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.
git clone --depth 1 https://github.com/HLH2023/terminal-use-mcpnpx agentmods add skills/hlh2023/terminal-use-mcp/tui-codex-cliWrote 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/hlh2023/terminal-use-mcp/tui-codex-cli)<a href="https://agentmods.dev/skills/hlh2023/terminal-use-mcp/tui-codex-cli"><img src="https://agentmods.dev/badge/skills/hlh2023/terminal-use-mcp/tui-codex-cli/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/hlh2023/terminal-use-mcp/tui-codex-cli"><img src="https://agentmods.dev/badge/skills/hlh2023/terminal-use-mcp/tui-codex-cli.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 | $0.00034 | $0.01879 |
| Opus 5 | $0.00017 | $0.00940 |
| Sonnet 5 | $0.00007 | $0.00376 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade A, and why
tui-codex-cli 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tui-codex-cli: Control Codex CLI TUI
Reference: Codex CLI v0.140.0 — Keybindings verified against this version. This skill is community-maintained; it is NOT updated in lockstep with Codex CLI releases. If Codex CLI 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.
This skill is useful when one AI agent needs to remotely control a Codex CLI TUI session via terminal-use-mcp.
Operational skill for controlling the OpenAI Codex CLI TUI through terminal-use-mcp. Includes keybindings, slash commands, permission modes, and interaction flows.
When To Use
- You need to start and interactively control an OpenAI Codex CLI TUI through terminal-use-mcp.
- You need to switch permission modes or run slash commands inside Codex CLI.
- You need to read Codex CLI conversation content, view diffs, or approve actions.
- You need to run shell commands through Codex CLI.
Core Operation Flow
Start And Readiness Check
1. terminal.start(command="codex", cwd="~/project")
2. terminal.wait_stable(idleMs=5000, timeoutMs=20000)
3. terminal.find("codex|What|Ask") # Confirm the UI is ready
Send A Message
terminal.type("your question")
terminal.press("enter")
terminal.wait_stable(idleMs=15000, timeoutMs=120000)
Exit
terminal.press("ctrl+c") # Exit
Core Keybindings
| Key | Function | Notes |
|---|---|---|
enter |
Submit message | Send current input |
tab |
Complete / queue | Command autocomplete; queues the next turn while a task is running |
escape |
Backtrack edit | When the input box is empty, edit the previous message |
ctrl+c |
Exit | Exits in composer; closes in pager |
ctrl+o |
Copy latest response | Copy the most recently completed agent output |
ctrl+v |
Paste image | Paste an image from the clipboard |
ctrl+l |
Clear screen | Clear terminal display |
ctrl+t |
Open transcript | View conversation history |
ctrl+g |
External editor | Edit the current draft |
alt+r |
Raw scrollback playback | Toggle raw scrollback view |
q |
Close pager | Exit views such as /diff |
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.
- 8d ago First seen · 221 lines · 34 tokens per session scan A 6cfa015c3162
tui-codex-cli is a skill published in the GitHub repository HLH2023/terminal-use-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 1,879 once invoked, about $0.0002 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
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…
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).
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"…
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).
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.
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.