By otaviof
Specialized agents and skills for Go development, infrastructure automation, and workflow management
Create and optimize specialized Claude Code agents. Expertise in agent design, prompt engineering, domain modeling, and best practices. Use PROACTIVELY when designing new agents or improving existing ones.
Shared DevSecOps, secrets management, and container build standards for CI/CD agents (tekton-expert, gha-expert).
Shared policies for Claude Code extensibility. Referenced by agent-expert, skill-expert.
Manages context across multiple agents and long-running tasks. Use PROACTIVELY when coordinating complex multi-agent workflows or when context needs to be preserved across multiple sessions. MUST BE USED for projects exceeding 10k tokens.
Behavioral guardrails for all agents. Prevents scope creep, overengineering, and silent assumptions.
5-element persona framework template for creating Claude Code agents
Extract readable web content, removing navigation/ads to save tokens.
Run Ginkgo BDD tests with Kubernetes-aligned conventions.
Run Go verification pipeline (build + test + vet + lint).
Go code quality standards, idioms, and YAGNI/KISS development principles.
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.
gosmithA Claude Code plugin providing specialized agents and skills for Go development, infrastructure, and workflow automation.
Add the marketplace and install the plugin:
/plugin marketplace add otaviof/gosmith
/plugin # Search and install "gosmith"
As well, non-interactively with the command line:
claude plugin marketplace add otaviof/gosmith
claude plugin install gosmith
Test the plugin locally without installing:
claude --plugin-dir ${PWD}
| Type | Count | Examples |
|---|---|---|
| Agents | 11 | go-architect, go-developer, tekton-expert, gha-expert |
| Skills | 10 | /go-check, /go-cover, /ginkgo, /jira, /make, /defuddle, /verify, /pr-comments |
flowchart LR
go-architect["go-architect<br/>Design"]
go-developer["go-developer<br/>Implement"]
go-tester["go-tester<br/>Test"]
go-reviewer["go-reviewer<br/>Review"]
go-code["/go-code<br/>Standards"]
verify["/verify<br/>Check"]
pr-comments["/pr-comments<br/>Triage"]
go-architect -->|PLAN.md| go-developer
go-developer -->|Code| go-tester
go-tester -->|Tests Pass| go-reviewer
go-reviewer -->|Approved| Merge([Merge])
go-reviewer -.->|Comments| pr-comments -.->|Fixes| go-developer
go-developer & go-reviewer -.->|invoke| go-code
go-architect & go-developer & go-tester & go-reviewer -.-> verify
After installing the plugin, agents and skills are available in Claude Code.
Invoke agents with @agent-name or the fully qualified @gosmith:agent-name:
# Design a new feature
@gosmith:go-architect Design a caching layer with Redis backend
# Implement the plan
@gosmith:go-developer Implement caching layer per PLAN.md
# Write tests
@gosmith:go-tester Write tests for caching layer, target 80% coverage
# Review before merge
@gosmith:go-reviewer Review caching implementation for security and correctness
Invoke skills with /skill-name or /gosmith:skill-name:
# Run Go verification pipeline
/gosmith:go-check
# Generate coverage report
/gosmith:go-cover ./...
# Fetch Jira ticket as markdown
/gosmith:jira PROJ-1234
# Run Makefile target
/gosmith:make test
# List all agents from this plugin
claude agents | grep gosmith
# List all skills from this plugin
claude skills | grep gosmith
| Agent | Purpose |
|---|---|
| go-architect | Creates PLAN.md blueprints with interfaces, data models, and steps. Invoke first for design decisions. |
| go-developer | Implements production Go code from plans or handles simple tasks directly. |
| go-tester | Writes adversarial tests, fuzz tests, and benchmarks. Validates against PLAN.md contracts. |
| go-reviewer | Reviews PRs for correctness, security, and plan compliance. Invoke before merging. |
| Agent | Purpose |
|---|---|
| openshift-expert | Kubernetes and OpenShift cluster specialist for platform administration and security. |
| tekton-expert | Tekton and Kubernetes-native CI/CD specialist for pipelines, GitOps, and automated delivery. |
| gha-expert | GitHub Actions specialist for workflows, CI/CD automation, and GitHub-native DevSecOps. |
| Agent | Purpose |
|---|---|
| context-manager | Maintains state across multi-agent workflows and sessions. Use for complex projects exceeding 10k tokens. |
| agent-expert | Creates and optimizes new Claude Code agents. Use when designing custom agents. |
| skill-expert | Designs and optimizes token-efficient Claude Skills. Use when creating or managing skills. |
| tech-writer | Produces README, API docs, and architecture documentation. Use after implementation is stable. |
These are referenced by other agents, not invoked directly:
npx claudepluginhub otaviof/gosmith --plugin gosmithMaster Go 1.25+ development with modern patterns, advanced concurrency, performance optimization, and production-ready microservices. Skills: golangci-lint, goreleaser, go-tool (Go 1.24+ tool dependencies), go-blackbox (black box test enforcement), go-structure (project layout), GitHub Actions, GitLab CI. MCP: context7
Go development following Google Go style guide with Go 1.25+ features and best practices
Run golang codebase related commands and tools
AI Agent Skills for production-ready Go projects
Go-specific development tools with idiomatic best practices
GitHub Actions CI/CD - workflows, authentication, inspection