us-prioritization

us-prioritization is a cursor rule for Cursor from KaelSensei/MagicAIBuilder. It costs 4,157 tokens per session, scanned A, original, MIT.

A set of methods for deciding which user stories to build first, estimating their relative complexity, and comparing their business value. User stories are short descriptions of what a user needs; the methods include Story Points, MoSCoW, and RICE scoring.

In plain words
What is it for?
Use it to estimate work with Fibonacci-based story points, classify work as Must-have or lower priority with MoSCoW, and rank opportunities using reach, impact, confidence, and effort in RICE.
Why use it?
It separates delivery effort, product importance, and expected value so teams can make clearer planning decisions.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: installed under .agents/ (shared by several agents).

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 rules/kaelsensei/magicaibuilder/us-prioritization
Clone the repo
git clone --depth 1 https://github.com/KaelSensei/MagicAIBuilder

Made for: Cursor.

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 us-prioritization

README.md
[![agentmods](https://agentmods.dev/badge/rules/kaelsensei/magicaibuilder/us-prioritization.svg)](https://agentmods.dev/rules/kaelsensei/magicaibuilder/us-prioritization)
Your own site
<a href="https://agentmods.dev/rules/kaelsensei/magicaibuilder/us-prioritization"><img src="https://agentmods.dev/badge/rules/kaelsensei/magicaibuilder/us-prioritization.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,157 This file is loaded in full into every session.
When invoked 4,157 The same file — it is already loaded in full.
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 $0.04157 $0.04157
Opus 5 $0.02079 $0.02079
Sonnet 5 $0.00831 $0.00831
Haiku 4.5 $0.00416 $0.00416

Measured 5d ago against content hash 24d74aa5b528, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

us-prioritization 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.

.agents/rules/us-prioritization.mdc · 415 lines

How it starts

The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NOTE: Cursor .cursor/skills/*.mdc files use alwaysApply frontmatter.

Set to false so it only applies when relevant.


alwaysApply: false

User Story Prioritization & Weighting

Master the three core frameworks for prioritizing user stories, estimating effort, and making data-driven decisions about what to build next.

Overview

Three complementary methodologies exist for prioritization, each optimized for different contexts:

Framework Best For Core Metric Effort Data Need
Story Points Team capacity planning Relative complexity Low Internal only
MoSCoW Risk/scope management Business category Minimal Strategic alignment
RICE Scoring Product-led growth Quantified ROI Medium Usage + analytics

Best practice: Use all three in parallel. They answer different questions:

  • Story Points → Can we deliver this in the sprint?
  • MoSCoW → Will this break the product if we skip it?
  • RICE → Which delivers the most business value per engineering day?

Story Points (Planning Poker)

What It Is

A Fibonacci-scaled (1, 2, 3, 5, 8, 13, 21) estimation of relative complexity, not time. Forces binary choice between "close to this story" vs. "further away."

Why Fibonacci?

  • 1, 2, 3: Fine-grain distinctions for small tasks
  • 5, 8, 13: Clear jumps for complexity gaps
  • 21+: Signals overscoping — usually needs splitting

When to Use

✅ Stable team, established velocity ✅ Predictable feature work (bug fixes, increments) ✅ Need to track burndown / capacity ✅ Multiple sprints planned ahead

❌ New team (velocity unknown) ❌ Emergency/ad-hoc work (can't predict velocity) ❌ Highly variable task scope (infrastructure, research)

Running Planning Poker

  1. Read the story aloud; clarify questions
  2. Each person silently picks a point value (1–21) without discussion
  3. Reveal simultaneously — outliers explain their thinking
  4. Re-estimate once if there was a wide spread
  5. Accept the estimate (don't aim for consensus, aim for reasonableness)

Read the full file on GitHub · 415 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. 5d ago First seen · 415 lines · 4,157 tokens per session scan A 24d74aa5b528

Subscribe to this mod's changes

us-prioritization is a cursor rule published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed 3d ago), licensed MIT. It adds 4,157 tokens to every session, about $0.0208 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.