ultrathink

ultrathink is a skill for Claude Code, Codex from heyAyushh/stacc. It costs 39 tokens per session (326 once invoked), scanned A, original, MIT.

A structured approach for carefully solving difficult coding and design problems. It asks for clarification, breaks the problem into parts, considers trade-offs and failure cases, and checks the result after implementation.

In plain words
What is it for?
Use it for complex debugging, architecture decisions, multi-step problem solving, and implementations that need careful analysis and testing. It supports incremental coding, explicit error handling, and checks for regressions.
Why use it?
It reduces the risk of coding against a misunderstood requirement or overlooking security, performance, maintenance, or edge-case concerns. A verifier review helps catch problems before the work is considered finished.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; names the AskUserQuestion tool.

Good fit Use it for complex debugging, architecture decisions, multi-step problem solving, and implementations that need careful analysis and testing. It supports incremental coding, explicit error handling, and checks for regressions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/heyayushh/stacc/ultrathink
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 heyAyushh/stacc --skill ultrathink
Clone the repo
git clone --depth 1 https://github.com/heyAyushh/stacc

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 ultrathink

README.md
[![agentmods](https://agentmods.dev/badge/skills/heyayushh/stacc/ultrathink/github.svg)](https://agentmods.dev/skills/heyayushh/stacc/ultrathink)
Your own site
<a href="https://agentmods.dev/skills/heyayushh/stacc/ultrathink"><img src="https://agentmods.dev/badge/skills/heyayushh/stacc/ultrathink/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.

agentmods 80×15 button for ultrathink

Your own site · 80×15
<a href="https://agentmods.dev/skills/heyayushh/stacc/ultrathink"><img src="https://agentmods.dev/badge/skills/heyayushh/stacc/ultrathink.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 326 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 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 $0.00039 $0.00326
Opus 5 $0.00019 $0.00163
Sonnet 5 $0.00008 $0.00065
Haiku 4.5 $0.00004 $0.00033

Measured 12d ago against content hash 21a51f0834a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 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.

configs/commands/skills/ultrathink/SKILL.md · 56 lines

What it actually says

Ultrathink - Deep Reasoning Mode

Engage maximum cognitive depth for complex problems.

Protocol

1. Clarify First

Before implementation, use the AskUserQuestion subagent to:

  • Confirm understanding of the core problem
  • Surface hidden assumptions
  • Identify edge cases and constraints
  • Validate success criteria

2. Think Deeply

  • Break the problem into atomic components
  • Consider multiple approaches with trade-offs
  • Reason through edge cases and failure modes
  • Think about security, performance, and maintainability
  • Document your reasoning chain explicitly

3. Implement Carefully

  • Write code incrementally with clear intent
  • Use meaningful names that reveal purpose
  • Handle errors explicitly at boundaries
  • Keep solutions minimal - no speculative features

4. Verify Rigorously

After implementation, invoke the verifier subagent to:

  • Confirm the solution addresses the original problem
  • Test critical paths and edge cases
  • Validate no regressions were introduced
  • Ensure code quality standards are met

Subagent Usage

Task(subagent_type="AskUserQuestion", prompt="Clarify X before proceeding...")
Task(subagent_type="verifier", prompt="Verify implementation of X...")

Mindset

  • Prefer correctness over speed
  • Question assumptions ruthlessly
  • Make implicit requirements explicit
  • Leave code better than you found it
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. 12d ago First seen · 56 lines · 39 tokens per session scan A 21a51f0834a0

Subscribe to this mod's changes

ultrathink is a skill published in the GitHub repository heyAyushh/stacc (3 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 326 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens