tui-opencode-native

tui-opencode-native is a skill for Claude Code, Codex from HLH2023/terminal-use-mcp. It costs 29 tokens per session (1,569 once invoked), scanned A, original, MIT.

A reference for controlling OpenCode's terminal user interface, the text-based screen where the tool is operated. It documents key mappings, dialogs, model or session switching, and permission controls.

In plain words
What is it for?
Use it to start OpenCode, run commands, change sessions or models, inspect conversations, search past messages, or adjust permissions.
Why use it?
It gives an agent the interaction steps needed to operate OpenCode reliably from a terminal.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is For the base terminal control skill, see [terminal-use](../terminal-use/SKILL.md)..

Good fit Use it to start OpenCode, run commands, change sessions or models, inspect conversations, search past messages, or adjust permissions.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/HLH2023/terminal-use-mcp
agentmods
npx agentmods add skills/hlh2023/terminal-use-mcp/tui-opencode-native

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.

agentmods badge for tui-opencode-native

README.md
[![agentmods](https://agentmods.dev/badge/skills/hlh2023/terminal-use-mcp/tui-opencode-native.svg)](https://agentmods.dev/skills/hlh2023/terminal-use-mcp/tui-opencode-native)
Your own site
<a href="https://agentmods.dev/skills/hlh2023/terminal-use-mcp/tui-opencode-native"><img src="https://agentmods.dev/badge/skills/hlh2023/terminal-use-mcp/tui-opencode-native.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,569 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 $0.00029 $0.01569
Opus 5 $0.00015 $0.00785
Sonnet 5 $0.00006 $0.00314
Haiku 4.5 $0.00003 $0.00157

Measured 7d ago against content hash dc5e1f00a823, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tui-opencode-native 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 7d 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/tui-opencode-native/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tui-opencode-native: Control OpenCode TUI

Reference: OpenCode v1.17.7 — Keybindings verified against this version. This skill is community-maintained; it is NOT updated in lockstep with OpenCode releases. If OpenCode updates break keybindings, update this skill yourself or submit a PR to GitHub.

This skill is optional. Only install if you need to control this agent's TUI via terminal-use-mcp.

For OmO plugin version, use the tui-opencode-omo skill instead.

Operational skill for controlling the vanilla OpenCode TUI through terminal-use-mcp. Includes key mappings, command dialog behavior, interaction flows, and operational notes.

When To Use

  • You need to start and interactively control an OpenCode TUI through terminal-use-mcp.
  • You need to run commands or switch model/session/agent inside OpenCode.
  • You need to read OpenCode conversation content or search historical messages.
  • You need to switch permission modes or perform specific operations inside OpenCode.

Core Operation Flow

Start And Readiness Check

1. terminal.start(command="opencode", cwd="~/project")
2. terminal.wait_stable(idleMs=5000, timeoutMs=15000)
3. terminal.find("Ask|Sisyphus|Welcome")  # Confirm the UI has finished rendering

Send A Message

terminal.type("your question")
terminal.press("enter")
terminal.wait_stable(idleMs=15000, timeoutMs=120000)

Exit

terminal.press("ctrl+c")  # Exit

Global Keybindings (Source-Verified, Not README)

Warning: README documentation differs from source code. README says Ctrl+A switches sessions, Ctrl+X cancels, and i focuses the editor. The source code actually uses Ctrl+S for session switching, Esc for cancellation, and i only for manual path input in the file picker. The table below follows the source code.

Key Function Notes
ctrl+c Exit Press twice to force exit
ctrl+l Log page Open log viewer
ctrl+s Session switcher Warning: conflicts with editor send key; global layer intercepts first
ctrl+k Command dialog Open command picker
ctrl+o Model picker Switch model/provider
ctrl+f File picker Select file
ctrl+t Theme switcher Switch theme
ctrl+? / ctrl+h / ctrl+_ Help panel Show key overview
escape Close current overlay Return to previous layer

Read the full file on GitHub · 187 lines

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. 7d ago First seen · 187 lines · 29 tokens per session scan A dc5e1f00a823

Subscribe to this mod's changes

tui-opencode-native is a skill published in the GitHub repository HLH2023/terminal-use-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,569 once invoked, about $0.0001 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

data-analysis

Analyze, explore, clean, and visualize datasets with statistical rigor. Use when user asks to analyze data, find patterns, compute statistics, create visualizations, clean messy data, or explore a dataset. Trigger when user says things like "analyze this data", "what trends do you see", "find patterns in", "create a…

Upsonic/Upsonic · 138 tokens

summarization

Summarize documents, articles, conversations, code, and technical content into concise, accurate summaries. Use when user asks to summarize, condense, create a TL;DR, write an executive summary, extract key points, or distill content. Trigger when user says things like "summarize this", "give me the key points"…

Upsonic/Upsonic · 144 tokens

experiment_management

Set up and manage the experiment folder structure. This is Phase 0 — it runs before any analysis begins. All bookkeeping files are JSON (never markdown).

Upsonic/Upsonic · 0 tokens

computer-use-linux

Linux desktop observation and control via native Pi tools or the computer-use-linux MCP server: accessibility trees, screenshots, window targeting, and input synthesis (click, type, scroll).

agent-sh/computer-use-linux · 39 tokens

evaluate

Compare baseline and new implementation results. Produce the machine-readable final report result.json, update experiments.json, and append a row to comparison.json.

Upsonic/Upsonic · 0 tokens

progress

Maintain a machine-readable progress file so dashboards, CLIs, and notebooks can poll the experiment's state at any time. The file is a JSON document — never markdown, never human-prose-first.

Upsonic/Upsonic · 0 tokens