docker-mcp: Instructions file for Codex

AGENTS.md

docker-mcp AGENTS.md is an instructions file for Codex, OpenCode from thargy/docker-mcp. It costs 862 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for an AI agent using docker-mcp, a tool for managing Docker containers and Docker Compose projects.

In plain words
What is it for?
It helps agents manage containers, run commands inside them, retrieve logs and statistics, and control Compose services.
Why use it?
It explains the available actions and required inputs, reducing mistakes when an agent lists, starts, stops, inspects, or troubleshoots Docker workloads.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is thargy/docker-mcp's own configuration. It tells Codex and OpenCode how to work on docker-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything docker-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thargy/docker-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/thargy/docker-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/thargy/docker-mcp

Made for: Codex, OpenCode.

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.

agentmods badge for docker-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thargy/docker-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/thargy/docker-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/thargy/docker-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thargy/docker-mcp/agents-md/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.

agentmods 80×15 button for docker-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thargy/docker-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thargy/docker-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 862 This file is loaded in full into every session.
When invoked 862 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00862 $0.00862
Opus 5.5 $0.00345 $0.00345
Sonnet 5.5 $0.00172 $0.00172
Haiku 4.5 $0.00086 $0.00086

Measured 2mo ago against content hash ec3c676efe32, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docker-mcp AGENTS.md 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.

AGENTS.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md: LLM Agent Guide for docker-mcp

This guide explains the tool schemas, action discriminators, and best practices for AI agents invoking docker-mcp.


1. Tool Reference & Action Discriminators

1. docker_containers

  • Schema:
    • action: 'list' | 'inspect' | 'start' | 'stop' | 'restart' | 'logs' | 'stats' | 'exec' | 'remove'
    • id: Container ID or exact name (required for inspect, start, stop, restart, logs, stats, exec, remove)
    • pattern: Regex or substring to filter container names/images on list
    • all: Include non-running (exited/paused) containers on list (default true)
    • tail: Number of lines of logs to retrieve on logs (default 100)
    • timestamps: Include RFC3339 timestamps on logs (default true)
    • command: Array of command strings to execute on exec (e.g. ["ls", "-la", "/app"])
    • force: Force removal or stop (default false)

2. docker_compose

  • Schema:
    • action: 'ps' | 'up' | 'down' | 'restart' | 'logs'
    • project: Compose project name (derived from com.docker.compose.project label)
    • services: Array of specific service names to target
    • tail: Number of lines for aggregated logs

3. docker_images

  • Schema:
    • action: 'list' | 'inspect' | 'pull' | 'prune' | 'remove'
    • image: Image tag or digest (e.g. node:22-alpine or sha256:...)
    • all: Include intermediate image layers on list (default false)
    • force: Force removal (default false)

4. docker_volumes

  • Schema:
    • action: 'list' | 'inspect' | 'create' | 'prune' | 'remove'
    • name: Volume name
    • driver: Storage driver (e.g. local)
    • labels: Key-value label pairs
    • force: Force remove volume

5. docker_networks

  • Schema:
    • action: 'list' | 'inspect' | 'create' | 'prune' | 'remove'
    • name: Network name or ID
    • driver: Network driver (bridge, overlay, macvlan)
    • internal: Restrict external network gateway access (default false)

Read the full file on GitHub · 66 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. 2mo ago First seen · 66 lines · 862 tokens per session scan A ec3c676efe32

Subscribe to this mod's changes

docker-mcp AGENTS.md is an instructions file published in the GitHub repository thargy/docker-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 862 tokens to every session, about $0.0034 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.

Related

docker-mcp AGENTS.md compared with instructions from other repositories

docker-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
docker-mcp AGENTS.mdthargy/docker-mcpInstructions file02mo agoMITA862Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode