How do I install the Docker Compose Drift skill?

Run npx skillmds@latest add knuckles-team/docker-compose-drift in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Docker Compose Drift safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Docker Compose Drift?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Docker Compose Drift free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Docker Compose Drift?

Knuckles-Team (@knuckles-team) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Docker Compose Drift by knuckles-team

Name: Docker Compose Drift
Author: Knuckles-Team

Docker Compose Drift

Detect drift between a host's running Docker Compose/Swarm state and its git configuration, then compile and redeploy the declared configuration where the operator confirms remediation. Use when a stack's live state may have diverged from its source of truth; this workflow never redeploys without the drift report as evidence.

Knuckles-Team 7b73238 2 files · 1.7 KB Updated Sep 17, 2026

File contents

Docker Compose Drift Workflow

Compose the named atomic skills without adding new comparison logic here.

Inputs

Provide the target host(s)/stack(s) and the git configuration reference.

Steps

Step 0: docker-compose-drift-detector [skill: docker-compose-drift-detector]

Invoke $docker-compose-drift-detector with the workflow inputs to compare running state against git configuration.

Expected: drift_report

Step 1: docker-compose-operator [skill: docker-compose-operator] [depends_on: Step 0]

Invoke $docker-compose-operator with drift_report to compile and redeploy the declared configuration for confirmed drift.

Expected: remediation_result

Output

Return drift_report and remediation_result.

Execution

Run first: Step 0 — $docker-compose-drift-detector.
After level 0: Step 1 — $docker-compose-operator.

Execution: If graph-os is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.

Frequently asked questions