Conversation
Adds Cluster mode to the existing elastic-beanstalk skill: mode routing in SKILL.md, a new references/cluster-mode.md, and scope notes on the two existing references, neither of which applies to Cluster mode.
karancode
requested review from
a team,
arnewouters,
laithalsaadoon and
rshevchuk-git
September 17, 2026 22:27
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds Beanstalk Cluster mode to the existing
elastic-beanstalkskill. Cluster mode runs a containerised application on a managed Amazon EKS Auto Mode cluster. The skill previously covered Standard mode on EC2 only and did not say so, so an agent asked for a Cluster deployment produced Standard mode configuration.This extends the existing skill rather than adding a new one, so mode selection sits with the rest of the Elastic Beanstalk routing.
Related
Changes
New file:
skills/elastic-beanstalk/references/cluster-mode.md— the twelveeksnamespaces, required IAM roles, environment creation, defaults worth setting deliberately, subnets, HTTPS, multi-service discovery and ingress groups, autoscaling, verification, troubleshooting order, immutable settings, costModified:
skills/elastic-beanstalk/SKILL.md— mode routing table, Cluster mode description triggers, existing content scoped as Standard, reference linkskills/elastic-beanstalk/references/platforms.md— scope note: Cluster mode has no platformskills/elastic-beanstalk/references/configuration.md— scope note: none of those namespaces apply to Cluster modeThe mode boundary is stated firmly because a Cluster environment accepts twelve
aws:elasticbeanstalk:eks*namespaces and rejects a classic namespace withInvalidParameterValueExceptionrather than ignoring it, so Standard mode configuration fails at create.Two notes for reviewers.
SKILL.mdgoes from 172 lines ("ideal") to 215 ("good"); holding "ideal" would mean moving existing Standard content intoconfiguration.md, which I left alone — happy to do it if you would prefer. And the parentdeployskill still routes generic containerised workloads to Fargate, so an implicit request that never names Elastic Beanstalk may not reach this mode table; that is a service-selection change and belongs in its own PR.Validation:
dprint check,markdownlint-cli2,validate-references.py,validate-cross-refs.cjs,validate-size.pyandvalidate-urls.pyall clean. Also exercised the skill via--plugin-diragainst three prompts — explicit Cluster request, ambiguous single container, and multi-service — to confirm mode routing and that no Standard-mode namespaces appear in Cluster output.Acknowledgment
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the project license.