TDD-based feature workflow with 7 phases - loads directly into session (no installation)
View on GitHubdevnogari/devnogari-claude-plugins
feature-workflow
January 23, 2026
Select agents to install to:
npx add-skill https://github.com/devnogari/devnogari-claude-plugins/blob/main/plugins/feature-workflow/skills/feature-workflow/SKILL.md -a claude-code --skill feature-workflowInstallation paths:
.claude/skills/feature-workflow/# Feature Workflow 7-phase TDD feature implementation workflow. Loads directly into session - no file installation required. ## š“ 4 CORE PRINCIPLES (ALWAYS ENFORCED) **These 4 principles are MANDATORY throughout the entire workflow. Violations are BLOCKED.** ### 1ļøā£ USE SUBAGENT (Task Tool) ``` ā BLOCKED: Direct Edit/Write without subagent ā REQUIRED: Task(subagent_type="...") for ALL implementation ``` | Task Type | Subagent | |-----------|----------| | Backend/API | `backend-architect` | | Frontend/UI | `frontend-architect` | | Tests | `quality-engineer` | | Types | `typescript-pro` | | Exploration | `Explore` | ### 2ļøā£ USE LSP (Not grep/glob) ``` ā BLOCKED: grep, glob, Grep, Glob for symbol search ā REQUIRED: LSP tool for code navigation ``` | Task | LSP Operation | |------|---------------| | Find definition | `goToDefinition` | | File symbols | `documentSymbol` | | Project search | `workspaceSymbol` | | Find references | `findReferences` | | Find implementations | `goToImplementation` | ### 3ļøā£ USE TDD (Tests First) ``` ā BLOCKED: Implementation before tests ā REQUIRED: Write tests ā Run (RED) ā Implement ā Run (GREEN) ``` - Phase 2 (Tests) MUST complete before Phase 3 (Implementation) - Tests should FAIL initially (red phase) - Implementation makes tests PASS (green phase) ### 4ļøā£ USE PARALLEL (Concurrent Execution) ``` ā INEFFICIENT: Sequential subagent calls ā REQUIRED: Parallel Task calls when no dependencies ``` ``` # GOOD: Single message with multiple Task calls Task(types) + Task(query-keys) ā Parallel (no dependency) # GOOD: Sequential only when dependent Task(api) ā Task(hooks) ā Sequential (hooks needs api) ``` ### Self-Check (BEFORE EVERY ACTION) ``` ā” Am I using Task tool with subagent? ā If NO, STOP ā” Am I using LSP for code navigation? ā If grep/glob, STOP ā” Did I write tests first? ā If NO, go back to Phase 2 ā” Can these tasks run in parallel? ā If YES, single message with multiple Task calls ``` --- ## Usage ```bash /feature-workfl