Menu
Enumerate AWS compute, storage, network, and IAM resources and write a structured inventory to AWS_STATE_DIR.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
| name | aws-scan-resources |
| description | Enumerate AWS compute, storage, network, and IAM resources and write a structured inventory to AWS_STATE_DIR. |
| model | sonnet |
| effort | medium |
| context | fork |
ASR-1. Verify: aws CLI, AWS_PROFILE, AWS_STATE_DIR.
ASR-2. Enumerate with read-only CLI (pass --profile $AWS_PROFILE --region $AWS_DEFAULT_REGION on every call):
aws ec2 describe-instances --query 'Reservations[].Instances[].{id:InstanceId,state:State.Name,type:InstanceType}'aws ecs list-clusters + aws ecs list-services --cluster <name>aws lambda list-functions --query 'Functions[].{name:FunctionName,runtime:Runtime}'aws s3api list-buckets --query 'Buckets[].Name'aws ec2 describe-volumes --query 'Volumes[].{id:VolumeId,size:Size,state:State}'aws rds describe-db-instances --query 'DBInstances[].{id:DBInstanceIdentifier,engine:Engine}'aws ec2 describe-vpcs, aws ec2 describe-security-groupsaws iam list-users, aws iam list-roles, aws iam list-policies --scope Local
ASR-3. Write raw data to $AWS_STATE_DIR/resources-<YYYYMMDD>.json. Single-region scope.
ASR-4. Write human-readable summary to $AWS_STATE_DIR/resources-<YYYYMMDD>.md:Skip if $AWS_STATE_DIR/resources-<YYYYMMDD>.json exists and is less than 4 hours old.
Conduct a decision-tree interview with the user to lock in requirements, motivation, scope, and non-goals before planning.
Stage 3 of three-stage planning pipeline. Produce a file-level implementation plan via detail-planner/detail-reviewer loop, then get user approval. Inputs are confirmed intent (<session-id>-intent.md) and outline (<session-id>-outline.md) from prior stages.
Edit source code for the current task. Delegates editing and lint/typecheck/self-repair to a subagent.
Plan and write test cases with high reasoning effort. Test iteration runs in a subagent to minimize confirmations.
Explore the codebase to understand existing patterns, constraints, and relevant files before planning.
Investigate git history, docs/history.md, and GitHub issue/PR timeline since the relevant issue opened, to surface changes that may invalidate the issue's premises.