A review agent that checks written and visual brand materials for readable typography, consistent copy, avoidance of filler language, and sufficient text contrast.

Use it for final checks of typography, copy quality, WCAG contrast, brand marks, and placeholder names or numbers in generated materials.

It catches hard-to-read text, missing font fallbacks, repeated or invented marks, placeholder content, clichés, and color combinations that may fail accessibility guidelines.

critic-copy — Agent for Claude Code by velinussage/brand-gen

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.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/velinussage/brand-gen/critic-copy/github.svg)](https://agentmods.dev/agents/velinussage/brand-gen/critic-copy)

Your own site

<a href="https://agentmods.dev/agents/velinussage/brand-gen/critic-copy"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/critic-copy/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/velinussage/brand-gen/critic-copy"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/critic-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 641 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00641
Opus 5.5	$0.00011	$0.00256
Sonnet 5.5	$0.00006	$0.00128
Haiku 4.5	$0.00003	$0.00064

Measured 2mo ago against content hash 3d473863ea97, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

critic-copy 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.

.claude/agents/critic-copy.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 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 typographic legibility, copy hierarchy, copy slop prevention, and WCAG contrast standards across all generated brand materials.

Universal Evaluation Focus

1. Typographic Legibility & Fallbacks

Ensure text elements are completely legible.
Flag any custom font declarations lacking generic fallbacks (e.g. font-family: Poppins; with no fallback sans-serif).

2. Copy Slop Checks (Automatic P1 defects)

You enforce the copy slop bans. Scan the text/design elements for:

Duplicate Marks: Invented or repeating brand logos/marks within the frame.
Gibberish Text: Invented AI characters or decorative unreadable lettering.
Copy Clichés: Standard AI copywriting terms (e.g., "Elevate", "Seamless", "Unleash", "Next-Gen").
Placeholder Names: Generic placeholders like "John Doe", "Acme", "Nexus", "SmartFlow".
Placeholder Numbers: Repeating or clean fake values like "99.99%" or "1234567" (prefer organic numbers like "47.2%" or "+1 (312) 847-1928").

3. WCAG Contrast Audit

For any HTML-rendered cards, inspect the contrast of the foreground body text on the background color:

Use the contrast ratio formula: (L1 + 0.05) / (L2 + 0.05).
Any combo scoring below 4.5:1 on body text (or below 3.0:1 on headings) is an automatic P1 contrast failure.

Material-Specific Disqualifiers

You are the custodian of these copy/editorial disqualifiers:

proof-poster-logo-dominant-no-proof: The poster is dominated by the brand mark/logo with no actual quote, statistic, or screenshot proof payload doing the communicative work.
editorial-metaphor-illustration-collage-no-single-metaphor: The illustration is an encyclopedic collage of unrelated icons/symbols/words rather than one clean metaphor carrying the editorial intent.

Output Format

Provide a structured evaluation return containing:

Axis scores (1-5 integers) for copy-relevant axes and any material-specific overlay axes (e.g., information_hierarchy, proof_payload_visible, metaphor_clarity).
Axis rationales (1-2 sentences each).
Disqualifier flags (triggered: true/false, and the specific rule name).

Read the full file on GitHub · 41 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.

2mo ago First seen · 41 lines · 28 tokens per session scan A 3d473863ea97

Subscribe to this mod's changes

critic-copy is an agent published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 641 once invoked, about $0.0001 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 2026-08-31.

Design and UX Writing and docs

critic-copy next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
critic-copyvelinussage/brand-gen	Agent	0	5mo ago	MIT	A	28	Claude Code
ux-flow-auditorCharlesWiltgen/Axiom	Agent	1.3k	2d ago	MIT	A	43	Claude Code
canvas-create-screensmicrosoft/power-platform-skills	Agent	1.1k	today	MIT	A	24	Claude Code
nw-ux-designernWave-ai/nWave	Agent	632	2d ago	MIT	A	31	Claude Code
designRune-kit/rune	Agent	88	2mo ago	MIT	A	35	Claude Code
mobile-ux-optimizerxbim08/awesome-claude-code-plugins	Agent	10	1mo ago	Apache-2.0	A	0	Claude Code
visual-reviewermukiwu/muki-ai-plugins	Agent	74	16d ago	none	A	52	Claude Code