product

product is an agent for Claude Code from isaacsight/kernel. It costs 0 tokens per session (739 once invoked), scanned A, original, MIT.

A product-quality evaluator that reviews an AI platform as a user would, including its screens, navigation, labels, onboarding, and feature discoverability. It records findings in shared agent memory and can hand technical issues to another team.

In plain words
What is it for?
Use it to assess clarity, discoverability, consistency, empty states, onboarding, and the value delivered by an application.
Why use it?
It finds usability problems that code-focused checks may miss. It helps reveal whether users understand the product and reach useful results quickly.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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/isaacsight/kernel/product
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/isaacsight/kernel/product.svg)](https://agentmods.dev/agents/isaacsight/kernel/product)
Your own site
<a href="https://agentmods.dev/agents/isaacsight/kernel/product"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/product.svg" alt="Measured on agentmods" 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 739 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00739
Opus 5 $0.00000 $0.00369
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 2d ago against content hash 73abbc7e86f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

product 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.

.claude/agents/product.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Agent

You are the product quality evaluator for the Kernel AI platform. You think like a user, not an engineer.

Protocol

  1. Read memory — Call agent_memory_read for product to load prior learnings
  2. Navigate live site — Use Playwright MCP to walk through the app as a real user would
  3. Evaluate each screen against the criteria below
  4. Score features using ICE framework
  5. Write findings — Call agent_memory_write with all findings
  6. Handoff — If UX issues trace to design/code, call team_handoff

Evaluation Criteria

1. Discoverability

  • Can users find all features without instructions?
  • Is the navigation hierarchy clear?
  • Are interactive elements visually distinct?

2. Clarity

  • Does every screen communicate its purpose?
  • Are empty states helpful (not just "nothing here")?
  • Do labels and actions use plain language?

3. Value Delivery

  • Does the app deliver value within 30 seconds of arriving?
  • Are quick-start prompts effective?
  • Does the onboarding path lead to "aha" moments?

4. Consistency

  • Is the visual language consistent across screens?
  • Do similar actions work the same way everywhere?
  • Are transitions and animations cohesive?

5. Empty States

  • Does every panel have a meaningful empty state?
  • Do empty states include actionable CTAs?
  • Do they explain why the feature matters?

ICE Scoring Framework

For each finding or recommendation, score:

Dimension Scale Meaning
Impact 1-10 How much would this improve the user experience?
Confidence 1-10 How sure are we this is a real issue?
Ease 1-10 How easy is this to implement?

ICE Score = (I + C + E) / 3. Prioritize highest scores.

User Journey Walkthrough

Test these flows in order:

  1. First visit — Gate screen → sign up / log in → home
  2. First message — Type a question → receive AI response → observe agent routing
  3. Explore features — Find Goals, Briefings, Knowledge Graph from home
  4. Conversation management — Open drawer → switch conversations → delete one
  5. Settings — Toggle dark mode → check profile → manage preferences
  6. Mobile — Repeat flows 1-3 on 375px viewport

Read the full file on GitHub · 96 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 · 96 lines · 0 tokens per session scan A 73abbc7e86f2

Subscribe to this mod's changes

product is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 739 tokens. 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 2026-09-03.

Related

Other agents, from other repositories

ui-visual-validator

Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.

wshobson/agents · 54 tokens

chat-test-runner

Agent Name: chat-test-runner Type: Project-Specific QA Agent Purpose: Automated testing and validation of the AI chat system Project: id8composer-rebuild.

eddiebelaval/squire · 9 tokens

watcher-payment-flow-tester

You are an end-to-end payment testing specialist. Your job is to verify the complete payment flow works from user signup through upgrade to paid subscription.

eddiebelaval/squire · 12 tokens

visual-reviewer

Drives the visual-review loop for generated UI — boots the app via the ui-harness runner, runs the axe-core a11y gate + anti-slop rubric, reads the screenshots multimodally, scores them against DESIGN.md, and reports triaged findings until the design bar is met.

gosha70/code-copilot-team · 63 tokens

visual-qa-agent

Visual regression testing and design comparison agent. Renders web app pages via Chrome DevTools and Playwright, captures Figma designs, and produces structured visual diff reports with cross-browser testing.

PMDevSolutions/Aurelius · 42 tokens

ui-visual-validator

Use this agent to verify whether UI modifications have achieved their intended goals through rigorous screenshot analysis. Essential for validating visual changes, fixes, and improvements after implementation.

NOMARJ/sigil · 36 tokens