Interactive (TUI) on core-agent

Interactive quickstart

Mon, 01 Jan 0001 00:00:00 +0000

15 minutes from core-agent installed → a tailored agent your whole team can use.

Prefer to have an agent walk you through this? The cli-setup skill covers the same material in workflow form. Install once, then say “help me set up core-agent for my project” and the agent walks the four layers with you, writing files as you go.

What you’ll have at the end

A project-scoped agent that:

Knows what your project is (system prompt via AGENTS.md)
Has a reusable named procedure (a skill)
Asks before running anything risky (permissions in ask mode by default)
Is checked into the repo so every teammate gets the same agent

The running example is a “Go code-reviewer” for a hypothetical project. Adapt as needed.

Workflows

Mon, 01 Jan 0001 00:00:00 +0000

Worked examples of using core-agent interactively. Each one shows a full .agents/ configuration you can adapt and a walkthrough of running it.

If you haven’t done the Interactive quickstart yet, do that first — these examples assume you know how AGENTS.md, skills, and permission posture fit together.

Workflow 1 — Go code reviewer with MCP-backed web search

The marquee operator example. A code-reviewer agent that knows your house style, follows a documented review procedure, and can reach the web when it needs context on an unfamiliar library.

Slash reference

Mon, 01 Jan 0001 00:00:00 +0000

Reference for every slash command and keybinding available in the interactive TUI. Type /help in any session for the operator-side version of this catalog.

For attach-mode (core-agent-tui remote client) commands, see Attach mode TUI.

Quick reference

Session control

Command	Aliases	Effect
`/help`		Print the command list + keybindings into the scrollback
`/clear`		Clear the local scrollback (session log is untouched)
`/quit`		Leave the TUI cleanly
`/interrupt`		Cancel the in-flight model turn (same as pressing Esc during a turn)
`/resume`		Resume a saved session from `<AgentsDir>/sessions/`
`/reload`		Re-walk `AGENTS.md`, skills, and MCP config on disk. Reports per-surface results inline (`Memory: ✓`, `Skills: ✓`, `MCP: ✗` with errors listed) so you can confirm an edit parsed cleanly. Live MCP server restart and system-prompt rebuild still require a daemon restart.

Status + observability

Command	Aliases	Effect
`/stats`		Session token totals, cost, duration, per-model breakdown
`/context`	`/boundaries`	Context-management activity: compactions, checkpoints, summarized chars, subtask cost
`/tools`		List the tools the agent has access to (built-ins + MCP + skills)
`/skills`		List loaded skills with their trigger descriptions
`/mcp`		List configured MCP servers and their status
`/subagents`	`/sub`	List background subagents spawned this session
`/memory`		Show the resolved `AGENTS.md` chain (user-global + project)

Context management

Command	Aliases	Effect
`/compact [focus]`	`/summarize`	Manually compact the session; optional `focus` biases what the summary preserves
`/done [note]`	`/checkpoint`	Write a task-boundary checkpoint; optional `note` becomes part of the handover record

Both run a summarizer LLM call (5-15s); the next turn picks up from the summary with prior history sliced. See Context management for the design.