Clean Workshop
- 1 installs
- 126 repo stars
- Updated August 4, 2026
- aws-samples/sample-amazon-bedrock-agentcore-onboarding
clean-workshop is a Claude Code skill that tears down the AWS resources created by the Amazon Bedrock AgentCore onboarding workshop in reverse dependency order.
About
This skill tears down the AWS resources created by the Amazon Bedrock AgentCore onboarding workshop. A developer runs it after finishing the workshop to remove agent runtimes, ECR repositories, memory instances, OAuth2/Cognito providers, gateways, and policy engines. It cleans resources in reverse dependency order and can target specific steps or clean everything.
- Cleans up AWS resources across 7 workshop steps in reverse dependency order
- Runs per-step clean_resources.py scripts guarded by config-file existence checks
- Supports selective cleanup by step number or full teardown
Clean Workshop by the numbers
- 1 all-time installs (skills.sh)
- Ranked #930 of 1,039 Cloud & Infrastructure skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
clean-workshop capabilities & compatibility
- Capabilities
- devops · ci cd
- Works with
- aws
- Use cases
- devops
- Runs
- Runs locally
- Pricing
- Bring your own API key
What clean-workshop says it does
Clean up AWS resources created by the AgentCore onboarding workshop.
Resources MUST be cleaned in reverse dependency order to avoid errors:
npx skills add https://github.com/aws-samples/sample-amazon-bedrock-agentcore-onboarding --skill clean-workshopAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 126 |
| Last updated | August 4, 2026 |
| Repository | aws-samples/sample-amazon-bedrock-agentcore-onboarding ↗ |
What it does
Tear down all AWS resources created by the Bedrock AgentCore onboarding workshop, in dependency-safe order.
Who is it for?
Removing AWS resources left behind after running the AgentCore onboarding workshop.
Skip if: Running or scaffolding workshop steps, or cleaning non-workshop AWS accounts.
When should I use this skill?
Someone wants to tear down, clean up, or remove AgentCore workshop resources.
What you get
All targeted workshop AWS resources are deleted with a per-step success/failure summary.
- Deleted AWS resources
- Per-step cleanup summary
By the numbers
- Cleans 7 workshop steps (02, 03, 05, 06, 07, 08, 09)
Files
Clean Workshop Resources
Clean up AWS resources created by the AgentCore onboarding workshop.
Usage
/clean-workshop— Clean all workshop resources (09, 08, 07, 06, 05, 03, 02)/clean-workshop 02— Clean only step 02 (runtime)/clean-workshop 02 03— Clean steps 02 and 03/clean-workshop 05 06 07— Clean steps 05, 06, and 07/clean-workshop 08 09— Clean steps 08 and 09
Arguments
$ARGUMENTS contains space-separated step numbers to clean (e.g., 02 03 07). If empty, clean ALL steps that have resources.
Steps with Cleanable Resources
Only these steps create AWS resources that need cleanup:
| Step | Directory | Resources | Config File |
|---|---|---|---|
| 02 | 02_runtime/ | Agent runtime, ECR repository, config files | .bedrock_agentcore.yaml |
| 03 | 03_memory/ | Memory instances (prefix: cost_estimator_memory) | None |
| 05 | 05_evaluation/ | Custom evaluator (name: cost_estimator_tool_usage) | None |
| 06 | 06_identity/ | OAuth2 provider, Cognito user pool/client/domain, runtime | inbound_authorizer.json |
| 07 | 07_gateway/ | Gateway targets, gateway, config files | outbound_gateway.json |
| 08 | 08_policy/ | Policy engine, policies, Cognito app clients | policy_config.json |
| 09 | 09_browser_use/ | Browser sessions (ephemeral, auto-expire) | None |
Dependency Order (CRITICAL)
Resources MUST be cleaned in reverse dependency order to avoid errors: 1. 09_browser_use first (independent, ephemeral sessions) 2. 08_policy second (depends on 07_gateway) 3. 07_gateway (depends on 06_identity) 4. 06_identity (depends on 02_runtime) 5. 05_evaluation (independent) 6. 03_memory (independent) 7. 02_runtime last (other steps depend on it)
Execution
For each step to clean, run:
cd <project_root>/<step_directory> && uv run python clean_resources.pyBefore cleaning each step:
1. Check if the config file exists (indicates resources were created) 2. If no config file, skip that step with a message 3. Run clean_resources.py from within the step directory (scripts use relative paths) 4. Report success or failure for each step
Error handling:
- If a step fails, log the error and continue with remaining steps
- Report a summary at the end showing which steps succeeded/failed
- Common errors: ResourceNotFoundException (already deleted), config file missing (never created)
Implementation
1. Parse $ARGUMENTS to determine which steps to clean. If empty, use all: 09 08 07 06 05 03 02 2. Sort the requested steps in correct cleanup order: 09, 08, 07, 06, 05, 03, 02 3. Create a task list tracking each step 4. For each step (in order): a. Check if the step directory and config file exist b. If resources exist, run clean_resources.py from that directory c. Mark task as completed 5. Print a final summary
Related skills
Azure AiIntegrates Azure AI Content Safety, Document Intelligence, Speech, and Search services into Java-based agents and applications.495k1.4kAzure PrepareGenerate the exact Azure infrastructure files, Dockerfiles, and azure.yaml configuration needed before deploying any new or modernized application.494k1.4kAzure StorageConnect agents and applications to Azure Blob Storage, File Shares, Queues, Tables, and Data Lake without leaving the coding environment.494k1.4kAppinsights InstrumentationAutomatically instrument web applications running on Azure App Service with Application Insights for observability without manual configuration.493k1.4kAzure Resource LookupInstantly list, query, and discover any Azure resources across subscriptions without leaving the agent chat.493k1.4kAzure AigatewayConfigure Azure API Management as a secure, governed gateway for routing traffic to LLMs, MCP servers, and agent tools.493k1.4kFAQ
Which workshop steps have cleanable AWS resources?
Steps 02 (runtime/ECR), 03 (memory), 05 (evaluation), 06 (identity/Cognito), 07 (gateway), 08 (policy), and 09 (browser sessions).
In what order does it clean resources?
Reverse dependency order: 09, 08, 07, 06, 05, 03, then 02 last.