agent-runtimes

A choice of command-line execution engines for running agents inside containers. The available runtimes are Claude Code, Gemini CLI, and OpenAI Codex; a container is an isolated environment where the agent runs.

In plain words
What is it for?
Selecting an agent runtime when creating an agent, optionally choosing its model, and seeing which runtime an existing agent uses.
Why use it?
It lets an agent template specify which coding-agent program should execute the work, while the surrounding chat behaves consistently.

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-runtimes
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 936 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 $0.00936
Opus 5 $0.00000 $0.00468
Sonnet 5 $0.00000 $0.00187
Haiku 4.5 $0.00000 $0.00094

Measured 2d ago against content hash e004092eb6e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-runtimes 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-runtimes.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Runtimes

Trinity agents run on a pluggable runtime — the CLI harness that executes the agent inside its container. Trinity supports Claude Code (default), Gemini CLI, and OpenAI Codex.

Concepts

Runtime -- The execution engine inside the agent container. Each runtime is a different coding-agent CLI with its own auth model, system-prompt file, and capabilities. A template picks one; if none is declared, the agent uses Claude Code.

Harness -- Another name for the runtime. The harness reads the agent's system prompt, calls tools and MCP servers, and produces responses, which Trinity treats identically regardless of which runtime ran them.

How It Works

A template selects the runtime in template.yaml:

runtime:
  type: codex          # claude-code (default) | gemini-cli | codex
  model: gpt-5.6-sol   # optional model override

The runtime is fixed when the agent is created. To change it, recreate the agent from a template that declares a different runtime — there is no post-creation switch.

On the Agent Detail page, a runtime badge shows which runtime the agent is using. Chat works the same across all runtimes. For Codex agents, the Session tab is hidden (Codex does not support session resume); the Chat tab remains, with full conversation continuity.

Runtime Comparison

Claude Code (default) Gemini CLI OpenAI Codex
Auth model Claude subscription / OAuth, or platform API key Gemini API key OPENAI_API_KEY (Codex skips Claude-subscription auto-assign)
System-prompt file CLAUDE.md CLAUDE.md AGENTS.md
Chat continuity Yes Yes Yes
Working memory across turns Yes Yes No (history replayed as text)
MCP support Yes Yes Yes
Cost reporting Actual Actual Estimated

Safety controls apply across all runtimes: read-only mode and credential redaction work the same regardless of runtime. Codex enforces read-only through its own sandbox (--sandbox read-only) rather than the Claude tool-use hook.

Read the full file on GitHub · 67 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. 2d ago First seen · 67 lines · 0 tokens per session scan A e004092eb6e6

Subscribe to this mod's changes

agent-runtimes 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 936 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens