ultron

ultron is a skill for Claude Code from SkiTemplar/ultron-control-center. It costs 63 tokens per session (552 once invoked), scanned A, original, MIT.

A master workflow for ULTRON, an agent system that routes tasks through memory layers, skills, hooks, and language-model fallbacks.

In plain words
What is it for?
Use it to initialize an ULTRON session, surface blocking information, consult its stored context, and choose an appropriate task mode.
Why use it?
It gives each session a starting context and defines different operating levels for simple through critical architecture work.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths.

Good fit Use it to initialize an ULTRON session, surface blocking information, consult its stored context, and choose an appropriate task mode.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skitemplar/ultron-control-center/ultron
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 SkiTemplar/ultron-control-center --skill ultron
Clone the repo
git clone --depth 1 https://github.com/SkiTemplar/ultron-control-center

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 ultron

README.md
[![agentmods](https://agentmods.dev/badge/skills/skitemplar/ultron-control-center/ultron/github.svg)](https://agentmods.dev/skills/skitemplar/ultron-control-center/ultron)
Your own site
<a href="https://agentmods.dev/skills/skitemplar/ultron-control-center/ultron"><img src="https://agentmods.dev/badge/skills/skitemplar/ultron-control-center/ultron/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 ultron

Your own site · 80×15
<a href="https://agentmods.dev/skills/skitemplar/ultron-control-center/ultron"><img src="https://agentmods.dev/badge/skills/skitemplar/ultron-control-center/ultron.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 552 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 $0.00063 $0.00552
Opus 5 $0.00032 $0.00276
Sonnet 5 $0.00013 $0.00110
Haiku 4.5 $0.00006 $0.00055

Measured 10d ago against content hash 0e229a149318, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ultron 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.

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.

skills/ultron/SKILL.md · 57 lines

What it actually says

ULTRON — Master Orchestrator

This is the template version of the ultron skill. It defines the baseline routing and protocol surface that ULTRON expects on every session. You are encouraged to fork and extend it for your own work.

Session wake-up protocol

On every SessionStart, ULTRON:

  1. Reads ~/.ultron/.tmp/context.md (L0 hot context, capped at ~400 tokens).
  2. Reads ~/.ultron/SYSTEM-MAP.md if present (system layout pointers).
  3. Surfaces any [BLOCKING] items.
  4. Optionally reads ~/.ultron/MEMORY.md for deeper orientation.

Modes

  • LOW — single-shot, no delegation, response under 50 words.
  • MEDIUM — default. Single-domain tasks, may delegate to a specialist skill.
  • HIGH — multi-domain, parallel agents allowed, deep planning.
  • ULTRA — critical architecture work, full triple-LLM review allowed.

Memory layers

Layer Path Purpose
L0 ~/.ultron/.tmp/context.md pinned session primer
L1 ~/.ultron/brain_index/index.db SQLite FTS5 over chunked vault
L2 ~/.ultron-vault/ curated markdown corpus
L3 remote git (optional) off-machine mirror of L2

Plus a Qdrant collection ultron_vault for semantic recall.

Dispatch

When the user prompt matches a registered skill trigger (defined in ~/.claude/skills/<name>/SKILL.md frontmatter description), invoke that skill via the Skill tool. Otherwise handle the request directly under the active mode.

Customize

This file is yours. Edit freely. Common extensions:

  • Add domain-specific routing rules (e.g. "if user mentions UE5 → delegate to gamedev-engineer").
  • Pin your own preferred response style.
  • Hook into vault/brain layers with custom queries.
  • Add your own session opening rituals.

Examples and the full original orchestrator design live in the project's documentation. Treat this as a starting point, not a destination.

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 · 57 lines · 63 tokens per session scan A 0e229a149318

Subscribe to this mod's changes

ultron is a skill published in the GitHub repository SkiTemplar/ultron-control-center (1 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 552 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 2026-08-31.

Related

Other skills, from other repositories

crewai-multi-agent

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…

davila7/claude-code-templates · 61 tokens

inspector-workbench

Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…

CopilotKit/CopilotKit · 112 tokens

trigger-realtime-and-frontend

Trigger.dev client/frontend surface: subscribe to runs in realtime (runs.subscribeToRun and the @trigger.dev/react-hooks hook useRealtimeRun), consume metadata and AI/text streams in React (useRealtimeStream), trigger tasks from the browser (useTaskTrigger, useRealtimeTaskTrigger), and mint scoped frontend credentials…

triggerdotdev/trigger.dev · 148 tokens

build-with-tinybase

Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, configuring browser or database persistence, configuring MergeableStore…

tinyplex/tinybase · 76 tokens

generating-clickhouse-query-performance-reports

Produce and structure slow-query performance reports for PostHog's production ClickHouse (US and EU). Use when asked for a slow query report, query performance analysis over the last N days, per-team query cost, OOM or timeout investigation, cluster cost/memory regressions, or materialization candidates. Covers the…

PostHog/posthog · 142 tokens

query-clickhouse-via-metabase

Run ClickHouse system.querylog analysis via the internal Metabase API. Use when investigating slow queries, materialization candidates, per-team query performance, ClickHouse cost or memory issues, or any system.querylog question. Covers prod-us and prod-eu, SSO-gated cookie auth via hogli, and ready-to-run query…

PostHog/posthog · 79 tokens