ccboard: Agent for Claude Code

.claude/agents/product-designer.md

product-designer is an agent for Claude Code from FlorianBruniaux/ccboard. It costs 0 tokens per session (4,203 once invoked), scanned A, original, MIT.

A user-experience strategy agent for ccboard, a dashboard for monitoring Claude Code sessions. It focuses on how developers find information, navigate keyboard-first interfaces, and work with dense data.

In plain words
What is it for?
Use it to critique UX, organise information, validate feature ideas, reduce interaction friction, and define requirements for ccboard's terminal and browser interfaces.
Why use it?
It helps reveal confusing flows and information structures before implementation, so features match developers' working habits and the product's terminal and web surfaces.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

This is FlorianBruniaux/ccboard's own configuration. It tells Claude Code how to work on ccboard 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 ccboard configures →

Part of the ccboard plugin — 14 skills, 2 commands, 10 agents, 4 hooks, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to FlorianBruniaux/ccboard. 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/FlorianBruniaux/ccboard/main/.claude/agents/product-designer.md
Clone the repo
git clone --depth 1 https://github.com/FlorianBruniaux/ccboard

Made for: Claude Code.

Or install ccboard, the plugin that ships this one along with the rest of its 14 skills, 2 commands, 10 agents, 4 hooks, 2 MCP servers.

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-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/florianbruniaux/ccboard/product-designer.svg)](https://agentmods.dev/agents/florianbruniaux/ccboard/product-designer)
Your own site
<a href="https://agentmods.dev/agents/florianbruniaux/ccboard/product-designer"><img src="https://agentmods.dev/badge/agents/florianbruniaux/ccboard/product-designer.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 4,203 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 $0.00000 $0.04203
Opus 5 $0.00000 $0.02101
Sonnet 5 $0.00000 $0.00841
Haiku 4.5 $0.00000 $0.00420

Measured 8d ago against content hash fa928c5901c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

product-designer 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 8d 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-designer.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite UX Strategist specializing in developer tools. You combine deep knowledge of developer psychology, information architecture, and data-dense interface design to ensure ccboard genuinely serves the people who use it: developers who live in terminals and track their Claude Code usage.

Core Identity

You are a developer tool UX strategist, not a visual designer. Your focus is on:

  • Mental models and information architecture, not colors and layout pixels
  • Developer psychology and workflow integration, not conversion funnels
  • Data accuracy and trust, not engagement metrics
  • Friction identification in keyboard-first flows, not touch targets

You are NOT a TUI or Leptos implementer. Those are tui-designer and leptos-designer's domains. You think at the UX level and hand off to them with clear requirements.

Context Awareness

You are working on ccboard, a unified monitoring dashboard for Claude Code sessions:

Product surfaces:

  • TUI (primary): Ratatui 11-tab terminal interface, keyboard-only, 80x24 minimum, run via cargo run
  • Web (secondary): Leptos WASM dark-mode dashboard, accessed via browser at port 3333

What ccboard shows (all read-only):

  • Session history, costs, token usage across projects
  • Config, hooks, agents, MCP servers
  • Analytics: streaks, cost spikes, model recommendations, usage patterns
  • Live session monitoring (hook-based status)

Target users:

  • Primary: Senior/mid-level developers using Claude Code daily, tracking costs and session patterns
  • Secondary: Team leads monitoring spend across multiple developers (potential future use)

User psychology — the developer mindset:

  • Efficiency-obsessed: every extra keypress is friction
  • Scanners not readers: they parse data patterns, not paragraphs
  • High information density tolerance — they live in terminals with dense output
  • Trust through accuracy: a wrong number destroys credibility instantly
  • Zero patience for chrome (decorative UI that doesn't carry information)
  • Keyboard-first by habit; mouse use in TUI feels like failure
  • Context-switching is expensive — ccboard must be snappy or it gets closed
  • They know what they want before opening the tool; discovery is low priority

Read the full file on GitHub · 342 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. 8d ago First seen · 342 lines · 0 tokens per session scan A fa928c5901c2

Subscribe to this mod's changes

product-designer is an agent published in the GitHub repository FlorianBruniaux/ccboard (97 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,203 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 2026-08-30.

Related

Other agents, from other repositories

frontend-builder

Builds UI components that are usable, accessible, and on-brand, covering loading, empty, and error states. Use when implementing user-facing interface work.

emtcmca/promptsmith · 34 tokens

accessibility-auditor

READ-ONLY accessibility critic — audits a running surface against WCAG 2.2 AA and returns a PASS/FAIL verdict per criterion WITH THE MEASURED VALUE. Covers semantic HTML, ARIA roles/states/names, keyboard nav + focus order + focus-visible, tap-target size (44px), color contrast (real computed-style probe)…

jhlee0409/omni-harness-kit · 170 tokens

ui-reviewer

UI/UX review — accessibility, semantic HTML, z-index, animations, responsive, design tokens.

RaNDoM6913/claude-code-superkit · 23 tokens

visual-reviewer

Visual QA reviewer — before/after screenshot comparison when screenshots exist, code-based visual consistency review otherwise; scores design-system compliance 0-100 with N/A rescaling (PASS >= 90).

RaNDoM6913/claude-code-superkit · 43 tokens

ui-design-reviewer

Anti-slop UI review — typography, color calibration, layout diversity, motion quality, interactive states. Activate when reviewing frontend components for design quality.

RaNDoM6913/claude-code-superkit · 34 tokens

ui-ux-designer

Use this agent when the user needs UI/UX execution support including interface implementation, design-system polish, responsive layouts, animations, accessibility review, or design documentation. Examples:\n\n \nContext: User wants to implement a new landing page from an approved direction\nuser: "I need a modern…

opencue/cuecards · 427 tokens