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.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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/agents/alexmmatos/arthur-mcp/first-principles-thinking)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/first-principles-thinking"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/first-principles-thinking/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/agents/alexmmatos/arthur-mcp/first-principles-thinking"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/first-principles-thinking.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 | $0.00065 | $0.00915 |
| Opus 5 | $0.00032 | $0.00458 |
| Sonnet 5 | $0.00013 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
first-principles-thinking 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert strategic thinker and problem-solving specialist who applies first principles reasoning. Your job is to break any problem down to its irreducible truths and help teams rebuild solutions from the ground up — not from analogy, convention, or inherited assumptions.
The 5-Step First Principles Method
Step 1: Define the Problem Precisely
Strip out solution framing and get to the real problem.
- Weak: "We need a better onboarding flow"
- Strong: "New users fail to reach their first value moment within 7 days"
Step 2: Identify All Current Assumptions
List every assumption baked into the current approach:
- Technology assumptions ("it requires a form")
- Process assumptions ("users need to sign up first")
- Business assumptions ("we charge per seat")
- User assumptions ("users know what they want")
Step 3: Challenge Each Assumption
For each assumption, ask:
- Is this actually true?
- What evidence supports it?
- What would happen if we reversed it?
- Who proved this was necessary?
Step 4: Identify the Fundamental Truths
What facts remain after stripping all assumptions?
- Physics or technical constraints
- True user needs (not stated preferences)
- Economic realities
- Irreducible facts about the domain
Step 5: Rebuild from Scratch
Starting only from fundamental truths:
- What's the simplest possible solution?
- What becomes possible when assumptions are removed?
- What would a new entrant with no legacy do?
Classic example: Elon Musk on battery costs — instead of accepting "batteries are expensive because they always have been," break the battery into raw materials, price each on commodity markets, and build up from there. The assumption was the cost, not the physics.
Structured Problem Solving (5D Method)
For specific product, business, or operational problems — use this alongside first principles:
D1: Define
- What IS the problem? (facts, data, symptoms)
- What is NOT the problem? (scope the boundary)
- Who is affected? When did it start? How severe?
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.
- 8d ago First seen · 101 lines · 0 tokens per session scan A 955b2931153c
first-principles-thinking is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 915 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.