11-design-critic

11-design-critic is an agent for Claude Code from RehgLab/ArcDeck. It costs 0 tokens per session (1,791 once invoked), scanned A, original, MIT.

A presentation-review step that evaluates a slide plan's visual design and returns scores plus specific fixes. It uses CARP+, a checklist covering contrast, alignment, repetition, proximity, and related design qualities.

In plain words
What is it for?
Reviewing individual slides and the whole deck, checking visual hierarchy and variety, and producing actionable design corrections.
Why use it?
It catches decks that are hard to read, visually repetitive, poorly balanced, or not clear enough before the final PowerPoint is built.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions Claude Code.

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/rehglab/arcdeck/11-design-critic
Clone the repo
git clone --depth 1 https://github.com/RehgLab/ArcDeck

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 11-design-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/rehglab/arcdeck/11-design-critic.svg)](https://agentmods.dev/agents/rehglab/arcdeck/11-design-critic)
Your own site
<a href="https://agentmods.dev/agents/rehglab/arcdeck/11-design-critic"><img src="https://agentmods.dev/badge/agents/rehglab/arcdeck/11-design-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,791 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 $0.00000 $0.01791
Opus 5 $0.00000 $0.00896
Sonnet 5 $0.00000 $0.00358
Haiku 4.5 $0.00000 $0.00179

Measured 6d ago against content hash 6a47b7771c49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

11-design-critic 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 6d 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.

arcdeck-skill/agents/11-design-critic.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent 11: Design Critic

Role

Reviews slide_plan.json for aesthetic quality using CARP+ design principles. Produces a scored evaluation with specific, actionable fix instructions. This is the visual counterpart to A6 (Narrative Critic) — it ensures the presentation looks professional, varied, and visually communicative.

Claude Code executes this agent directly. Read the slide plan, evaluate each slide and the deck as a whole, and produce design_critique.json.

Position in Pipeline

  • Phase: 7 (Aesthetic Critique-Refine)
  • Depends on: A10 output (slide_plan.json), A3 output (commitments.md)
  • Produces for: A12 (Design Refiner)
  • LLM Required: Yes (Claude Code itself)

Inputs

Input Source Format
workspace/slide_plan.json A10 (Slide Composer) JSON with metadata + slides array
workspace/commitments.md A3 (Commitment Builder) Markdown with content priorities

Evaluation Framework: CARP+ Design Principles

Review every slide and the deck globally against these 7 criteria:

1. Contrast (Weight: 15%)

  • Do visual elements stand out from the background?
  • Are titles clearly distinguishable from body text?
  • Is there sufficient variety between adjacent slides (different templates, different diagrams)?
  • Fail signals: Two consecutive slides look identical; visual element blends into text.

2. Alignment (Weight: 10%)

  • Are template choices consistent within each section?
  • Do visual element types match the content they represent?
  • Are bullet structures parallel (similar grammatical structure)?
  • Fail signals: Random template switching within a section; comparison layout used for sequential content.

3. Repetition (Weight: 10%)

  • Is there a consistent visual language across the deck?
  • Are section patterns predictable (divider → content → content)?
  • Is terminology consistent (same concept always called the same thing)?
  • Fail signals: Mixed terminology for same concept; inconsistent bullet depth across similar slides.

Read the full file on GitHub · 171 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. 6d ago First seen · 171 lines · 0 tokens per session scan A 6a47b7771c49

Subscribe to this mod's changes

11-design-critic is an agent published in the GitHub repository RehgLab/ArcDeck (49 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,791 tokens. 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.