first-principles

first-principles is a command for Claude Code from llcoolblaze/claude-boris. It costs 13 tokens per session (437 once invoked), scanned A, original, MIT.

A problem-solving command that breaks a complex task into its basic goal, constraints, assumptions, inputs, outputs, and transformations. It then rebuilds a solution from those fundamentals.

In plain words
What is it for?
Use it to analyze technical or business problems, identify constraints, compare assumptions with facts, and design a simpler approach.
Why use it?
It helps reveal unnecessary assumptions and separates actual requirements from usual habits or preferred methods. This can make difficult problems easier to reason about.

Command for Claude Code

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.

agentmods
npx agentmods add commands/llcoolblaze/claude-boris/first-principles
Clone the repo
git clone --depth 1 https://github.com/llcoolblaze/claude-boris

Made for: Claude Code.

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/commands/llcoolblaze/claude-boris/first-principles.svg)](https://agentmods.dev/commands/llcoolblaze/claude-boris/first-principles)
Your own site
<a href="https://agentmods.dev/commands/llcoolblaze/claude-boris/first-principles"><img src="https://agentmods.dev/badge/commands/llcoolblaze/claude-boris/first-principles.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00013 $0.00437
Opus 5 $0.00006 $0.00218
Sonnet 5 $0.00003 $0.00087
Haiku 4.5 $0.00001 $0.00044

Measured 5d ago against content hash 632907452f00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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.

.claude/commands/first-principles.md · 78 lines

What it actually says

First Principles Analysis

Problem: $ARGUMENTS


Framework

Step 1: What are we actually trying to achieve?

Strip away assumptions. What is the fundamental goal?

Step 2: What are the absolute constraints?

Not "how it's usually done" but physical/logical limits:

  • Technical constraints (what's actually impossible)
  • Business constraints (actual requirements)
  • Time/resource constraints (real limits)

Step 3: What assumptions are we making?

List every assumption, then challenge each:

  • Is this actually true?
  • Is this how it HAS to be, or how it's usually done?
  • What if this assumption were wrong?

Step 4: What are the fundamental building blocks?

Break down to atomic components:

  • What are the inputs?
  • What are the outputs?
  • What transformations are needed?

Step 5: Rebuild from fundamentals

Now construct the solution from first principles:

  • What's the simplest path from inputs to outputs?
  • What's actually necessary vs nice-to-have?
  • What would we build if starting from scratch?

Output Format

## First Principles Analysis: [Problem]

### Fundamental Goal
[What we actually need to achieve]

### Real Constraints
1. [Constraint that can't be changed]
2. [Another real limit]

### Challenged Assumptions
| Assumption | Status | Reasoning |
|------------|--------|-----------|
| "We need X" | ❌ False | Actually we need Y |
| "Must use Z" | ✅ True | Required for [reason] |

### Building Blocks
- Input: [What we start with]
- Output: [What we need]
- Core operation: [Fundamental transformation]

### First Principles Solution
[The approach derived from fundamentals]

### Comparison
| Aspect | Conventional | First Principles |
|--------|--------------|------------------|
| Complexity | High | Lower |
| Time | X days | Y days |
| Maintenance | Hard | Easier |

### Recommendation
[Which approach and why]
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. 5d ago First seen · 78 lines · 13 tokens per session scan A 632907452f00

Subscribe to this mod's changes

first-principles is a command published in the GitHub repository llcoolblaze/claude-boris (48 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 437 once invoked, about $0.0001 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 2026-08-30.