resilience-hub-getting-started

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: aws, resilience, setup, strategy, validation.

What it does

Sets up AWS Resilience Hub v2 from scratch: creates resilience policies with SLO targets, registers systems and user journeys, onboards services with input sources, and runs a first failure mode assessment. Applies when the user wants to get started with Resilience Hub v2, create a policy, onboard a service, or run an assessment — including creating one concrete policy with specific availability/RTO/RPO targets and a DR approach for a single service (even a tier-1 one). Does not apply to FIS experiments or ARC routing controls.

Install

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

npx skills add aws/agent-toolkit-for-aws --skill resilience-hub-getting-started

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/skills/specialized-skills/resilience-skills/resilience-hub-getting-started ~/.claude/skills/resilience-hub-getting-started

Safety box score

Grade C, moderate risk: 35 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 uses the AWS CLI to create and configure Resilience Hub v2 resources in your AWS account, then starts assessments and optionally generates reports. The main blast radius is cloud-side mutation plus exposure of architecture details in assessments/reports; it does not include local scripting, package installs, or filesystem-heavy actions.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It requires running specific `aws resiliencehubv2 ...` commands and polling loops, so the skill executes shell commands with real effects in AWS.
Network access	2 (moderate)	The skill sends configuration and assessment requests to AWS APIs and can export reports to S3, so service data leaves the machine and goes to remote AWS endpoints.
Filesystem reach	0 (none)	There are no steps that read, write, or delete local files outside the skill bundle/working directory; the only file references are to bundled markdown references.
Secrets & credentials	1 (low)	It does not request passwords or tokens, but it explicitly warns that assessment findings and reports can contain sensitive architecture detail and should be access-restricted.
Privilege & persistence	1 (low)	It depends on AWS IAM permissions and an `invokerRoleName` trust relationship for `resiliencehub.amazonaws.com`, but it does not require sudo or local OS privilege changes.
Instruction hijack surface	0 (none)	I found no hidden text, prompt-suppression, or instructions to ignore higher-level rules or follow fetched remote content.
Irreversible actions	3 (high)	The skill automatically creates policies, systems, user journeys, services, input sources, assessments, and reports, which is broad cloud-side action in the customer account.
Transparency	0 (none)	The skill text is plain markdown with explicit AWS CLI commands; there are no binaries, decoded payloads, or unreviewable installers.

Before installing

Verify `aws --version` works and confirm the intended default region, or be ready to add `--region` to every command.
Check that the Resilience Hub invoker role exists and is assumable by `resiliencehub.amazonaws.com` with the expected policy attached.
Decide whether you want assessment findings/reports stored in S3, since they may contain sensitive architecture detail.
If this is your first time, try it in a sandbox AWS account first.

Rated 2026-10-20 by an automated review of 2 files from the skill's repository.

Source

Repository: aws/agent-toolkit-for-aws (all skills from this repository)
Path: skills/specialized-skills/resilience-skills/resilience-hub-getting-started/SKILL.md
Branch: main
Updated: 2026-09-19

arc-region-switch — Answers questions about Amazon Application Recovery Controller (ARC) Region switch including architecture, plans, execution blocks, workflows, triggers.
aws-resilience-lifecycle — Guides the end-to-end AWS resilience lifecycle integrating Resilience Hub v2, Fault Injection Service, and Application Recovery Controller.
resilience-hub-failure-mode-assessment — Runs and interprets AWS Resilience Hub v2 failure mode assessments.
resilience-program-design — Designs a resilience program: how to structure and standardize resilience policies across an organization, team.
aws-security — Covers AWS security services and workflows — Security Hub V2 (OCSF) findings, connectors, aggregators, automation rules, and security posture summaries.
signing-in-to-aws — Gets AWS credentials for CLI/SDK access via `aws login`.