By smartnews
EPCC (Explore-Plan-Code-Commit) systematic development workflow with 12 specialized agents for exploration, planning, coding, and commit phases
Code phase of EPCC workflow - implement with confidence
Commit phase of EPCC workflow - finalize with confidence
Explore phase of EPCC workflow - understand thoroughly before acting
Plan phase of EPCC workflow - strategic design before implementation
Use PROACTIVELY during requirements gathering and before technical implementation begins. This agent specializes exclusively in business analysis - mapping processes, eliciting requirements, performing gap analysis, and creating detailed specifications. Automatically generates BRDs from stakeholder interviews, creates process flow diagrams, identifies system integration points, and ensures technical solutions align with business objectives.
Use PROACTIVELY when inheriting legacy codebases or before making changes to undocumented systems. This agent specializes exclusively in reverse-engineering complex code - tracing data flows, uncovering hidden dependencies, mapping system architecture, and identifying technical debt. Automatically generates comprehensive system documentation from code analysis, reveals undocumented business logic, and creates dependency graphs for safe refactoring.
Use PROACTIVELY before every production deployment to ensure zero-downtime releases and instant rollback capability. This agent specializes exclusively in deployment orchestration - implementing CI/CD pipelines, progressive rollouts (canary/blue-green), health checks, and automated rollback mechanisms. Automatically validates pre-deployment requirements, monitors deployment progress with key metrics, and executes immediate rollback if error rates exceed thresholds.
MUST BE USED whenever code is created or modified to maintain living documentation. This agent specializes exclusively in generating and maintaining technical documentation - creating API references, architecture diagrams, README files, and inline comments that stay synchronized with code. Automatically detects undocumented code, generates comprehensive documentation with working examples, and ensures all public APIs have complete docstrings with usage examples.
MUST BE USED when implementing performance optimizations based on profiling data. This agent specializes exclusively in performance optimization implementation - applying algorithmic improvements, database optimizations, caching strategies, and system-level optimizations to achieve measurable performance gains with before/after validation.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This guidance enables organizations to provide secure, centralized access to Claude models through Amazon Bedrock using existing enterprise identity providers. By integrating with OIDC providers like Okta, Azure AD, and Auth0, organizations can maintain their current authentication workflows while giving users seamless access to Claude Code without managing individual API keys.
See Prerequisites including setting up supported OIDC providers.
# Clone the repository
git clone https://github.com/aws-solutions-library-samples/guidance-for-claude-code-with-amazon-bedrock
cd guidance-for-claude-code-with-amazon-bedrock/source
# Install dependencies
poetry install
# Run interactive setup wizard
poetry run ccwb init
# Deploy infrastructure
poetry run ccwb deploy
# Create distribution package for users (all platforms)
poetry run ccwb package --target-platform=all
# Create and distribute package via secure URL (Optional)
poetry run ccwb distribute
# Test package locally
poetry run ccwb test
# Generate secure distribution URL (expires in 48 hours)
poetry run ccwb distribute
# Or specify custom expiration
poetry run ccwb distribute --expires-hours=72
You are responsible for the costs of AWS services while running this guidance. If you decide that you no longer need the guidance, please ensure that infrastructure resources are removed.
poetry run ccwb destroy
This guidance implements an Enterprise Authentication Pattern that enables organizations to securely integrate Claude Code with their existing identity infrastructure. The pattern provides:
Step-by-step flow for end-users:

npx claudepluginhub smartnews/guidance-for-claude-code-with-amazon-bedrock --plugin epcc-workflowComplete Diataxis documentation framework with 12 specialized agents for tutorials, how-tos, references, explanations, and analysis
Product and technical requirements gathering with expert technology evaluation guidance for informed decision-making
Deployment orchestration and compliance automation with progressive rollout strategies
Systematic debugging and problem-solving with ask-for-help mechanism to prevent spinning wheels and ensure methodical issue resolution
Security scanning, auditing, and compliance validation with 4 specialized agents for automated security gates and analysis
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
The Claude Code knowledge system — 380+ skills, 182+ agents, 100+ commands, 40 hooks, 32 rules, and workflows.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.