A Docker-based runtime for defining and running teams of AI agents. Agents and their tools are described in YAML files.

Use it to build multi-agent systems, configure agent teams, connect MCP tools, and run them locally through the cagent command-line tool.

It provides one local way to coordinate several agents, connect them to tools, and manage their roles and sub-agents.

cagent — Skill for Claude Code by Tyler-R-Kendrick/agent-skills

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.

Any agent

npx skills add Tyler-R-Kendrick/agent-skills --skill cagent

Clone the repo

git clone --depth 1 https://github.com/Tyler-R-Kendrick/agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 57 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/cagent/github.svg)](https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/cagent)

Your own site

<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/cagent"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/cagent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/cagent"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/cagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,251 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.

Model	Per session	Once invoked
Fable 5.1	$0.00094	$0.01251
Opus 5.5	$0.00038	$0.00500
Sonnet 5.5	$0.00019	$0.00250
Haiku 4.5	$0.00009	$0.00125

Measured 2mo ago against content hash 796a5678df4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cagent 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 2mo 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/ai/cagent/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cagent — Docker Agent Runtime

Overview

cagent is an open-source multi-agent runtime from Docker that lets you define, orchestrate, and run teams of AI agents. Agents are configured in YAML with specialized capabilities, tools, and sub-agents. cagent supports MCP for tool integration, the Agent Client Protocol (ACP) for IDE integration, and runs locally via cagent run. Bundled in Docker Desktop.

Installation

# Bundled with Docker Desktop, or install standalone:
brew install docker/tap/cagent     # macOS
# Or download from github.com/docker/cagent/releases

Agent Configuration

Agents are defined in a cagent.yaml file:

version: "2"

agents:
  root:
    model: anthropic/claude-sonnet-4-5-20250929
    description: A helpful AI assistant with search and file access
    instruction: |
      You are a knowledgeable assistant that helps users with various tasks.
      Be helpful, accurate, and concise in your responses.
      Write your results to disk.
    toolsets:
      - type: mcp
        ref: docker:duckduckgo
      - type: mcp
        command: rust-mcp-filesystem
        args: ["--allow-write", "."]
        tools: ["read_file", "write_file"]

Model Configuration

Define models inline or as named references:

version: "2"

models:
  fast:
    provider: openai
    model: gpt-5-mini
    max_tokens: 4096
  strong:
    provider: anthropic
    model: claude-sonnet-4-5-20250929
    max_tokens: 64000

agents:
  root:
    model: strong
    description: Main orchestrator
    sub_agents: [researcher, writer]

  researcher:
    model: fast
    description: Finds information
    toolsets:
      - type: mcp
        ref: docker:duckduckgo

  writer:
    model: strong
    description: Writes polished content

MCP Tool Integration

Docker MCP Gateway

Use containerized MCP servers via Docker's MCP Gateway:

toolsets:
  - type: mcp
    ref: docker:duckduckgo      # Search
  - type: mcp
    ref: docker:fetch           # HTTP fetch
  - type: mcp
    ref: docker:github          # GitHub API

Read the full file on GitHub · 175 lines

Files

What ships with it

12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 175 lines · 94 tokens per session scan A 796a5678df4f

Subscribe to this mod's changes

cagent is a skill published in the GitHub repository Tyler-R-Kendrick/agent-skills (13 stars, last pushed 5mo ago), licensed MIT. It adds 94 tokens to every session and 1,251 once invoked, about $0.0004 per session on Opus 5.5. 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.

Building agents Containers DevOps and cloud

cagent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cagentTyler-R-Kendrick/agent-skills	Skill	13	5mo ago	MIT	A	94	Claude Code
deploy-docker-composeomnigent-ai/omnigent	Skill	11k	yesterday	Apache-2.0	A	84	Claude Code, Codex
bdd-container-updateNVIDIA-AI-Blueprints/video-search-and-summarization	Skill	2.0k	yesterday	Apache-2.0	A	117	Cursor
securing-kubernetes-on-cloudxalgorix/xalgorix	Skill	1.3k	2d ago	Apache-2.0	A	80	Claude Code, Codex
detecting-privilege-escalation-in-kubernetes-podsxalgorix/xalgorix	Skill	1.3k	2d ago	Apache-2.0	A	40	Claude Code, Codex
docker-socket-mountPurpleAILAB/Decepticon	Skill	6.5k	8d ago	Apache-2.0	B	67	Claude Code
k8s-networkingrohitg00/kubectl-mcp-server	Skill	968	15d ago	MIT	A	34	Claude Code, Codex