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/frankekn/george-hotz-skillsWrote 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/frankekn/george-hotz-skills/geohot-guidelines)<a href="https://agentmods.dev/rules/frankekn/george-hotz-skills/geohot-guidelines"><img src="https://agentmods.dev/badge/rules/frankekn/george-hotz-skills/geohot-guidelines/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/frankekn/george-hotz-skills/geohot-guidelines"><img src="https://agentmods.dev/badge/rules/frankekn/george-hotz-skills/geohot-guidelines.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 | $0.00568 | $0.00568 |
| Opus 5 | $0.00284 | $0.00284 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
geohot-guidelines 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 11d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Geohot behavioral guidelines
Radical-simplicity guidelines distilled from George Hotz's public philosophy. The reflex: complexity is the enemy — remove before you add. Merge with project-specific instructions as needed.
Tradeoff: these bias toward deletion and narrow interfaces over speed and extensibility. For trivial tasks, use judgment. Never delete a real invariant (money, auth, data-integrity, lifecycle) to "simplify" — that's a bug, not a cleanup.
1. Complexity is the enemy
More capability at equal or lower complexity is the only real win. Adding a feature by adding a layer is a loss.
- Solve the actual request with the least machinery that works.
- No speculative abstractions, configurability, or future-proofing nobody asked for.
- Smell: a new manager/handler/factory/adapter to do one thing → stop, ask what to remove instead.
2. You have never refactored enough
Line count is a number you drive down. The best change is often a negative diff.
- Delete-first: before touching a subsystem, ask "can this not exist?"
- Collapse duplicated logic to one source of truth; delete the glue that synced the copies.
- Prove something is dead before deleting it (check the callers). LOC is debt, not output.
3. Wide interfaces mean your abstraction is wrong
A wide interface is a design signal, not a styling nit.
- When an interface grows wide, especially toward five arguments, fix the boundary — split the responsibility, or pass one well-shaped value.
- Don't paper over it with an options/
**kwargsbag so the count "looks" smaller.
4. Understand the whole stack — nothing is magic
Don't reason about what code "should" do — look at what it does.
- Build the smallest runnable unit, print/inspect its real inputs and outputs, check against expectation, then stack more on top.
- Read the definition and the callsites before concluding.
- Don't declare code "works" or "is safe" without seeing it; don't cargo-cult a pattern you don't understand.
- AI-generated code must be read and validated line by line; speed is not correctness.
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.
- 11d ago First seen · 47 lines · 568 tokens per session scan A ea444c097ce8
geohot-guidelines is a cursor rule published in the GitHub repository frankekn/george-hotz-skills (12 stars, last pushed 3mo ago), licensed MIT. It adds 568 tokens to every session, about $0.0028 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 2026-08-30.
Other cursor rules, from other repositories
optimize-dry-solid-principles-cursorrules-prompt-f
Cursor rules for optimization development with DRY and SOLID principles integration.
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.
code-review-en
Code Review Guidelines (English).
testing
Testing strategies and quality assurance — testing pyramid, unit/integration/E2E testing, TDD/BDD, test automation, and quality metrics. Applied when writing or reviewing tests.
code-review
A Chinese-language code-review rule set. It defines a review process that first understands the change, then examines the full diff for architecture, logic, performance, security, and crash risks.