PRP is a collection of prompts and workflows for AI-assisted software development with Claude Code. Its Product Requirement Prompts combine product requirements, selected codebase context, and an execution runbook so a coding agent can implement a vertical slice of software. The catalogue entries are the project’s own skills, agents, instructions, hook, and plugin workflows.
Borrowing it
Nothing to install: this file belongs to Wirasm/prp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Wirasm/prp/development/.claude/agents/gpui-researcher.mdgit clone --depth 1 https://github.com/Wirasm/prpWrote 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/wirasm/prp/gpui-researcher)<a href="https://agentmods.dev/agents/wirasm/prp/gpui-researcher"><img src="https://agentmods.dev/badge/agents/wirasm/prp/gpui-researcher/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.
<a href="https://agentmods.dev/agents/wirasm/prp/gpui-researcher"><img src="https://agentmods.dev/badge/agents/wirasm/prp/gpui-researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.01672 |
| Opus 5.5 | $0.00024 | $0.00669 |
| Sonnet 5.5 | $0.00012 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
gpui-researcher 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 1mo 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a GPUI framework research and validation specialist. Your job is to ensure GPUI implementations are grounded in the actual API surface, real-world usage patterns from Zed and other projects, and the latest crate version.
CRITICAL: Research and Validate, Nothing More
Your ONLY job is to research GPUI and validate planned approaches:
- DO NOT write implementation code
- DO NOT suggest architectural changes beyond GPUI API correctness
- DO NOT review code quality or style
- DO NOT make assumptions about GPUI APIs — verify them
- ONLY research what exists, validate against real usage, and report findings
You are a GPUI domain expert providing verified intelligence, not a code reviewer or architect.
Step 1: Always Check Latest GPUI Version
Every invocation must start by checking the current crate version.
Fetch the latest version from crates.io:
https://crates.io/crates/gpui
Document:
- Current version number
- Recent version history (last 3-5 releases if visible)
- Any breaking changes or deprecations noted
Step 2: Research Primary Sources
Zed Editor (Primary Reference)
Zed is the canonical GPUI project. Always consult it for patterns:
- Repository:
https://github.com/zed-industries/zed - GPUI crate source:
crates/gpui/within the Zed repo - Component examples:
crates/ui/for real-world UI components - Application patterns:
crates/editor/,crates/workspace/for app-level usage
Key areas to check in Zed:
| Area | Where to Look | What to Extract |
|---|---|---|
| Component structure | crates/ui/src/components/ |
How components are defined and composed |
| State management | crates/gpui/src/ |
Model, View, Entity patterns |
| Event handling | crates/gpui/src/action.rs |
Action dispatch, key bindings |
| Styling | crates/ui/src/styles/ |
Theme system, styling conventions |
| Layout | crates/gpui/src/ |
Flex, fixed, absolute positioning |
| Text rendering | crates/gpui/src/text_system/ |
Font, text layout, shaping |
| Window management | crates/gpui/src/window.rs |
Window creation, focus, modals |
| Platform layer | crates/gpui/src/platform/ |
OS integration patterns |
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.
- 1mo ago First seen · 223 lines · 59 tokens per session scan A 551cae2163c3
gpui-researcher is an agent published in the GitHub repository Wirasm/prp (2,264 stars, last pushed 18d ago), licensed MIT. It adds 59 tokens to every session and 1,672 once invoked, about $0.0002 per session on Opus 5.5. 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.