agentmods.dev

ultrathink

ultrathink is a skill for Claude Code from husniadil/ekstend. It costs 24 tokens per session (626 once invoked), scanned A, original, MIT.

A structured method for solving problems through a sequence of written thoughts, tracked assumptions, confidence levels, revisions, and alternative paths.

In plain words
What is it for?
Use it for multi-step debugging, system design, architecture choices, algorithm planning, optimisation, and other problems that need more than a simple answer.
Why use it?
It makes complex reasoning easier to inspect and correct when the first approach may be wrong or incomplete.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ultrathink plugin — 1 skill shipped together

not rated 1repo 4mo ago A scan 24 tokens original MIT

Good fit Use it for multi-step debugging, system design, architecture choices, algorithm planning, optimisation, and other problems that need more than a simple answer.

Compare 6 skills from other repositories ↓
View source ↗ husniadil/ekstend
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add husniadil/ekstend
Claude Code
/plugin install ultrathink

Made for: Claude Code.

Or install ultrathink, the plugin that ships this one along with the rest of its 1 skill.

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/husniadil/ekstend/ultrathink/github.svg)](https://agentmods.dev/skills/husniadil/ekstend/ultrathink)
Your own site
<a href="https://agentmods.dev/skills/husniadil/ekstend/ultrathink"><img src="https://agentmods.dev/badge/skills/husniadil/ekstend/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/husniadil/ekstend/ultrathink"><img src="https://agentmods.dev/badge/skills/husniadil/ekstend/ultrathink.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 626 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 $0.00024 $0.00626
Opus 5 $0.00012 $0.00313
Sonnet 5 $0.00005 $0.00125
Haiku 4.5 $0.00002 $0.00063

Measured 10d ago against content hash 0b86acd0eba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/ultrathink.py, tests/test_ultrathink.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/ultrathink/skills/ultrathink/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UltraThink - Sequential Thinking CLI

A tool for dynamic and reflective problem-solving through structured, sequential thoughts.

When to Use

Use this skill for:

  • Breaking down complex problems (>3 reasoning steps)
  • Planning and design with room for revision
  • Architecture decisions with multiple trade-offs
  • Algorithm design and optimization
  • Debugging multi-layered issues
  • Analysis that might need course correction

Do NOT use for:

  • Simple one-step answers
  • Straightforward code edits
  • Basic file operations
  • Simple factual questions

Instructions

  1. Start a session with initial thought and estimated total
  2. Continue session using session_id from response
  3. Use --confidence to track uncertainty (0.0-1.0)
  4. Revise thoughts with --is-revision --revises <num>
  5. Branch to explore alternatives with --branch-from <num> --branch-id <name>
  6. Track assumptions with --assumptions, --depends-on, --invalidates
  7. Monitor risky_assumptions in response
  8. Continue until next_thought_needed is false

Quick Start

# Start new session
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Analyzing the problem..." -n 5

# Continue session
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Next step..." -n 5 -s <session-id>

# With confidence
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "I believe X is correct" -n 3 -c 0.8

# With assumption
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Assuming Redis available" -n 3 \
  --assumptions '[{"id":"A1","text":"Redis is available"}]'

Example Session

Thought 1 (confidence: 0.6): "Analyzing access patterns for caching strategy..."
Thought 2 (confidence: 0.7): "Two approaches: LRU or LFU..."
Thought 3 (revision of 2): "Should also consider TTL-based expiration..."
Thought 4 (branch from 2): "Exploring hybrid LRU+TTL approach..."
Thought 5 (confidence: 0.95): "Hybrid approach recommended."

Read the full file on GitHub · 70 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 70 lines · 24 tokens per session scan A 0b86acd0eba2

Subscribe to this mod's changes

ultrathink is a skill published in the GitHub repository husniadil/ekstend (1 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 626 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 2026-08-31.

Claude CodePlanningclaude-code-plugindeveloper-toolsplugin-marketplace
Related

Other skills, from other repositories

codex

Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.

PyModel/claude-architect · 31 tokens

commit

A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.

restarter/lets-workflow · 90 tokens

x-multi-llm-align

A review process in which two sub-agents examine an API, data format, event schema, or workflow from their separate implementation perspectives. The user passes documents and feedback between them over multiple rounds.

KtKID/x-dev-pipeline · 293 tokens

design

Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…

cryndoc/polisade-orchestrator · 162 tokens

x-cr

A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.

KtKID/x-dev-pipeline · 183 tokens

explain

Use when user invokes /explain with a file path, directory path, function/class name, or natural language concept. Also triggers on "explain this", "how does X work", "walk me through". Produces a structured, layered explanation of what the code does, how it connects, and where to start if you need to change it. Do…

harnessprotocol/harness-kit · 95 tokens