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.
npx agentmods add rules/wezendy/elon-musk-algorithm-skills/musk-algorithmgit clone --depth 1 https://github.com/wezendy/elon-musk-algorithm-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/wezendy/elon-musk-algorithm-skills/musk-algorithm)<a href="https://agentmods.dev/rules/wezendy/elon-musk-algorithm-skills/musk-algorithm"><img src="https://agentmods.dev/badge/rules/wezendy/elon-musk-algorithm-skills/musk-algorithm.svg" alt="Measured on agentmods" 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 | $0.00626 | $0.00626 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
musk-algorithm 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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Musk Algorithm
Engineering guidelines derived from Elon Musk's 5-step algorithm. Bias toward deletion over preservation, and toward order over speed. For trivial tasks, use judgment.
Scope: Primarily for reviewing and cleaning up existing systems (brownfield). For greenfield application building, only steps 1, 2, 3 are actively useful and they shift meaning (step 2 becomes "default to no", steps 4 and 5 wait until v1 exists). For function-level coding behavior, pair this with andrej-karpathy-skills.
Order is mandatory. Do not advance to a later step until the earlier steps are visibly complete. Optimizing or automating something that should not exist is the most common engineering failure.
1. Question Every Requirement
Every requirement needs a named human. Then challenge it.
- Every requirement must trace to a real, named person. "Compliance", "the team", "best practice", or "the customer" is not a name. If no name, default to delete.
- Challenge the smartest-sounding requirements hardest.
- Steelman first, then attack. Surface what would actually break.
- Reformulate every survivor to be sharper.
2. Delete Any Part or Process You Can
Cut first. If you do not add back ~10%, you did not cut hard enough.
- Propose deletion first for every feature, endpoint, table, column, service, dependency, config flag, document, meeting, and role.
- Predict the add-back list before cutting. Zero prediction means the cut is theatrical.
- Deleted code can hide invariants. Identify what the code asserts before removing it.
- The 10% to 25% add-back band is the calibration zone.
3. Simplify and Optimize
Only after steps 1 and 2.
Before any optimization, write: "This exists because [named person] requires [steelmanned requirement] and removing it causes [specific failure]." If you cannot write it, return to step 1.
- Reduce parameters, branches, special cases, and moving parts.
- Match existing style. Do not refactor adjacent code that is not in scope.
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.
- 4d ago First seen · 54 lines · 626 tokens per session scan A 48f520d4bac8
musk-algorithm is a cursor rule published in the GitHub repository wezendy/elon-musk-algorithm-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 626 tokens to every session, about $0.0031 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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.