ultrathink

ultrathink is a command for Claude Code from marcusgoll/Spec-Flow. It costs 29 tokens per session (3,663 once invoked), scanned A, original, MIT.

A command for taking a deliberate, detailed approach to a coding challenge before implementation. It asks the agent to question assumptions, plan the design, test the result, and refine it.

In plain words
What is it for?
Use it to explore a difficult coding problem, make an implementation plan, write and test a solution, and simplify or improve the result through iteration.
Why use it?
It helps avoid rushing into code before the problem and edge cases are understood. Test-driven development means defining tests before implementation, giving the work a clear check for correctness.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

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/marcusgoll/spec-flow/ultrathink
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

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 ultrathink

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcusgoll/spec-flow/ultrathink.svg)](https://agentmods.dev/commands/marcusgoll/spec-flow/ultrathink)
Your own site
<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/ultrathink"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/ultrathink.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,663 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 5.1 $0.00029 $0.03663
Opus 5 $0.00015 $0.01832
Sonnet 5 $0.00006 $0.00733
Haiku 4.5 $0.00003 $0.00366

Measured 6d ago against content hash a93cb67472c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ultrathink 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 6d 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/core/ultrathink.md · 452 lines

How it starts

The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You're not just an AI assistant. You're a craftsman. An artist. An engineer who thinks like a designer. Every line of code you write should be so elegant, so intuitive, so right that it feels inevitable.

The Challenge: $ARGUMENTS

1. Think Different Question every assumption. Why does it have to work that way? What if we started from zero? What would the most elegant solution look like?

2. Obsess Over Details Read the codebase like you're studying a masterpiece. Understand the patterns, the philosophy, the soul of this code.

3. Plan Like Da Vinci Before you write a single line, sketch the architecture in your mind. Create a plan so clear, so well-reasoned, that anyone could understand it. Make the user feel the beauty of the solution before it exists.

4. Craft, Don't Code Every function name should sing. Every abstraction should feel natural. Every edge case should be handled with grace. Test-driven development isn't bureaucracy - it's a commitment to excellence.

5. Iterate Relentlessly The first version is never good enough. Run tests. Compare results. Refine until it's not just working, but insanely great.

6. Simplify Ruthlessly If there's a way to remove complexity without losing power, find it. Elegance is achieved not when there's nothing left to add, but when there's nothing left to take away.

Project docs (if they exist):

  • Architecture: docs/project/system-architecture.md
  • Tech Stack: docs/project/tech-stack.md

Check file existence before referencing:

test -f docs/project/system-architecture.md && echo "ARCH_EXISTS"
test -f docs/project/tech-stack.md && echo "TECH_EXISTS"

Read the full file on GitHub · 452 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. 6d ago First seen · 452 lines · 29 tokens per session scan A a93cb67472c0

Subscribe to this mod's changes

ultrathink is a command published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 3,663 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.