aws-agents-for-devsecops Claude Code Plugin
Claude Code PluginClaude CodeDevelopmentSecurity, Auth & ComplianceCloud, Deployment & CI/CDMonitoring & ObservabilityThe explanation below is AI-generated. Please verify it against the sources.
This plugin adds a set of Claude Code skills, slash commands, and a remote MCP server connection that let a user drive AWS DevOps Agent and AWS Security Agent for DevSecOps work. According to the README, it supports investigating production incidents, reviewing pull requests for release readiness, running UAT-style release tests, scanning code for vulnerabilities, and executing penetration tests. Access requires AWS SigV4 credentials or an access token, and most investigative or scanning skills are triggered automatically by contextual keywords while setup and chat actions are invoked explicitly. The README also warns that responses returned by the agents are generated text and must not be auto-executed without explicit user approval.
About the service
AWS DevOps Agent and AWS Security Agent are remote AWS services reached through an MCP server; they provide incident investigation, cost/architecture chat, release testing and readiness review, and code/security scanning and remediation capabilities, and require AWS account credentials (SigV4 or an access token) to use.
What you can do with aws-agents-for-devsecops
- Ask AWS DevOps Agent to investigate incidents based on symptoms such as errors or alarms
- Chat with AWS DevOps Agent about cost, architecture, or topology questions
- Run a release readiness review on a pull request before merging
- Execute UI or API release tests for UAT-style validation
- Run full or diff-only code security scans
- Run penetration tests against live endpoints
- Perform STRIDE-based threat modeling on design documents
- Fetch, triage, and remediate security findings
- Coordinate work across multiple AWS AgentSpaces or accounts
- Set up authentication using a bearer token or SigV4