---
title: "Docker Agent Configuration: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/docker-agent-config/
description: "Build Docker Agent configurations with per-agent toolsets, provider credentials, delegated teams and bounded autonomy."
---

# Docker Agent Configuration: review, setup & limitations · Undominated.ai

> Build Docker Agent configurations with per-agent toolsets, provider credentials, delegated teams and bounded autonomy.

[← Explore all skills](/skills/)

AGENT DEVELOPMENT / docker

# Docker Agent Configuration

Build Docker Agent configurations with per-agent toolsets, provider credentials, delegated teams and bounded autonomy.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/docker/skills/tree/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-config)

SOURCE REVIEW

 Reviewed 2026-10-15
 Evidence 5 linked sources
 Publisher docker
 Licence [Apache-2.0 ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/LICENSE)
 Revision f79172733725
 [Read what was—and wasn’t—checked ↓](#review)

“Use this skill when creating or editing an agent.yaml (or .yml/.hcl) configuration file for Docker Agent (cagent), including defining agents, models/providers, built-in or MCP toolsets, multi-agent teams with sub_agents. Even if the user just says they want to "build an AI agent with Docker", "make a coding agent config", "add a tool to my agent", or "set up a team of agents", this skill applies. Covers agent properties (model, instruction, toolsets, sub_agents, fallback), the models/providers sections, built-in toolsets (filesystem, shell, think, todo, memory, fetch), MCP toolset references, and named commands.”

 [docker · upstream description ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-config/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - It writes a Docker Agent agent.yaml, including models, toolsets, and sub-agents, and it does not cover running or serving the agent.
- API keys stay out of the file, and a local dmr model is the path that needs no credential.
- Specifies configuration-file ownership separately from run/serve workflows.
- Includes a reviewer restricted with readonly rather than assuming a filesystem toolset is read-only.

### A good fit for

 - Creating an agent.yaml for Docker Agent without putting a provider token in the file
- Marking a reviewer agent readonly so its toolsets cannot mutate
- Create a coordinator/coder/reviewer agent team.
- Connect a custom model endpoint or MCP toolset while keeping credentials out of prompts.

### Weigh up before choosing

 - The skill does not cover docker agent run, serve, or share.
- redact_secrets is described as defense in depth, not a guarantee.
- ${env.VAR} expands into prompt text sent to the model, so interpolation is only for non-sensitive context.
- This review did not execute the resource.
- Configuration compatibility depends on Docker Agent; legacy cagent paths remain in use.
- Secret redaction only recognizes supported patterns; environment interpolation can still disclose sensitive text to models.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - skills/docker-agent-config/SKILL.md
- skills/docker-agent-config/assets/team-agent.yaml
- README.md
- LICENSE

### Our findings

 - The overview says the skill owns agent.yaml and does not cover invoking the CLI or serving the config.
- Provider credentials come from the environment or docker agent setup; the file says never to hardcode an API key.
- dmr is the local provider with no API key, for agents that must not send data to a third party.
- readonly true restricts every toolset to read-only tools, and the skill does not itself run the agent.
- Inspected team asset gives shell access to coder and readonly filesystem access to reviewer.
- Definition distinguishes isolated sub-agent delegation from a named command that switches the active agent.

### Not established by this review

 - The resource was not executed and its tools were not called.
- No skill execution, authenticated service operation, or outcome benchmark was performed.
- Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/README.md)

DOCUMENTED COMMAND

 npx skills add docker/skills/skills/docker-agent-config Copy command ↗

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

 Optional: install the reviewed revision

Keeps the original source and installer version where recorded, while leaving your AI tools and installation scope for you to choose.

 npx skills add https://github.com/docker/skills/tree/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-config Copy reviewed-revision command ↗ - Install the pinned skill directory interactively, retaining its bundled references and scripts.
- Inspect the actual CLI version and choose model/provider entries and toolsets for each agent.
- Set appropriate iteration limits, retain reviewer readonly and configure credentials through supported mechanisms.

### Before you start

 - Docker Agent CLI plugin
- Chosen provider/model access or local model runtime

### Compatibility

Agents supporting directory-based SKILL.md instructions

### Local instructions; runtime access depends on the workflow

 - Filesystem/shell/MCP toolsets grant real capabilities; each agent needs its own scoped configuration.
- Cloud providers receive prompt/tool content and may charge for requests.

### Cost model

The skill is free; service usage and infrastructure can incur charges.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Pinned skill definition ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-config/SKILL.md) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-config/SKILL.md Supports: summary, whySelected, bestFor, limitations, install, access, review
- [Publisher repository and installation guidance ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/README.md) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/README.md Supports: install
- [Apache-2.0 licence ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/LICENSE) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/LICENSE Supports: license
- [skills/docker-agent-config/assets/team-agent.yaml ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-config/assets/team-agent.yaml) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-config/assets/team-agent.yaml Supports: review, limitations, access, install
- [2026-10-15 C2-W20 source re-review at the existing pin ↗](https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-config/SKILL.md) Checked 2026-10-15 https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-config/SKILL.md Supports: upstreamDescription, review.notTested, review.reviewedAt

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Docker Agent run ↗ Pins Docker's skill for docker agent run, including the safety modes and the exception that a local stdio MCP server stays outside the sandbox VM.](/skills/docker-agent-run/)[### Testing Handbook Skill Generator ↗ Maintainer workflow that reads sections of the Trail of Bits Testing Handbook (appsec.guide) and writes or refreshes the matching Claude Code skills inside the trailofbits/skills testing-handbook-skills plugin.](/skills/trailofbits-testing-handbook-generator/)[### Agent Development for Claude Code Plugins ↗ Explains how to write a Claude Code plugin agent file (frontmatter, trigger description, system prompt) and ships a Bash script that checks one agent file.](/skills/anthropic-agent-development/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
