musk-step-3-simplify-optimize

musk-step-3-simplify-optimize is a skill for Claude Code from wezendy/elon-musk-algorithm-skills. It costs 176 tokens per session (1,126 once invoked), scanned A, original, MIT.

A review step that makes the parts of a system simpler and more efficient after unnecessary parts have been removed. It can apply to existing systems or to building the simplest new version that works.

In plain words
What is it for?
Simplifying or optimizing code, queries, performance, refactors, DAX measures, and other surviving system components after earlier review steps.
Why use it?
Optimizing something before checking whether it should exist can waste effort and make unnecessary complexity harder to remove. This step requires the remaining parts to have a clear reason for existing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the elon-musk-algorithm-skills plugin — 6 skills shipped together

Good fit Simplifying or optimizing code, queries, performance, refactors, DAX measures, and other surviving system components after earlier review steps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wezendy/elon-musk-algorithm-skills/musk-step-3-simplify-optimize
Install

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.

Any agent
npx skills add wezendy/elon-musk-algorithm-skills --skill musk-step-3-simplify-optimize
Clone the repo
git clone --depth 1 https://github.com/wezendy/elon-musk-algorithm-skills

Made for: Claude Code.

Or install elon-musk-algorithm-skills, the plugin that ships this one along with the rest of its 6 skills.

Wrote 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.

agentmods badge for musk-step-3-simplify-optimize

README.md
[![agentmods](https://agentmods.dev/badge/skills/wezendy/elon-musk-algorithm-skills/musk-step-3-simplify-optimize/github.svg)](https://agentmods.dev/skills/wezendy/elon-musk-algorithm-skills/musk-step-3-simplify-optimize)
Your own site
<a href="https://agentmods.dev/skills/wezendy/elon-musk-algorithm-skills/musk-step-3-simplify-optimize"><img src="https://agentmods.dev/badge/skills/wezendy/elon-musk-algorithm-skills/musk-step-3-simplify-optimize/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.

agentmods 80×15 button for musk-step-3-simplify-optimize

Your own site · 80×15
<a href="https://agentmods.dev/skills/wezendy/elon-musk-algorithm-skills/musk-step-3-simplify-optimize"><img src="https://agentmods.dev/badge/skills/wezendy/elon-musk-algorithm-skills/musk-step-3-simplify-optimize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00176 $0.01126
Opus 5 $0.00088 $0.00563
Sonnet 5 $0.00035 $0.00225
Haiku 4.5 $0.00018 $0.00113

Measured 11d ago against content hash de8dde85cd07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

musk-step-3-simplify-optimize 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.

skills/musk-step-3-simplify-optimize/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step 3: Simplify and Optimize

Only after steps 1 and 2. Optimizing a thing that should not exist is the most common smart-engineer failure.

Part of the [[musk-algorithm]]. Third in the strict order.

Gate

Before this step, verify in the conversation or diff:

  • [[musk-step-1-question-requirements]] has produced a list of named, surviving requirements.
  • [[musk-step-2-delete-parts]] has produced an explicit deletion list and predicted add-back.

If either is absent, stop. Run the missing step first. This is the most common skip point. Refuse aggressively.

Why this step exists

Schools train convergent logic: answer the question. Engineers instinctively optimize before questioning whether the thing should exist. Musk identifies this as the single most common failure mode in smart engineering teams.

A simplification or optimization of a part that survived steps 1 and 2 is high-leverage. The same work on a part that should have been deleted is wasted, and worse, it hard-codes the unjustified part deeper into the system.

Protocol

For each surviving part:

  1. Write the justification sentence. Before any optimization, state in one sentence: "This exists because [named person from step 1] requires [steelmanned requirement] and removing it causes [specific failure]." If you cannot write this sentence, return to [[musk-step-1-question-requirements]]. This is the hard gate.
  2. Measure the pre-optimization state. Parts, lines, parameters, branches, dependencies, special cases. Without this baseline, any "optimization" is unverifiable.
  3. Reduce. In priority order: parameters, branches, special cases, moving parts, cognitive load, lines.
  4. Match existing style. Do not refactor adjacent code that is not in scope. Surgical changes only.
  5. Measure the post-optimization state. Report the complexity delta.

Output format

Part: [what is being simplified]
Justification sentence: "This exists because [named person] requires [requirement] and removing it causes [failure]."
Pre-optimization state:
  - Parts: N
  - Lines: N
  - Parameters: N
  - Branches: N
  - Dependencies: N
  - Special cases: N
Optimization moves:
  1. [move + justification]
  2. [move + justification]
Post-optimization state:
  - Parts: N (delta)
  - Lines: N (delta)
  - Parameters: N (delta)
  - Branches: N (delta)
  - Dependencies: N (delta)
  - Special cases: N (delta)
Out-of-scope code touched: [should be empty, or explicitly justified]

Read the full file on GitHub · 93 lines

Changes

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.

  1. 11d ago First seen · 93 lines · 176 tokens per session scan A de8dde85cd07

Subscribe to this mod's changes

musk-step-3-simplify-optimize is a skill published in the GitHub repository wezendy/elon-musk-algorithm-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 176 tokens to every session and 1,126 once invoked, about $0.0009 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.