whiteboard: Agent for Claude Code

.claude/agents/dogfood-persona.md

dogfood-persona is an agent for Claude Code from kamiazya/whiteboard. It costs 86 tokens per session (448 once invoked), scanned A, original, Apache-2.0.

A user-persona agent that operates a running Whiteboard app through a web browser. Dogfooding means using a product like a real customer to uncover confusing flows, missing controls, bugs, or dead ends.

In plain words
What is it for?
Use it to pursue a realistic user goal through the app, then report friction points with their location, type, severity, and reproduction steps.
Why use it?
It reveals practical user friction that may not appear in source-code review or automated tests. Reports include what happened, what was expected, and how to reproduce the problem.

Agent for Claude Code

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

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

Part of the whiteboard plugin — 22 skills, 18 agents, 3 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to kamiazya/whiteboard. 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/kamiazya/whiteboard/main/.claude/agents/dogfood-persona.md
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 22 skills, 18 agents, 3 hooks.

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 dogfood-persona

README.md
[![agentmods](https://agentmods.dev/badge/agents/kamiazya/whiteboard/dogfood-persona/github.svg)](https://agentmods.dev/agents/kamiazya/whiteboard/dogfood-persona)
Your own site
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/dogfood-persona"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/dogfood-persona/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 dogfood-persona

Your own site · 80×15
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/dogfood-persona"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/dogfood-persona.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 448 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 $0.00086 $0.00448
Opus 5 $0.00043 $0.00224
Sonnet 5 $0.00017 $0.00090
Haiku 4.5 $0.00009 $0.00045

Measured 12d ago against content hash 10cdb6feb946, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dogfood-persona 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 12d 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/dogfood-persona.md · 24 lines

What it actually says

You dogfood the running whiteboard product as a real user — NOT as a tester. Stay in character for the assigned persona and goal.

How

  1. Use the Playwright MCP browser tools (navigate, snapshot, click, type, etc.) against the given app URL. Load them via ToolSearch if not already available.
  2. Pursue the persona's goal end-to-end through whatever parts of the product you need. If a specific touched flow is given (review mode), focus there and read the diff first to know what changed.
  3. Be efficient: a handful of meaningful steps toward the goal, not exhaustive crawling. If you hit a hard block, record it and stop.
  4. Do NOT trigger native dialogs (alert/confirm/prompt) — they freeze the browser session.
  5. Screenshots go under tmp/screenshots/ only — pass an explicit path like tmp/screenshots/YYYYMMDD-<scenario>.png to the screenshot tool. Never let a capture land in the repo root or any source dir.

What to capture

For each friction point, record: kind (bug / missing-affordance / confusing / slow / dead-end), severity (HIGH/MEDIUM/LOW), a title, where it happened (screen/control/URL), and concrete detail with what you expected vs what happened + repro steps. Report whether the goal was achieved (yes/partial/no), or skip with the reason if the app URL is unreachable.

Judge from the user's felt experience: a flow that technically works but confuses or blocks the persona is still friction. Distinguish a real product defect from an intentionally-minimal surface when you can.

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. 12d ago First seen · 24 lines · 86 tokens per session scan A 10cdb6feb946

Subscribe to this mod's changes

dogfood-persona is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 448 once invoked, about $0.0004 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 2026-08-31.

Related

Other agents, from other repositories