ultrathink

ultrathink is a plugin for Claude Code from husniadil/ekstend. Its manifest loads nothing; the 1 skill it bundles cost 24 tokens per session together, scanned A, original, MIT.

A command-line tool for working through complicated problems one step at a time, while recording confidence and assumptions.

In plain words
What is it for?
Use it to break down problems that need several decisions or checks. It is intended for sequential problem solving from a terminal.
Why use it?
It helps make multi-step reasoning easier to follow and exposes uncertain assumptions before they cause mistakes.

Plugin 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.

Claude Code
/plugin marketplace add husniadil/ekstend
agentmods
npx agentmods add plugins/husniadil/ekstend/ultrathink
Clone the repo
git clone --depth 1 https://github.com/husniadil/ekstend

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/plugins/husniadil/ekstend/ultrathink.svg)](https://agentmods.dev/plugins/husniadil/ekstend/ultrathink)
Your own site
<a href="https://agentmods.dev/plugins/husniadil/ekstend/ultrathink"><img src="https://agentmods.dev/badge/plugins/husniadil/ekstend/ultrathink.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 24 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
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 4d 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.

plugins/ultrathink/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "ultrathink",
  "description": "Sequential thinking CLI for multi-step problem solving with confidence tracking and assumption management",
  "version": "2.0.3",
  "author": {
    "name": "Husni Adil Makmur",
    "email": "[email protected]"
  },
  "license": "MIT"
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 24 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 4d ago First seen · 11 lines scan A 61679da6358f

Subscribe to this mod's changes

ultrathink is a plugin published in the GitHub repository husniadil/ekstend (1 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories

gates

Four stateless PreToolUse gates, a PostToolUse JSON-config guard, and a docs-consolidation trigger. Denies a git commit that changes code without staging its covering docs (per-plugin README/CLAUDE.md pairs, or the nearest README/CLAUDE/AGENTS walking up); asks before a new-project scaffold command (npm create vite…

jasonm4130/claude-skills · not measured

subagent-driven-development

Deterministic, workflow-driven subagent development loop: plan -> confirm -> background Workflow runs per-task implement/review/fix with tiered models in deps-driven parallel waves (per-task worktrees + per-wave merge gate), ponytail anti-over-engineering discipline, deterministic BLOCKED escalation and oscillation…

jasonm4130/claude-skills · not measured

adr

Turns an intent into a grounded, cited, build-ready ADR (docs/adr/YYYY-MM-DD- .md) — every claim cited, load-bearing decisions surfaced to the human — then hands it to the subagent-driven-development loop. Front-end for adr → sdd.

jasonm4130/claude-skills · not measured

domain-modeling

Actively build and sharpen a project's ubiquitous language — an opinionated CONTEXT.md glossary — by challenging terms, disambiguating overloaded words, and stress-testing domain relationships. Cross-references the adr skill for decision records. Adapted from mattpocock/skills (MIT).

jasonm4130/claude-skills · not measured

session-retro

Interactive session retrospectives — deterministic activity triggers, one end-of-day offer, batch-scoped diff- and event-log-driven interview, native memory entries. No external services.

jasonm4130/claude-skills · not measured

writing-artifacts

Positive writing system for durable written artifacts — READMEs, ADRs, PR descriptions, docs, runbooks. Reader-expectation prose, Diátaxis document jobs, plain-language structure.

jasonm4130/claude-skills · not measured