coordinating-multi-space-devops-agent

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: analysis, automation, aws-devops, cloud, multi-agent.

What it does

Coordinate the AWS DevOps Agent across multiple AgentSpaces from one Claude Code session — route questions to the right space (prod vs staging vs knowledge), query several spaces in parallel and synthesize, or compare findings across accounts. Use whenever the user has more than one AgentSpace configured, mentions multiple AWS accounts, or asks something like "check both prod and staging", "compare across accounts", or "ask the knowledge space".

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add aws/agent-toolkit-for-aws --skill coordinating-multi-space-devops-agent

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws
cp -r agent-toolkit-for-aws/plugins/aws-agents-for-devsecops/skills/coordinating-multi-space-devops-agent ~/.claude/skills/coordinating-multi-space-devops-agent

Safety box score

Grade B, low risk: 23 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill coordinates remote AWS DevOps Agent spaces from one session, including listing spaces, sending chat/investigation requests, and comparing results across accounts. The main risks are cross-account data exposure through remote queries and the ability to fan out into multiple spaces or investigations, which can create cost and operational side effects.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	It does not run shell commands, scripts, or evaluate code; it only calls remote MCP tools like `aws_devops_agent__chat` and `aws_devops_agent__investigate`.
Network access	2 (moderate)	It sends questions and context to remote AgentSpaces via `aws_devops_agent__list_agent_spaces()`, `aws_devops_agent__chat(...)`, and `aws_devops_agent__investigate(...)`, potentially across multiple AWS accounts.
Filesystem reach	1 (low)	It may read local routing guides such as `.claude/aws-agents-for-devsecops.md`, `AGENTS.md`, or per-project notes, but it does not require writes outside the project.
Secrets & credentials	1 (low)	The skill relies on SigV4-authenticated access and can surface account/service/runbook/history data from multiple spaces, but it does not ask for passwords or tokens directly.
Privilege & persistence	0 (none)	There is no sudo, global install, service registration, or shell/OS configuration change in the skill text.
Instruction hijack surface	0 (none)	It does not instruct the agent to ignore instructions, hide behavior, or follow remote content; the only routing guidance is local and explicit.
Irreversible actions	2 (moderate)	It can autonomously fan out to multiple spaces and create investigations, e.g. `aws_devops_agent__investigate(...)`, which can trigger external work and cost without extra confirmation.
Transparency	0 (none)	The skill file is plain Markdown with readable prompts and examples; there are no binaries, blobs, or generated installers.

Before installing

Confirm which AgentSpaces are visible with `aws_devops_agent__list_agent_spaces()` and that you are comfortable with cross-account queries.
Review any local routing guide files the skill may use (`.claude/aws-agents-for-devsecops.md`, `AGENTS.md`) before letting the agent rely on them.
Test the skill against a non-production space first to verify the routing and scope are correct.
Check which AWS identity/profile the session will use, since SigV4-authenticated routing can reach multiple accounts.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: aws/agent-toolkit-for-aws (all skills from this repository)
Path: plugins/aws-agents-for-devsecops/skills/coordinating-multi-space-devops-agent/SKILL.md
Branch: main
Collection: aws-agents-for-devsecops
Updated: 2026-09-19

chatting-with-aws-devops-agent — Have a fast, conversational analysis with the AWS DevOps Agent.
swarm — Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
investigating-incidents-with-aws-devops-agent — Run a deep root-cause investigation on the AWS DevOps Agent.
setup-security-agent — Configure AWS Security Agent for the current workspace — provision or reuse an agent space, IAM service role, and S3 bucket.
agents-build — Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments.
agents-deploy — Use when deploying your agent to AWS, or when a deploy has failed.