agent-terminal

A browser terminal for opening an agent's interactive command-line workspace. It can switch between Claude Code, Gemini, and Bash, and connects to the agent container through a live terminal session.

In plain words
What is it for?
Use it to work in an agent container through Claude Code, Gemini, or Bash, control which API key is used, and—when permitted—obtain temporary SSH access.
Why use it?
It provides one place to interact with an agent, run shell commands, or use different command-line assistants while seeing the terminal resize with the browser.

Agent

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.

agentmods
npx agentmods add agents/abilityai/trinity/agent-terminal
Clone the repo
git clone --depth 1 https://github.com/Abilityai/trinity
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00400
Opus 5 $0.00000 $0.00200
Sonnet 5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured 2d ago against content hash ef5f8ccd2459, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-terminal 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 2d 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.

docs/user-docs/agents/agent-terminal.md · 40 lines

What it actually says

Agent Terminal

Browser-based xterm.js terminal providing direct access to the agent's Claude Code TUI, with mode switching between Claude, Gemini, and Bash.

How It Works

  1. Open the agent detail page and click the Terminal tab.
  2. The terminal connects via WebSocket to the agent container's PTY.
  3. The default mode is the Claude Code TUI (interactive AI assistant).
  4. A mode toggle in the terminal header switches between Claude, Gemini, and Bash:
    • Claude -- Claude Code interactive mode.
    • Gemini -- Gemini CLI (requires GEMINI_API_KEY credential).
    • Bash -- Raw shell access to the agent container.
  5. The terminal supports resize and adapts to the browser window dimensions.
  6. Per-agent API key control: toggle between the platform API key and your own Claude subscription in the Terminal tab.

SSH Access

  • Admin-only: SSH access is restricted to admin users for security.
  • Generate ephemeral SSH credentials via the API or MCP.
  • ED25519 keys with configurable TTL, controlled by ops settings.
  • API: POST /api/agents/{name}/ssh-access
  • MCP: get_agent_ssh_access(name)
  • SSH ports: 2222-2262 (incrementing per agent).

System Agent Terminal

  • Admin-only browser terminal for the system agent (trinity-system).
  • Accessible via the System Agent page.

For Agents

Each agent container runs an SSH server and a PTY multiplexer. The browser terminal connects through the backend's WebSocket proxy -- agents do not need to expose ports directly. Mode switching restarts the PTY process inside the container without dropping the WebSocket connection.

See Also

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. 2d ago First seen · 40 lines · 0 tokens per session scan A ef5f8ccd2459

Subscribe to this mod's changes

agent-terminal is an agent published in the GitHub repository Abilityai/trinity (496 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 400 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

audit-geo

Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).

XuanRanL/loamwright-SEO-Skill · 44 tokens

praman-sap-planner-cli

SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.

mrkanitkar/playwright-praman · 36 tokens

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

performance-optimizer

Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".

DDS-Solutions/AI-TadPole-OS · 40 tokens