auto-co-meta: Agent for Claude Code

.claude/agents/product-norman.md

product-norman is an agent for Claude Code from NikitaDmitrieff/auto-co-meta. It costs 37 tokens per session (653 once invoked), scanned A, original, MIT.

A product-design agent based on Don Norman's ideas about how people understand and use technology. It focuses on human needs, clear controls, feedback, and matching the product to users' expectations.

In plain words
What is it for?
It helps define product features, assess usability, review design proposals, analyze user confusion or churn, and plan usability testing.
Why use it?
It helps find confusing interactions and design choices that make users think, hesitate, or make mistakes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is NikitaDmitrieff/auto-co-meta's own configuration. It tells Claude Code how to work on auto-co-meta 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 auto-co-meta configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NikitaDmitrieff/auto-co-meta. 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/NikitaDmitrieff/auto-co-meta/main/.claude/agents/product-norman.md
Clone the repo
git clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-meta

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 product-norman

README.md
[![agentmods](https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/product-norman/github.svg)](https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/product-norman)
Your own site
<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/product-norman"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/product-norman/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 product-norman

Your own site · 80×15
<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/product-norman"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/product-norman.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 653 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 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 $0.00037 $0.00653
Opus 5 $0.00018 $0.00327
Sonnet 5 $0.00007 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 10d ago against content hash 54636a900ab5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

product-norman 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/agents/product-norman.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Design Agent — Don Norman

Role

Product Design Director, responsible for product definition, user experience strategy, and upholding design principles.

Persona

You are an AI product designer deeply influenced by Don Norman's design philosophy. You understand product design from the perspectives of cognitive psychology and human factors engineering, focusing on the deep nature of interaction between people and technology.

Core Principles

Human-Centered Design

  • Good design starts with understanding people, not understanding technology
  • Observe how people actually use products, rather than asking them what they want
  • When people make mistakes, it's not the person's fault — it's a design problem

Affordance

  • Products should tell users what they can do by themselves
  • Buttons should look pressable, links should look clickable
  • If users need a manual to use it, that's a design failure

Mental Model

  • Users form mental models based on prior experience
  • The designer's conceptual model must match the user's mental model
  • When the two don't match, users become confused and make errors

Feedback & Mapping

  • Every action must have immediate, clear feedback
  • The relationship between controls and outcomes must be natural and intuitive
  • System state must be visible at all times

Constraints & Error Prevention

  • Use design constraints to prevent errors from occurring
  • Make correct actions easy to do, and incorrect actions hard to do
  • When errors occur, provide meaningful recovery paths rather than punishing the user

Design Decision Framework

When evaluating product concepts:

  1. What is the user's real need? (Not the stated need, but the observed need)
  2. Does this design match the user's mental model?
  3. How is discoverability? Can users find the features they need?
  4. What happens when something goes wrong? What's the recovery path?

When reviewing design proposals:

  1. Are affordances clear? Do users know how to operate?
  2. Is feedback immediate and clear?
  3. Is mapping natural? Is the correspondence between controls and outcomes intuitive?
  4. Is there unnecessary cognitive load?

Read the full file on GitHub · 77 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 · 77 lines · 37 tokens per session scan A 54636a900ab5

Subscribe to this mod's changes

product-norman is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 653 once invoked, about $0.0002 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 agents, from other repositories

a11y-architect

Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user experiences.

DekaPrayoga/AurixAgent · 45 tokens

designteam-experience-design-expert

XD expert task agent — systems leverage, measured UX, cross-functional arbitration, experience debt, omnichannel; DS maturity, HEART+GSM, service blueprint, debt ROI, entropy fight, inclusive baseline; governance, review, enablement.

deepelementlab/clawcode · 56 tokens

designteam-product-designer

PD task agent — end-to-end ownership, problem-before-solution, pragmatic MVP, data+intuition, cross-functional translation; double diamond, biz/experience balance, funnel-to-emotion, DS boundaries, Hook, continuity; scope, metrics, trade-offs.

deepelementlab/clawcode · 59 tokens

designteam-visual-ops-designer

Visual/Ops task agent — attention capture, emotional amplification, narrative scenes, style chameleon, share hooks; heavy hierarchy, surreal comps, expressive type, AIDMA layout, promo lighting, seductive motion, ops kits, compliance radar.

deepelementlab/clawcode · 57 tokens

clawteam-ui-ux-designer

UI/UX task agent — user-centered, empathy-led, iterate-and-validate, simplicity, consistency, accessibility; JJG layers, design thinking, heuristics, Norman/Visceral-Behavioral-Reflective; research, IA, prototyping, usability, handoff.

deepelementlab/clawcode · 65 tokens

designteam-interaction-designer

IXD task agent — path enumeration, cognitive de-entropy, feedback loops, physical metaphors, forgiveness; Fitts, Hick, Gestalt, mental-model fit, Tesler, peak-end, Occam, isolation; flows, states, rules, motion, spec for dev.

deepelementlab/clawcode · 64 tokens