A guide to configuring, troubleshooting, and migrating Bosch Rexroth ctrlX AI and its built-in Agent iXi. It covers version-aware settings, connected tools, providers, prompts, skills, and related configuration.

Use it when setting up or migrating ctrlX AI, checking models and providers, configuring tools and approvals, or investigating Agent iXi behavior.

It helps avoid applying instructions from the wrong product version or deployment and provides a structured way to diagnose configuration problems.

ctrlx-ai — Skill for Claude Code and Codex by gmantoha

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 gmantoha/ctrlx-os-agent-skills --skill ctrlx-ai

Clone the repo

git clone --depth 1 https://github.com/gmantoha/ctrlx-os-agent-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gmantoha/ctrlx-os-agent-skills/ctrlx-ai/github.svg)](https://agentmods.dev/skills/gmantoha/ctrlx-os-agent-skills/ctrlx-ai)

Your own site

<a href="https://agentmods.dev/skills/gmantoha/ctrlx-os-agent-skills/ctrlx-ai"><img src="https://agentmods.dev/badge/skills/gmantoha/ctrlx-os-agent-skills/ctrlx-ai/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gmantoha/ctrlx-os-agent-skills/ctrlx-ai"><img src="https://agentmods.dev/badge/skills/gmantoha/ctrlx-os-agent-skills/ctrlx-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,451 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.

Model	Per session	Once invoked
Fable 5.1	$0.00124	$0.01451
Opus 5.5	$0.00050	$0.00580
Sonnet 5.5	$0.00025	$0.00290
Haiku 4.5	$0.00012	$0.00145

Measured yesterday against content hash 967f5f6e338f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ctrlx-ai 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 yesterday.

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/ctrlx-ai/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ctrlX AI / Agent iXi

Turn ctrlX AI questions into a version-aware configuration proposal, migration plan or diagnosis. Keep this skill usable on its own: all required product notes are bundled below.

Scope and evidence

These notes summarize the supplied ctrlX AI - Automation Intelligence User Manual, whose changelog describes 0.5.0 and migration from 0.3.0. They are documentation-derived, not proof of behavior on a particular device. See source provenance.

Check the installed app version before applying version-dependent advice. For older or newer versions, verify the live tool schemas, shipped configuration templates and version-matched documentation rather than assuming these notes apply unchanged. Tool names can be prefixed by the client or additional server.

Start here

Establish the task, app version and deployment: ctrlX OS snap or standalone. For device work, establish the target and whether it is real or virtual; do not infer a target from examples.
Discover connected ctrlX MCP tools first using the client's tool search/list facility. Prefer typed tools. For REST operations not exposed as typed tools, use the discovered http_request tool if available; do not invent its argument schema.
Inspect only the relevant non-secret configuration and logbook errors. Confirm the active configuration / allowed filesystem base at runtime. Paths such as agent/models.yaml below are relative to the app data in the active configuration, not to this repository or an assumed absolute solution path.

Load the relevant reference:

Task	Read
LLM provider, model selection, discovery, limits, caching, secrets or YAML errors	Models and agent settings
MCP authentication, additional servers, HTTP/process access, permissions or approval rules	MCP and security
Custom prompts/skills, dashboard hosting, attachments or widget behavior	Prompts and usage
Upgrade from 0.3.0, obsolete environment settings or symptom-led diagnosis	Migration and troubleshooting

Read the full file on GitHub · 79 lines

Files

What ships with it

7 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.

yesterday First seen · 79 lines · 124 tokens per session scan A 967f5f6e338f

Subscribe to this mod's changes

ctrlx-ai is a skill published in the GitHub repository gmantoha/ctrlx-os-agent-skills (7 stars, last pushed yesterday), licensed MIT. It adds 124 tokens to every session and 1,451 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-11-05.

Building agents Hardware and IoT

ctrlx-ai next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ctrlx-aigmantoha/ctrlx-os-agent-skills	Skill	7	yesterday	MIT	A	124	Claude Code, Codex
gke-compute-classesgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	83	Claude Code, Codex
jetson-diagnosticNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code, Codex
holoscan-install-wheelNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	34	Claude Code, Codex
offensive-z-waveSnailSploit/Claude-Red	Skill	10k	25d ago	MIT	A	113	Claude Code, Codex
doca-socket-relayNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	236	Claude Code, Codex
hsb-flashNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	B	94	Claude Code