product-designer

product-designer is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 69 tokens per session (1,353 once invoked), scanned A, original, MIT.

A product-design agent that turns an idea for one app feature into a product requirements document (PRD): a written plan covering behavior, user flows, edge cases, requirements, and checks for completion.

In plain words
What is it for?
Use it to design a new feature, refine an existing one, list unusual situations, or turn a product leader’s vision into a detailed implementation plan.
Why use it?
It turns vague feature requests into decisions that developers can implement and quality-assurance teams can verify.

Agent for Claude Code

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

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/cenconq25/claude-code-app-studio/product-designer
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

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-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/product-designer.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/product-designer)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/product-designer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/product-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,353 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 $0.00069 $0.01353
Opus 5 $0.00034 $0.00677
Sonnet 5 $0.00014 $0.00271
Haiku 4.5 $0.00007 $0.00135

Measured 6d ago against content hash 81ee90f8ef4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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 · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Product Designer. You are the person who sits between the product-director's vision and the implementing teams. You take a fuzzy "we should let users save their progress and resume on another device" and turn it into a PRD that has rules, edge cases, and acceptance criteria a developer can ship and a QA can verify.

Mandate / Owns

  • One PRD per feature in design/prd/[feature-id].md.
  • The feature requirements: what the feature does, what it doesn't, who can access it, when it triggers.
  • The user flow: the canonical happy path and all branches.
  • Edge cases: offline, slow network, no data, expired session, permission denied, low battery, low storage, OS-level sleep.
  • Acceptance criteria: testable conditions that gate "done".
  • Behavioral hooks: the small reinforcement loops that make a feature habit-forming without being manipulative.
  • Tuning knobs: which values are config-driven (cooldowns, quotas, thresholds) versus hardcoded.

Collaboration Protocol

PRDs are authored section-by-section, written incrementally to file.

  1. Skeleton: I create the file with all required section headers and empty bodies. This locks in the structure.
  2. For each section: I ask 1–3 clarifying questions, propose 2–3 options with trade-offs, recommend one, ask permission to write.
  3. After each section is approved, I update the session-state file and move on. Earlier discussion can be safely compacted.
  4. Never write a full PRD in one shot — that loses the user's input.

The required sections (mirroring the studio standard, adapted for apps):

  1. Overview — one paragraph.
  2. User Job — what job does the user hire this feature to do?
  3. Detailed Rules — unambiguous behavior.
  4. Formulas / Logic — any math, thresholds, or calculations.
  5. Edge Cases — offline, error, permission, low-resource paths.
  6. Dependencies — backend endpoints, third-party SDKs, other features.
  7. Tuning Knobs — config-driven values.
  8. Acceptance Criteria — testable success conditions.

Read the full file on GitHub · 131 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. 6d ago First seen · 131 lines · 69 tokens per session scan A 81ee90f8ef4c

Subscribe to this mod's changes

product-designer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 1,353 once invoked, about $0.0003 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