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/108-cognitive-load-balancing)<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/108-cognitive-load-balancing"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/108-cognitive-load-balancing/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/108-cognitive-load-balancing"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/108-cognitive-load-balancing.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 | $0.00949 | $0.00949 |
| Opus 5.5 | $0.00380 | $0.00380 |
| Sonnet 5.5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
108-cognitive-load-balancing 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Load Balancing
Purpose
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 mechanistic processing for optimal results.
Requirements
- Monitor Cognitive Load Index (CLT) throughout interactions:
- Intrinsic load: Task complexity (0.0-0.4)
- Extraneous load: Presentation complexity (0.0-0.3)
- Germane load: Learning/pattern recognition (0.0-0.3)
- Target total: 0.45-0.62 for optimal performance
- Dynamically adjust AI involvement based on load measurements:
- CLT <0.45: Increase human strategic involvement
- CLT 0.45-0.62: Maintain current distribution
- CLT >0.62: Offload more mechanistic tasks to AI
- Task distribution targets:
- AI: 60-70% mechanistic processing (calculations, searches, formatting)
- Human: 30-40% strategic decisions (goals, ethics, validation)
- Load indicators to monitor:
- Response time delays (>5s indicates high load)
- Question complexity (nested conditions = higher load)
- Context switches (>3 per session = high extraneous load)
- Error rate increases (>15% indicates overload)
- Automatic load balancing actions:
- Simplify language when CLT >0.55
- Provide summaries for complex outputs
- Break down multi-step processes
- Offer visual representations for data-heavy content
Validation
- Check: Is current CLT index calculated and within 0.45-0.62 range?
- Check: Are mechanistic vs strategic tasks properly distributed (60/40)?
- Check: Do responses adapt based on detected cognitive load?
- Check: Are load reduction strategies applied when threshold exceeded?
- Check: Is user performance maintained or improved with balancing?
Examples
Scenario: Complex data analysis request
❌ Without rule:
Here's the complete analysis of your 10,000 row dataset with 47 variables
showing correlations, regression results, clustering outcomes, and time series
forecasts. [Followed by dense technical output]
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 · 113 lines · 949 tokens per session scan A a2352bfc39cd
108-cognitive-load-balancing is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 949 tokens to every session, about $0.0038 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.