metis: Command for Claude Code

.claude/commands/i-harden.md

i-harden is a command for Claude Code from terrene-foundation/metis. It costs 0 tokens per session (762 once invoked), scanned A, a copy of i-harden, Apache-2.0.

A command for checking frontend screens and components against difficult real-world conditions, such as long text, missing information, slow connections, multiple languages, and unusual input.

In plain words
What is it for?
Use it to review a page or component for text overflow, language expansion, network and form errors, missing data, and other edge cases.
Why use it?
It helps find layout and interaction problems that are easy to miss when testing only with ideal data and fast networks.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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-harden.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-harden

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/terrene-foundation/metis/i-harden"><img src="https://agentmods.dev/badge/commands/terrene-foundation/metis/i-harden.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 762 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 88% 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 $0.00762
Opus 5 $0.00000 $0.00381
Sonnet 5 $0.00000 $0.00152
Haiku 4.5 $0.00000 $0.00076

Measured 10d ago against content hash 07d2636d49e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

i-harden 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.

Origin

This is a copy

88% identical to i-harden — 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-harden.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/i-harden - Production Hardening for Frontend

Purpose

Prepare frontend interfaces for real-world usage by stress-testing against imperfect conditions: long text, missing data, slow networks, diverse languages, and unconventional inputs.

Adapted from Impeccable (Apache 2.0), enhanced for enterprise contexts.

Usage

Command Action
/i-harden Full production hardening audit of current file/component
/i-harden $ARGUMENTS Focused hardening on a specific area (e.g., text, i18n, errors, edge-cases)

Philosophy

"Designs that only work with perfect data aren't production-ready."

Enterprise users have long names, mixed-language content, slow connections, and unexpected input. Hardened interfaces handle all of it gracefully.

Workflow

Step 1: Load Hardening Checklist

Read skills/23-uiux-design-principles/production-hardening.md for the full 6-category checklist covering:

  1. Text & Content Resilience -- overflow, length extremes, dynamic content
  2. Internationalization -- text expansion, formatting, character encoding
  3. Error States & Recovery -- network errors, HTTP status handling, form errors
  4. Edge Cases & Boundary -- empty states, loading states, data volume, concurrency
  5. Accessibility Resilience -- zoom, keyboard nav, screen reader, touch targets
  6. Performance Under Stress -- lazy loading, virtual scrolling, debouncing

If $ARGUMENTS specifies a focus area, evaluate only that category. Otherwise, evaluate all six.

Step 2: Evaluate Current Code

For each category in scope:

  1. Read the target component/page files
  2. Check each item against the detailed checklist
  3. Note PASS, FAIL, or N/A for each item
  4. For FAILs, draft a concrete fix with code direction

Read the full file on GitHub · 94 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 · 94 lines · 0 tokens per session scan A 07d2636d49e8

Subscribe to this mod's changes

i-harden 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 762 tokens. A static security scan graded it A with 0 findings. It is 88% identical to i-harden, differing in 5 lines, and is treated as a copy.