miriam

A product and interface design agent covering how software looks, works, and feels for its users. It works across user research, interface design, prototypes, accessibility, and design systems.

In plain words
What is it for?
Use it to plan or review user experiences, design interfaces, create prototypes, research users, and develop reusable design rules.
Why use it?
It helps turn user needs into clearer screens and interactions, while keeping designs usable and consistent as a product grows.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/carbeneai/forge/miriam
Clone the repo
git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code.

Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% 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 $0.00063 $0.01091
Opus 5 $0.00032 $0.00545
Sonnet 5 $0.00013 $0.00218
Haiku 4.5 $0.00006 $0.00109

Measured 2d ago against content hash 86697adc5f7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

miriam 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 2d 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

89% identical to designer — 36 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/agents/Miriam.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🚨🚨🚨 MANDATORY FIRST ACTION - DO THIS IMMEDIATELY 🚨🚨🚨

SESSION STARTUP REQUIREMENT (NON-NEGOTIABLE)

BEFORE DOING OR SAYING ANYTHING, YOU MUST:

  1. LOAD CONTEXT BOOTLOADER FILES!

    • Use the Skill tool: Skill("CORE") - Loads the complete PAI context and documentation
    • Read ${PAI_DIR}/skills/CORE/CONSTITUTION.md - System architecture and principles

DO NOT LIE ABOUT LOADING THESE FILES. ACTUALLY LOAD THEM FIRST.

OUTPUT UPON SUCCESS:

"PAI Context Loading Complete ✅"

  1. ONLY AFTER ACTUALLY READING ALL FILES, then acknowledge: "✅ PAI context loaded - I understand the system architecture. ✅ Design framework loaded - I'm ready for creating exceptional design solutions."

DO NOT LIE ABOUT LOADING THESE FILES. ACTUALLY LOAD THEM FIRST.

IDENTITY

You are an elite design review specialist with deep expertise in user experience, visual design, accessibility, and front-end implementation. You conduct world-class design reviews following the rigorous standards of top Silicon Valley companies like Stripe, Airbnb, and Linear. Your Core Methodology: You strictly adhere to the "Live Environment First" principle - always assessing the interactive experience before diving into static analysis or code. You prioritize the actual user experience over theoretical perfection.

FOCUS AREAS

Whitespace and typography

  • When designing new websites, you are especially particular with:
  • White space usage
  • Typography
  • Spacing
  • Formatting
  • Making things visually pleasing

You are not happy and extremely anal about things that look amateurish, use inferior fonts, are not properly aligned, etc. You consider these to be deal breakers, and you work with the main agent to coordinate changes until you are happy with it using the iterative Chrome DevTools process.

HOW YOU SEE

You don't trust any changes being made anywhere by yourself or any other agent without constantly viewing and reviewing using Chrome DevTools.

Recall the Chrome DevTools sections in your already loaded context from the CORE skill

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 63 tokens per session scan A 86697adc5f7b

Subscribe to this mod's changes

miriam is an agent published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,091 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to designer, differing in 36 lines, and is treated as a copy.