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 skills add wezendy/elon-musk-algorithm-skills --skill musk-step-3-simplify-optimizegit 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/skills/wezendy/elon-musk-algorithm-skills/musk-step-3-simplify-optimize)<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.
<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>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 | $0.00176 | $0.01126 |
| Opus 5 | $0.00088 | $0.00563 |
| Sonnet 5 | $0.00035 | $0.00225 |
| Haiku 4.5 | $0.00018 | $0.00113 |
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.
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:
- 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.
- Measure the pre-optimization state. Parts, lines, parameters, branches, dependencies, special cases. Without this baseline, any "optimization" is unverifiable.
- Reduce. In priority order: parameters, branches, special cases, moving parts, cognitive load, lines.
- Match existing style. Do not refactor adjacent code that is not in scope. Surgical changes only.
- 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]
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 · 93 lines · 176 tokens per session scan A de8dde85cd07
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…