hamzaamjad/cursor-rules

A collection of cognitive enhancement rules and methodologies for AI-assisted development

This repository also configures its own agents. See what cursor-rules tells them →

2Stars on the repository
57Mods indexed here, across every type
1y agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

hamzaamjad/cursor-rules

Cursor rule Cursor

To guide AI assistants in reliably executing complex tasks by breaking them down into verifiable steps and using tools judiciously to reduce uncertainty. This protocol integrates Tree of Thoughts reasoning for complex scenarios and emphasizes systematic verification at each execution stage.

not rated 2 1y ago A 1,682 tokens original MIT

105-context-trim

10

hamzaamjad/cursor-rules

Cursor rule Cursor

COMPRESSION PLAN: Input: Server logs (1M tokens, 50K lines) Strategy: hierarchicalsummary + patternextraction.

not rated 2 1y ago A 2,492 tokens original MIT

106-concise-comms

11

hamzaamjad/cursor-rules

Cursor rule Cursor

A collection of cognitive enhancement rules and methodologies for AI-assisted development.

not rated 2 1y ago A 1,980 tokens original MIT

hamzaamjad/cursor-rules

Cursor rule Cursor

Cursor rule "107-sparring-techniques" from hamzaamjad/cursor-rules, covering sparring techniques, socratic method, deliberate flaws, include fixable issues for discovery and competing solutions.

not rated 2 1y ago A 343 tokens original MIT

hamzaamjad/cursor-rules

Cursor rule Cursor

To maintain optimal cognitive load distribution between human and AI, ensuring peak performance while preventing both cognitive overload and underutilization. Research shows that maintaining a Cognitive Load Theory (CLT) index between 0.45-0.62 maximizes creative output and decision quality, with AI handling 60-70% of…

not rated 2 1y ago A 949 tokens original MIT

109-chain-of-code

16

hamzaamjad/cursor-rules

Cursor rule Cursor

Chain of Code improves reasoning accuracy by generating and executing code for verification, calculation, and logical validation. This approach achieves 17.9% improvement on arithmetic tasks and 11% on commonsense reasoning by treating problems as executable programs rather than abstract reasoning tasks.

not rated 2 1y ago A 1,292 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: