How awslabs/agent-plugins works
Agent Plugins for AWS package reusable expertise for AI coding agents: skills guide workflows, MCP servers expose live services, hooks automate guardrails, and references supply supporting knowledge. The documented user journey is to install a plugin, invoke a relevant capability while architecting, deploying, or operating on AWS, and review the generated result. Sampled code shows concrete DSQL query-safety, deployment-diagram processing, and SageMaker data/model workflows. Most plugin workflows are documented but their implementation files are not present in the supplied tree; edges therefore reflect only README statements or visible calls.
Main entry points: safe_query.py Safe SQL builder · transformation.py Dataset transformation · rlvr.py Model fine-tuning · llmaaj_evaluator.py Model evaluation
Components 19
Plugin capabilities
- AWS agent plugins
- Guided skills
- MCP connections
- Hooks and guardrails
- Reference knowledge
Deployment diagrams
- Diagram post-processing
plugins/deploy-on-aws/scripts/lib/post_process_drawio.py - Diagram validation
plugins/deploy-on-aws/scripts/lib/validate_drawio.py - Icon colors and badges
plugins/deploy-on-aws/scripts/lib/fix_icon_colors.py - Step badges
plugins/deploy-on-aws/scripts/lib/fix_step_badges.py
Aurora DSQL
- Safe SQL builder
plugins/databases-on-aws/skills/dsql/mcp/tools/safe_query.py - Aurora DSQL tools
SageMaker AI
- Dataset transformation
plugins/sagemaker-ai/skills/dataset-transformation/code_templates/transformation.py - Transformation helpers
plugins/sagemaker-ai/skills/dataset-transformation/scripts/transformation_tools.py - Model fine-tuning
plugins/sagemaker-ai/skills/finetuning/code_templates/rlvr.py - RLVR reward function
plugins/sagemaker-ai/skills/finetuning/templates/rlvr_reward_function_source_template.py - Model evaluation
plugins/sagemaker-ai/skills/model-evaluation/code_templates/llmaaj_evaluator.py - Model deployment
plugins/sagemaker-ai/skills/model-deployment/code_templates/deploy-oss-bedrock.py - Dataset format detection
plugins/sagemaker-ai/skills/dataset-evaluation/scripts/format_detector.py
Other components
- AI coding agent user
Connections 10
- AI coding agent user → AWS agent plugins: installs and invokes
README.md - AWS agent plugins → Guided skills: packages
README.md - AWS agent plugins → MCP connections: packages
README.md - AWS agent plugins → Hooks and guardrails: packages
README.md - AWS agent plugins → Reference knowledge: packages
README.md - Guided skills → Diagram post-processing: guides diagram work
- Safe SQL builder → Aurora DSQL tools: builds SQL for
plugins/databases-on-aws/skills/dsql/mcp/tools/safe_query.py - Dataset transformation → Transformation helpers: uses helpers
- Model fine-tuning → RLVR reward function: configures reward source
plugins/sagemaker-ai/skills/finetuning/code_templates/rlvr.py - Model evaluation → Model deployment: evaluates then deploys