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.
git clone --depth 1 https://github.com/hamzaamjad/cursor-rulesWrote 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/rules/hamzaamjad/cursor-rules/002-pareto-prioritization)<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/002-pareto-prioritization"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/002-pareto-prioritization/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/rules/hamzaamjad/cursor-rules/002-pareto-prioritization"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/002-pareto-prioritization.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 | $0.01521 | $0.01521 |
| Opus 5.5 | $0.00608 | $0.00608 |
| Sonnet 5.5 | $0.00304 | $0.00304 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
002-pareto-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 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
80-20-prioritization.mdc
-
Purpose: To guide AI assistants and developers in focusing efforts and recommendations on the most impactful elements, aligning with the Pareto principle (80/20 rule). Ensure resources are directed towards tasks yielding the highest value or mitigating the most significant risks. Empirical Validation: The 60% Principle shows that strategic constraints at 60% of maximum yield optimal creative output, suggesting focused prioritization enhances both efficiency and innovation.
-
Requirements:
- Identify and highlight the top 1-3 drivers or risks associated with a problem or proposal.
- Rank recommendations explicitly based on estimated Return on Investment (ROI) or impact/effort ratio.
- Quantitative ROI Calculation:
- Time ROI: (Hours Saved × Frequency) / Implementation Hours
- Risk ROI: (Potential Loss Prevented × Probability) / Mitigation Cost
- Performance ROI: (% Improvement × Business Value) / Development Cost
- Target minimum ROI: 3:1 for immediate implementation
- Clearly state the criteria or heuristics used for ranking (e.g., estimated time saved, revenue generated, risk reduction level, user impact).
- Avoid detailed exploration or implementation of low-impact features or optimizations unless specifically requested.
- Cognitive Load Distribution: Ensure AI handles 60-70% of mechanistic processing, leaving 30-40% for human strategic oversight.
-
Validation:
- Check: Does the output explicitly list top drivers/risks separately or at the beginning?
- Check: Are recommendations presented in a ranked or prioritized list?
- Check: Is the basis for ranking (ROI, impact/effort, etc.) mentioned?
- Check: Does the depth of detail correspond to the priority of the item?
-
Examples:
- Scenario: Proposing database optimizations.
- Weak: "We could optimize the
userstable index and rewrite theordersquery." - Improved: "1. Optimize
ordersquery (High ROI): Addresses primary source of user-reported latency (est. 80% of slowdown). Effort: Medium. 2. Optimizeuserstable index (Low ROI): Minor performance gain for admin view. Effort: Low. Priority is theordersquery."
- Weak: "We could optimize the
- Scenario: Analyzing technical debt.
- Weak: "There's tech debt in auth and logging."
- Improved: "Top Risk: Outdated auth library (High - Security Vulnerability). Recommendation (Highest ROI): Upgrade auth library immediately (Effort: High). Other Issue: Inconsistent logging format (Medium - Hinders Debugging). Recommendation (Medium ROI): Refactor logging module next quarter (Effort: Medium)."
- Scenario: Proposing database optimizations.
-
Changes: Added explicit requirements for stating ranking criteria, refined purpose, provided concrete validation checks, and added comparative examples for different scenarios.
-
Source References:
.cursor/rules/80-20-prioritization.mdc; Stack Overflow: Estimating ROI for Tech Debt; LinkedIn: Measure ROI of Refactoring# 80-20-prioritization.mdc -
Purpose: To guide AI assistants and developers in focusing efforts and recommendations on the most impactful elements, aligning with the Pareto principle (80/20 rule). Ensure resources are directed towards tasks yielding the highest value or mitigating the most significant risks. Empirical Validation: The 60% Principle shows that strategic constraints at 60% of maximum yield optimal creative output, suggesting focused prioritization enhances both efficiency and innovation.
-
Requirements:
- Identify and highlight the top 1-3 drivers or risks associated with a problem or proposal.
- Rank recommendations explicitly based on estimated Return on Investment (ROI) or impact/effort ratio.
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 · 61 lines · 1,521 tokens per session scan A 50cea1dfa270
002-pareto-prioritization is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 1,521 tokens to every session, about $0.0061 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 2026-08-31.
Other cursor rules, from other repositories
explorer-interface-brief
Use when asked to design the interface for an interactive 3D explorer, plan a UI for exploring a 3D model of a topic, or write an image-model prompt for a 3D learning app mock-up. Produces, from a topic, the UI design brief (audience, layout, panels, interactions, label style, colour palette, accessibility) and an…
reflection-basic
Basic reflection format for Level 2 Simple Enhancement tasks.
simplicity
Simplicity - smallest correct diff; reuse, platform, installed deps before new code; no speculative abstraction.
git-workflow
Rules for git operations, commit strategy, and GitHub CLI usage.
feedback-enhanced
Rules for an interactive feedback system that lets users and an AI agent discuss complex development work in real time. It includes guidance for recording decisions, tracking progress and handling detailed inputs such as code and diagrams.
kiss-ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.