first-principles

first-principles is a skill for Claude Code, Codex from martineserios/thebrana. It costs 99 tokens per session (4,271 once invoked), scanned A, a copy of first-principles, MIT.

A problem-solving method that starts with basic facts and builds an answer from them. It is also called first-principles thinking.

In plain words
What is it for?
Use it to examine difficult decisions, challenge accepted assumptions, and reason about strategy, costs, or new solutions.
Why use it?
It helps when familiar approaches, assumptions, or comparisons are blocking progress on a difficult problem.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

Good fit Use it to examine difficult decisions, challenge accepted assumptions, and reason about strategy, costs, or new solutions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/martineserios/thebrana/first-principles
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 martineserios/thebrana --skill first-principles
Clone the repo
git clone --depth 1 https://github.com/martineserios/thebrana

Made for: Claude Code, Codex.

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 first-principles

README.md
[![agentmods](https://agentmods.dev/badge/skills/martineserios/thebrana/first-principles.svg)](https://agentmods.dev/skills/martineserios/thebrana/first-principles)
Your own site
<a href="https://agentmods.dev/skills/martineserios/thebrana/first-principles"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/first-principles.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,271 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 100% copy Near-identical to another mod 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 $0.00099 $0.04271
Opus 5 $0.00049 $0.02135
Sonnet 5 $0.00020 $0.00854
Haiku 4.5 $0.00010 $0.00427

Measured 8d ago against content hash 697805728775, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

first-principles 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 8d 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.

Origin

This is a copy

100% identical to first-principles — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/first-principles/SKILL.md · 629 lines

How it starts

The opening of the file, as written. The whole thing — 629 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First Principles Thinking

Break down complex problems to their fundamental truths, then reason up from there. Master Aristotle's ancient method modernized by Elon Musk to solve seemingly impossible problems.

When to Use This Skill

  • Facing a "impossible" problem where conventional solutions don't work
  • Challenging industry assumptions that everyone accepts as truth
  • Pricing or cost analysis to find dramatic savings (like Musk with batteries)
  • Product innovation when iterating on existing solutions isn't enough
  • Strategic decisions where analogies to other companies may mislead
  • Breaking through mental blocks when you're stuck in conventional thinking

Methodology Foundation

Aspect Details
Source Aristotle (384-322 BC), modernized by Elon Musk
Expert Aristotle called it "the first basis from which a thing is known"; Musk applies it to SpaceX, Tesla, and every venture
Core Principle "Boil things down to the most fundamental truths and say, 'What are we sure is true?'... and then reason up from there." - Elon Musk

What Claude Does vs What You Decide

"Claude structures the breakdown. You challenge the assumptions."

Claude handles You provide
Systematically listing assumptions Domain expertise to validate/invalidate
Breaking down atomic components Real-world cost/constraint data
Applying the physics vs convention test Judgment on what's truly immutable
Structuring the rebuild from fundamentals Strategic decisions on which path to pursue
Generating novel solution frameworks Feasibility assessment and implementation

Remember: First principles is a thinking tool. Claude accelerates the structure; breakthrough insights come from YOUR willingness to question everything.


What This Skill Does

  1. Deconstructs assumptions - Identifies what you think is true vs. what IS true
  2. Reveals hidden constraints - Exposes artificial limitations masquerading as laws
  3. Enables breakthrough solutions - Creates paths invisible to analogical thinkers
  4. Reduces costs dramatically - Finds the true floor price of anything
  5. Builds original insights - Generates conclusions others can't reach by copying

Read the full file on GitHub · 629 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. 8d ago First seen · 629 lines · 99 tokens per session scan A 697805728775

Subscribe to this mod's changes

first-principles is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 4,271 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to first-principles, differing in 0 lines, and is treated as a copy.