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 commands/mort-lab/excel-mcp/prp-poc-create-parallelgit clone --depth 1 https://github.com/mort-lab/excel-mcpWrote 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/commands/mort-lab/excel-mcp/prp-poc-create-parallel)<a href="https://agentmods.dev/commands/mort-lab/excel-mcp/prp-poc-create-parallel"><img src="https://agentmods.dev/badge/commands/mort-lab/excel-mcp/prp-poc-create-parallel.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 | $0.00000 | $0.02483 |
| Opus 5 | $0.00000 | $0.01241 |
| Sonnet 5 | $0.00000 | $0.00497 |
| Haiku 4.5 | $0.00000 | $0.00248 |
Grade A, and why
prp-poc-create-parallel 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 5d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Parallel React POCs
Request: $ARGUMENTS
Usage: /prp-poc-create-parallel [number_of_demos] "[problem_statement]"
Example: /prp-poc-create-parallel 5 "create a dashboard for tracking team productivity with real-time metrics"
Parallel POC Creation Mission
Create multiple React POC variations simultaneously to maximize concept validation through diverse implementation approaches. This command generates PRPs for parallel execution using specialized UI/UX and User Journey agents.
Critical Understanding: Each POC targets different aspects of the same problem:
- Different UI/UX approaches (minimal, polished, experimental)
- Different user journey focuses (power user, casual user, admin)
- Different technical approaches (component-heavy, page-based, single-file)
- Different fidelity levels (wireframe, demo, MVP)
Parallel Creation Strategy
Agent Specialization Pattern
For N demos requested, create N pairs of specialized agents:
- N UI-UX Agents: Each focusing on different design approaches
- N User Journey Agents: Each targeting different user personas/flows
Agent Assignment Matrix:
Demo 1: @ui-ux-agent (Minimal/Clean) + @user-journey-agent (Power User)
Demo 2: @ui-ux-agent (Polished/Professional) + @user-journey-agent (Casual User)
Demo 3: @ui-ux-agent (Experimental/Modern) + @user-journey-agent (Admin User)
Demo 4: @ui-ux-agent (Dashboard-Heavy) + @user-journey-agent (Mobile-First)
Demo 5: @ui-ux-agent (Component-Library) + @user-journey-agent (Accessibility-First)
POC Variation Strategy
Each POC should explore different aspects:
Design Variations:
- Minimal: Clean, simple, content-focused
- Polished: Professional, brand-aligned, stakeholder-ready
- Experimental: Modern patterns, micro-interactions, innovative UI
- Dashboard-Heavy: Data visualization focused, charts/graphs
- Component-Library: Showcases reusable design system components
User Journey Variations:
- Power User: Feature-rich, keyboard shortcuts, advanced workflows
- Casual User: Simplified navigation, guided experiences, fewer options
- Admin User: Management interfaces, bulk actions, system controls
- Mobile-First: Touch-optimized, responsive, gesture-based
- Accessibility-First: Screen reader optimized, keyboard navigation, high contrast
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.
- 5d ago First seen · 259 lines · 0 tokens per session scan A c375832a2351
prp-poc-create-parallel is a command published in the GitHub repository mort-lab/excel-mcp (5 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,483 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 2026-08-31.
Other commands, from other repositories
build-app
Build web client application (Next.js, React, Vite).
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.
sync
Full bidirectional sync between local and GitHub.
refactoring
Workflow command scaffold for refactoring in fdic-mcp-server.