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.
npx agentmods add agents/velinussage/brand-gen/critic-compositiongit clone --depth 1 https://github.com/velinussage/brand-genWrote 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.
[](https://agentmods.dev/agents/velinussage/brand-gen/critic-composition)<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>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 | $0.00025 | $0.00559 |
| Opus 5 | $0.00013 | $0.00280 |
| Sonnet 5 | $0.00005 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
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.
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
#000000backgrounds; 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).
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.
- 5d ago First seen · 42 lines · 25 tokens per session scan A ccc5761c2891
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.