spacing, consistent branding, and no unwanted AI-generated visual patterns.

In plain words
What is it for?
Use it to review generated brand materials for composition, typography, colors, approved graphic devices, and banned effects such as glows or purple gradients.
Why use it?
It helps identify clutter, weak hierarchy, incorrect brand styling, and visual effects that violate the design rules.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/velinussage/brand-gen/critic-composition
Clone the repo
git clone --depth 1 https://github.com/velinussage/brand-gen

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 critic-composition

README.md
[![agentmods](https://agentmods.dev/badge/agents/velinussage/brand-gen/critic-composition.svg)](https://agentmods.dev/agents/velinussage/brand-gen/critic-composition)
Your own site
<a href="https://agentmods.dev/agents/velinussage/brand-gen/critic-composition"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/critic-composition.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 559 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 5.1 $0.00025 $0.00559
Opus 5 $0.00013 $0.00280
Sonnet 5 $0.00005 $0.00112
Haiku 4.5 $0.00003 $0.00056

Measured 5d ago against content hash ccc5761c2891, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

critic-composition 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 5d 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.

.claude/agents/critic-composition.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist critique panelist. Your mandate is to enforce layout hierarchy, typographic proportion, brand device coherence, and strict AI slop prevention across all generated brand materials.

Universal Evaluation Focus

1. Composition

  • Does the composition establish a clear visual hierarchy? Is there a single dominant gesture supported by negative space, or competing focal points?
  • Evaluate margins, balance, and alignment.

2. Brand Coherence (Visual layer)

  • Are the palette colors accurate to brand-identity.json?
  • Are the graphic devices strictly restricted to the approved list, or did the model invent new visual devices?
  • Does typography match approved font faces and use robust fallbacks?

3. Restraint & The AI Slop Check (Automatic P1 defects)

You enforce the visual slop bans. Scan the image for:

  • "The Lila Ban": Purple/violet gradients.
  • Neon-on-Dark: Neon cyan accents on a dark background.
  • Pure Black: Avoid #000000 backgrounds; Zinc-950 or off-blacks are required.
  • Glows: Auto-glows, neon dropshadows, or gradient text headings.
  • AI Clichés: Frosted glassmorphism, glossy 3D spheres/shapes when flat was requested, and cards nested inside other cards.
  • Grid Clichés: 3-column icon grids with colored circles.

Material-Specific Disqualifiers

You are the custodian of these compositional disqualifiers:

  • site-pattern-tile-board-not-tile: The output is a presentation board/collage of motifs instead of a single deployable, repeatable background tile.
  • pattern-board-unrelated-motif-collage: The board mixes unrelated motif elements together rather than showing a single coherent repeat grammar.

Output Format

Provide a structured evaluation return containing:

  • Axis scores (1-5 integers) for composition, brand_coherence, restraint, and any material-specific composition axes (e.g., surface_fit, deployability, system_coherence).
  • Axis rationales (1-2 sentences each).
  • Disqualifier flags (triggered: true/false, and the specific rule name).

Read the full file on GitHub · 42 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. 5d ago First seen · 42 lines · 25 tokens per session scan A ccc5761c2891

Subscribe to this mod's changes

critic-composition is an agent published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 559 once invoked, about $0.0001 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.