metis: Command for Claude Code

.claude/commands/i-polish.md

i-polish is a command for Claude Code from terrene-foundation/metis. It costs 0 tokens per session (1,137 once invoked), scanned A, a copy of i-polish, Apache-2.0.

A visual refinement command for fixing design problems in a web page or interface component. It works through typography, color, spacing, interaction, motion, and other visual-quality areas, usually using an earlier audit.

In plain words
What is it for?
Use it to refine a page or component, focus on areas such as typography, color, or motion, and prioritize fixes from an interface audit.
Why use it?
It turns visual review findings into concrete changes instead of leaving aesthetic problems as a list of observations.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths.

This is terrene-foundation/metis's own configuration. It tells Claude Code how to work on metis 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 metis configures →

Reuse

Borrowing it

Nothing to install: this file belongs to terrene-foundation/metis. 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/terrene-foundation/metis/main/.claude/commands/i-polish.md
Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/metis

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 i-polish

README.md
[![agentmods](https://agentmods.dev/badge/commands/terrene-foundation/metis/i-polish/github.svg)](https://agentmods.dev/commands/terrene-foundation/metis/i-polish)
Your own site
<a href="https://agentmods.dev/commands/terrene-foundation/metis/i-polish"><img src="https://agentmods.dev/badge/commands/terrene-foundation/metis/i-polish/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 i-polish

Your own site · 80×15
<a href="https://agentmods.dev/commands/terrene-foundation/metis/i-polish"><img src="https://agentmods.dev/badge/commands/terrene-foundation/metis/i-polish.svg" alt="Reviewed on agentmods" width="80" 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 1,137 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 95% copy Near-identical to another mod 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 $0.01137
Opus 5 $0.00000 $0.00568
Sonnet 5 $0.00000 $0.00227
Haiku 4.5 $0.00000 $0.00114

Measured 9d ago against content hash cdab0cd0ff11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

i-polish 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 9d 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.

Origin

This is a copy

95% identical to i-polish — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/i-polish.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/i-polish - Visual Refinement Workflow

Purpose

Systematically fix aesthetic and visual quality issues identified by /i-audit. Takes audit findings in dimensions 1-7 and applies concrete fixes to typography, color, spacing, interaction, and motion.

Part of the Impeccable pipeline: /i-audit (diagnose) → /i-polish (refine) → /i-harden (fortify)

Usage

Command Action
/i-polish Full visual refinement pass on current file/component
/i-polish $ARGUMENTS Focused refinement on a specific area (e.g., typography, color, motion)

Refinement Process

Step 1: Context Gathering (Mandatory)

Before refining, gather:

  1. What framework? (React, Flutter, vanilla HTML/CSS)
  2. What component/page? (Read the target files)
  3. Existing design system? (Check for design tokens, theme files)
  4. Audit results? (Check if /i-audit was run — use those scores to prioritize)

If no audit exists, run /i-audit first to establish a baseline.

Step 2: Systematic Refinement (7 Areas)

Work through each area, prioritizing by audit score (lowest scores first):

1. Visual Hierarchy

  • Apply size/weight/position formula: primary > secondary > tertiary
  • Ensure important elements draw attention first
  • Fix competing focal points

2. Information Architecture

  • Apply 70/30 rule (core content vs. supporting)
  • Implement progressive disclosure for complexity
  • Group related elements logically

3. Typography

  • Establish modular type scale (e.g., 1.25 ratio: 12, 15, 19, 24, 30, 37)
  • Create weight contrast (not font-weight: 600 on everything)
  • Optimize line-height per context (headings: 1.1-1.3, body: 1.5-1.7)
  • Set measure to 45-75 characters for readability

4. Color & Contrast

  • Apply semantic color usage (meaning, not decoration)
  • Verify WCAG AA contrast ratios (4.5:1 text, 3:1 large text)
  • Remove decorative gradients and random accent colors
  • Establish intentional palette with purpose for each color

Read the full file on GitHub · 137 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. 9d ago First seen · 137 lines · 0 tokens per session scan A cdab0cd0ff11

Subscribe to this mod's changes

i-polish is a command published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,137 tokens. A static security scan graded it A with 0 findings. It is 95% identical to i-polish, differing in 5 lines, and is treated as a copy.