By JamesPrial
Go development workflow with TDD-first parallel agents, failure triage, and automated code quality hooks
Go development workflow - explore, design, implement, review, optimize with parallel agent execution
Lightweight bug fix and refactor workflow — explore, patch, verify
Refactoring workflow — restructure code while preserving behavior (DI, interfaces, DRY, package organization)
Designs features, proposes architectural patterns, and defines component boundaries
Traces code paths, maps architecture, and analyzes dependencies in codebases
Writes production-quality Go code following idiomatic patterns and best practices
Performance and resource analysis agent for Go applications
Researches Go documentation, best practices, and library APIs via web search
Go error handling patterns. Routes to specific patterns.
Go interface design patterns and best practices
Go static analysis. Routes to specific tools.
Go nil safety patterns. Routes to specific traps.
Go testing patterns. Routes to specific patterns.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
TDD-first parallel agents with intelligent failure triage for Claude Code
--tdd) for strict red-green-refactor discipline/install-plugin <marketplace-url>
Run a full parallel implementation workflow:
/implement Add a rate-limited HTTP client with exponential backoff
Run with strict TDD (tests first, verified to fail, then implementation):
/implement --tdd Add a concurrent-safe LRU cache with TTL expiration
Lightweight bug fix or refactor:
/patch Fix the nil pointer dereference in ParseConfig when input is empty
The plugin orchestrates the rest — exploration, design, implementation, testing, review, and optimization happen automatically across specialized agents.
Traditional AI coding writes tests after seeing the implementation, creating tests that mirror the code rather than verify the contract. golang-workflow solves this:
| Test Writer | Implementer | |
|---|---|---|
| Sees | Test specifications (scenarios, error conditions, edge cases) | Architecture design + test expectations (WHAT is tested) |
| Does NOT see | Implementation code | Test code (HOW it's tested) |
| Writes | *_test.go files from specification only | *.go files to satisfy the contract |
The test writer works from the architect's specification — scenario tables, error conditions, edge cases, fuzz targets — without any knowledge of how the code is structured. The implementer knows what behaviors will be tested but not how the tests assert them. This separation produces tests that genuinely verify the contract rather than parroting the implementation.
Each agent has a focused role, specific tools, and the right model tier:
| Agent | Model | Role | Active In |
|---|---|---|---|
| explorer | sonnet | Code investigation, architecture mapping, dependency analysis | Wave 1 |
| architect | opus | Interface design, package structure, test specifications | Wave 1 |
| researcher | sonnet | Web search for Go docs, best practices, library documentation | Wave 1 |
| implementer | sonnet | Writes idiomatic Go code (NOT tests) — has fix mode for targeted repairs | Wave 2 |
| test-writer | opus | Writes tests from specifications only — has fix mode for test iteration | Wave 2 |
| test-runner | sonnet | Executes tests, race detection, coverage, linting, compilation checks | Wave 2, 3 |
| reviewer | opus | Code quality review only (NO test execution) | Wave 2, 3 |
| optimizer | sonnet | Performance analysis, benchmarks, memory profiling | Wave 3 |
| triage | sonnet | Classifies failures as CODE_BUG, TEST_BUG, or CONTRACT_MISMATCH | On failure |
Opus-tier agents handle tasks requiring deeper reasoning (architecture, test design, code review). Sonnet-tier agents handle execution-heavy tasks (exploration, implementation, testing, optimization).
The default mode runs agents in parallel wherever possible, with quality gates that block progression until both tests pass and code review approves.
flowchart TD
W1[Wave 1: Parallel Exploration]
E[Explorer]
A[Architect]
R[Researcher]
W2a[Wave 2a: Parallel Creation]
I[Implementer]
TW[Test Writer]
W2a5[Wave 2a.5: Compilation Check]
W2b[Wave 2b: Quality Gate]
TR[Test Runner]
RV[Reviewer]
T{Triage}
W3[Wave 3: Final Review]
TR2[Test Runner]
RV2[Reviewer]
O[Optimizer]
W4[Wave 4: Verification]
npx claudepluginhub jamesprial/claude-plugins --plugin golang-workflowGit operations and GitHub CLI agents for version control workflows
Create custom slash commands for Claude Code with syntax, patterns, and helper scripts
Captures TodoWrite tool usage and saves to timestamped history file with configurable log location (default: .claude/todos.json)
Security hooks to detect and block potential secrets in git commits
Claude Code documentation for plugins, hooks, MCP servers, skills, and settings
Go-specific development tools with idiomatic best practices
gopilot is your Go copilot - a skill for writing idiomatic Go code, covering design patterns, error handling, testing, concurrency, generics, and stdlib patterns up to Go 1.26.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.
Go development following Google Go style guide with Go 1.25+ features and best practices
Go code review and development skills covering architecture, middleware, data persistence, concurrency, and framework-specific patterns for BubbleTea, Wish SSH, and Prometheus.
Enhances code agents with Go best practices covering performance, modern syntax, generics, patterns, testing, error handling, and concurrency.