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.
npx skills add SkiTemplar/ultron-control-center --skill ultrongit clone --depth 1 https://github.com/SkiTemplar/ultron-control-centerWrote 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.
[](https://agentmods.dev/skills/skitemplar/ultron-control-center/ultron)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- Reads
~/.ultron/.tmp/context.md(L0 hot context, capped at ~400 tokens). - Reads
~/.ultron/SYSTEM-MAP.mdif present (system layout pointers). - Surfaces any
[BLOCKING]items. - Optionally reads
~/.ultron/MEMORY.mdfor 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.
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.
- 10d ago First seen · 57 lines · 63 tokens per session scan A 0e229a149318
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.
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…
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…
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…
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…
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…
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…