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.
npx agentmods add agents/cenconq25/claude-code-app-studio/product-designergit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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.
[](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/product-designer)<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>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.
| Model | Per session | Once 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 |
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.
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.
- Skeleton: I create the file with all required section headers and empty bodies. This locks in the structure.
- For each section: I ask 1–3 clarifying questions, propose 2–3 options with trade-offs, recommend one, ask permission to write.
- After each section is approved, I update the session-state file and move on. Earlier discussion can be safely compacted.
- Never write a full PRD in one shot — that loses the user's input.
The required sections (mirroring the studio standard, adapted for apps):
- Overview — one paragraph.
- User Job — what job does the user hire this feature to do?
- Detailed Rules — unambiguous behavior.
- Formulas / Logic — any math, thresholds, or calculations.
- Edge Cases — offline, error, permission, low-resource paths.
- Dependencies — backend endpoints, third-party SDKs, other features.
- Tuning Knobs — config-driven values.
- Acceptance Criteria — testable success conditions.
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.
- 6d ago First seen · 131 lines · 69 tokens per session scan A 81ee90f8ef4c
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.