Tui Agent Channel — Development skill for Claude Code
Use when Claude needs to send MDL commands to a running mxcli TUI, execute operations with human oversight, or automate TUI interactions via the agent socket.
How to install Tui Agent Channel
Installs to ~/.claude/skills/mendixlabs-mxcli-tui-agent-channel/SKILL.md
mkdir -p ~/.claude/skills/mendixlabs-mxcli-tui-agent-channel && curl -fsSL https://raw.githubusercontent.com/mendixlabs/mxcli/HEAD/.claude/skills/tui-agent-channel.md -o ~/.claude/skills/mendixlabs-mxcli-tui-agent-channel/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Tui Agent Channel does
name: tui-agent-channel description: Use when Claude needs to send MDL commands to a running mxcli TUI, execute operations with human oversight, or automate TUI interactions via the agent socket. Also use when setting up Claude-TUI integration for supervised Mendix project modifications.
TUI Agent Channel
Send MDL commands to a running mxcli TUI over a Unix socket. **All agent actions simulate normal user operations** — every command is visible in the TUI, understandable by the human
Alternatives in Development
- Updater Setting — updater-setting-sop 669 ★
- Maestro Next — Unified entry for all development intents — classify intent, assess complexity, route to the correct execution 530 ★
- Claude Code iOS Dev Guide — A comprehensive guide for setting up Claude Code CLI with PRD-driven workflows, extended thinking (ultrathink) 492 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Jam
Share one real Claude Code session with other humans — attributed messages, human-only side channel, live mirr
Skill Gmail API
Claude Agent Skill for Gmail API - read, draft, send, archive, label, batch operations
Autonomous Overnight
Run a scoped autonomous work session that can continue without human supervision, queuing irreversible operati
Agent Speak Readability
An agent skill that makes an agent's natural-language output readable to a human: cross-language rules plus a
Implement Mdl Feature
Implement New MDL Feature Skill
Transcripto
Index your coding-agent transcripts, keep only the turns you actually typed, and grade them. Local, stdlib-onl
Related Agents
Execute Plan
Execute PLAN.md tasks one at a time with human oversight. Triggers on "execute", "execute plan", "execute the
Human Validator
Use this agent for strategic human oversight integration in high-stakes decisions. Specializes in determining
Data Layer
AI ethics, data governance, and schema validation checkpoint. Use for W4 feature validation ethics clearance,