pixel-council: Instructions file for Claude Code

CLAUDE.md

pixel-council CLAUDE.md is an instructions file for Claude Code from blinkz-ai/pixel-council. It costs 1,562 tokens per session, scanned A, original, MIT.

A Claude Code plugin for building and reviewing user interfaces against published design guidelines from Google, Apple, and IBM. It includes references from Material Design 3, Apple’s Human Interface Guidelines, and IBM Carbon.

In plain words
What is it for?
Use it to create UI code, review existing interfaces, and validate details such as colors, typography, icons, spacing, and interaction patterns.
Why use it?
It gives the agent concrete design specifications to check against instead of relying only on general visual judgment. This helps keep interface code consistent with established systems.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is blinkz-ai/pixel-council's own configuration. It tells Claude Code how to work on pixel-council itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pixel-council configures →

Reuse

Borrowing it

Nothing to install: this file belongs to blinkz-ai/pixel-council. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/blinkz-ai/pixel-council/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/blinkz-ai/pixel-council

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 pixel-council CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/blinkz-ai/pixel-council/claude-md/github.svg)](https://agentmods.dev/instructions/blinkz-ai/pixel-council/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/blinkz-ai/pixel-council/claude-md"><img src="https://agentmods.dev/badge/instructions/blinkz-ai/pixel-council/claude-md/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.

agentmods 80×15 button for pixel-council CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/blinkz-ai/pixel-council/claude-md"><img src="https://agentmods.dev/badge/instructions/blinkz-ai/pixel-council/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,562 This file is loaded in full into every session.
When invoked 1,562 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01562 $0.01562
Opus 5 $0.00781 $0.00781
Sonnet 5 $0.00312 $0.00312
Haiku 4.5 $0.00156 $0.00156

Measured 10d ago against content hash 8f6dfc889d70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pixel-council CLAUDE.md 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 10d 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.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pixel Council

A Claude Code plugin that produces production-grade UI by reading real design system specifications from Google Material Design 3, Apple HIG, and IBM Carbon Design System.

Project Structure

pixel-council/
├── .claude-plugin/
│   └── plugin.json                    # Plugin manifest
├── agents/
│   └── ui-reviewer.md                 # Reviews UI code against reference specs
├── scripts/
│   └── validate-carbon-refs.sh        # Validates ibm/ reference files (frontmatter, sections, hex, line counts)
├── docs/superpowers/
│   ├── specs/2026-04-25-carbon-integration-design.md      # Design spec for the Carbon integration
│   └── plans/2026-04-25-carbon-integration.md             # Implementation plan (8 phases)
├── skills/
│   └── pixel-council/
│       ├── SKILL.md                   # The skill prompt (builds UI from specs)
│       └── references/                # 129 reference files
│           ├── google/                # Google Material Design 3
│           │   ├── overview.md        # Full M3 token system (34 colors, typography, elevation, motion)
│           │   ├── icons.md           # Material Symbols CDN, variable axes, 20 SVG fallbacks
│           │   ├── editorial-type.md  # Marketing type scale 88px→11px
│           │   ├── page-patterns.md   # Section patterns, 12-col grid, tonal elevation
│           │   └── components/        # 32 per-component specs with complete HTML+CSS
│           ├── apple/                 # Apple HIG
│           │   ├── overview.md        # System colors, SF Pro, Liquid Glass, shadows
│           │   ├── icons.md           # SF Symbols SVGs, stroke specs, 20-icon library
│           │   ├── editorial-type.md  # Marketing type scale 96px→12px
│           │   ├── page-patterns.md   # apple.com section patterns, hero layouts
│           │   └── components/        # 33 per-component specs with complete HTML+CSS
│           ├── ibm/                   # IBM Carbon Design System (Apache 2.0)
│           │   ├── overview.md        # 4 themes (White/G10/G90/G100), 122 hex tokens, IBM Plex, motion, 2x grid, AI tokens, Shape rules (border-radius: 0)
│           │   ├── icons.md           # @carbon/icons (web-redistributable), 24 inlined SVGs, 4 sizes (16/20/24/32)
│           │   ├── pictograms.md      # @carbon/pictograms (Carbon-only) — 12 inlined editorial illustrations
│           │   ├── editorial-type.md  # Expressive + Fluid + Display scale (42-92px responsive)
│           │   ├── page-patterns.md   # IBM.com marketing + UIShell dashboards + AI surface + chat shell patterns
│           │   └── components/        # 38 component specs — each embeds verbatim React + WC Storybook source code
│           └── blended/               # Best-of-both defaults (DEFAULT)
│               ├── design-principles.md
│               └── components/        # 12 blended specs with complete HTML+CSS
├── LICENSE
├── README.md
└── CLAUDE.md                          # This file

Read the full file on GitHub · 102 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. 10d ago First seen · 102 lines · 1,562 tokens per session scan A 8f6dfc889d70

Subscribe to this mod's changes

pixel-council CLAUDE.md is an instructions file published in the GitHub repository blinkz-ai/pixel-council (24 stars, last pushed 4mo ago), licensed MIT. It adds 1,562 tokens to every session, about $0.0078 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens