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-2-delete-partsgit 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-2-delete-parts)<a href="https://agentmods.dev/skills/wezendy/elon-musk-algorithm-skills/musk-step-2-delete-parts"><img src="https://agentmods.dev/badge/skills/wezendy/elon-musk-algorithm-skills/musk-step-2-delete-parts/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-2-delete-parts"><img src="https://agentmods.dev/badge/skills/wezendy/elon-musk-algorithm-skills/musk-step-2-delete-parts.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 | $0.00163 | $0.01159 |
| Opus 5 | $0.00081 | $0.00580 |
| Sonnet 5 | $0.00033 | $0.00232 |
| Haiku 4.5 | $0.00016 | $0.00116 |
Grade A, and why
musk-step-2-delete-parts 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 2: Delete Any Part or Process You Can
Cut first. If you do not add back ~10%, you did not cut hard enough.
Part of the [[musk-algorithm]]. Second 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.
If absent, stop. Run step 1 first. No exceptions.
Why this step exists
Smart engineers default to addition. Adding a part feels like progress. Removing one feels risky. The Musk algorithm inverts this default: every part is guilty until proven necessary by a surviving requirement from step 1.
Musk's calibration rule: if you do not end up adding back at least 10% of what you deleted, you did not delete enough. Adding back zero means the cuts were never load-bearing in the first place, which means the system has even more bloat than was just removed.
Protocol
For every part in scope (feature, endpoint, table, column, service, dependency, config flag, document, meeting, role, dashboard, report):
- Inventory. List every part. If the list is incomplete, stop and request the rest.
- Map each part to a surviving requirement. If no surviving requirement from step 1 justifies a part, default to delete.
- Identify hidden invariants. Code, especially, can assert things that are not in the requirements. Before deleting, ask: what does this code assert? If the assertion matters and lives nowhere else, the assertion must be relocated before the code is cut.
- Predict the add-back list. Before any deletion, name the parts you expect to restore once pain shows up. Zero predicted add-back means the cut is theatrical. Recut.
- Execute the cut.
- Audit the actual add-back over the relevant time horizon. Less than 10% means the cut was too soft. Recut deeper. More than ~25% means the cut was sloppy. Redo with more care.
Output format
Inventory: [list of all parts in scope]
Deletion list: [parts proposed for removal, with one-line justification each]
Justifications for kept parts: [each kept part tied to a named-owner requirement from step 1]
Predicted add-back: [parts you expect to restore, with reasoning]
Expected add-back percentage: [explicit number, target 10-25%]
Hidden invariants identified: [what kept code or processes assert]
Cut executed: [what was actually deleted]
Audit plan: [when and how the actual add-back will be measured]
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.
- 12d ago First seen · 87 lines · 163 tokens per session scan A e5a44ca9a607
musk-step-2-delete-parts is a skill published in the GitHub repository wezendy/elon-musk-algorithm-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 163 tokens to every session and 1,159 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…