Use when orchestrating a complete 8-phase development iteration. Activated by /iterate command or when user asks to follow the iteration workflow.
Orchestrates an 8-phase development iteration with parallel subagents and TDD.
npx claudepluginhub kennard123661/kenkenmain-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
This skill activates when:
/iterate <task>Announce: "I'm using the iteration-workflow skill to orchestrate this task through all 8 mandatory phases."
Phase 1: Brainstorm -> superpowers:brainstorming + N parallel subagents
Phase 2: Plan -> superpowers:writing-plans + N parallel subagents
Phase 3: Implement -> superpowers:subagent-driven-development + N subagents
Phase 4: Review -> superpowers:requesting-code-review (3 rounds)
Phase 5: Test -> make lint && make test
Phase 6: Simplify -> code-simplifier agent
Phase 7: Final Review -> @codex-high MCP review (3 rounds)
Phase 8: Codex -> @codex-xhigh MCP final validation
State file: .agents/iteration-state.json
Initialize at start:
{
"version": 1,
"task": "<task description>",
"startedAt": "<ISO timestamp>",
"currentPhase": 1,
"phases": {
"1": { "status": "in_progress", "startedAt": "<timestamp>" },
"2": { "status": "pending" },
"3": { "status": "pending" },
"4": { "status": "pending" },
"5": { "status": "pending" },
"6": { "status": "pending" },
"7": { "status": "pending" },
"8": { "status": "pending" }
}
}
Update state after each phase transition.
Purpose: Explore problem space, generate ideas, clarify requirements
Required Skill: superpowers:brainstorming + superpowers:dispatching-parallel-agents
Actions:
in_progress in state filesuperpowers:dispatching-parallel-agents:
superpowers:brainstorming process:
docs/plans/YYYY-MM-DD-<topic>-design.mdExit criteria:
Transition: Mark Phase 1 complete, advance to Phase 2
Purpose: Create detailed implementation plan with bite-sized tasks including tests
Required Skill: superpowers:writing-plans + superpowers:dispatching-parallel-agents
Actions:
in_progresssuperpowers:writing-plans format:
docs/plans/YYYY-MM-DD-<feature-name>.mdPlan header must include:
# [Feature Name] Implementation Plan
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
**Goal:** [One sentence describing what this builds]
**Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries]
**Test Strategy:** [Testing approach and frameworks]
---
Exit criteria:
Transition: Mark Phase 2 complete, advance to Phase 3
Purpose: TDD-style implementation following the plan
Required Skill: superpowers:subagent-driven-development + superpowers:test-driven-development
Required Plugins: LSP plugins for code intelligence
Actions:
in_progresssuperpowers:subagent-driven-development process:
You have access to LSP (Language Server Protocol) tools:
- mcp__lsp__get_diagnostics: Get errors/warnings for a file
- mcp__lsp__get_hover: Get type info and documentation at position
- mcp__lsp__goto_definition: Jump to symbol definition
- mcp__lsp__find_references: Find all references to a symbol
- mcp__lsp__get_completions: Get code completions at position
Use LSP tools to:
- Check for errors before committing
- Understand existing code via hover/go-to-definition
- Find all usages before refactoring
b. Answer any questions from subagent
c. Subagent follows superpowers:test-driven-development:
mcp__lsp__get_diagnostics to check for errorsmake lint && make test to verify all tests passNote: Implementation subagents run sequentially (to avoid file conflicts), but reviewer subagents can run in parallel.
Exit criteria:
make lint && make test passTransition: Mark Phase 3 complete, advance to Phase 4
Purpose: Code review with 3 mandatory rounds
Required Skill: superpowers:requesting-code-review
Actions:
in_progressBASE_SHA=$(git merge-base HEAD main)
HEAD_SHA=$(git rev-parse HEAD)
superpowers:requesting-code-review
b. Provide:
Exit criteria:
Transition: Mark Phase 4 complete, advance to Phase 5
Purpose: Run lint and test suites
Actions:
in_progressmake lint
make test
Exit criteria:
make lint passesmake test passesTransition: Mark Phase 5 complete, advance to Phase 6
Purpose: Reduce code bloat using code-simplifier plugin
Required Plugin: code-simplifier:code-simplifier (from claude-plugins-official)
Actions:
in_progressTask(
description: "Simplify modified code",
prompt: "Review and simplify code modified in this iteration. Focus on clarity and maintainability while preserving functionality.",
subagent_type: "code-simplifier:code-simplifier"
)
Exit criteria:
Transition: Mark Phase 6 complete, advance to Phase 7
Purpose: Final review focused on merge readiness using Codex high reasoning
Required Tool: mcp__codex-high__codex
Actions:
Mark Phase 7 as in_progress
For round in [1, 2, 3]:
a. Invoke mcp__codex-high__codex with review prompt:
Review round {N}/3 for merge readiness. Run these commands first:
1. make lint
2. make test
Focus on:
- Documentation accuracy
- Edge cases and error handling
- Test coverage completeness
- Code quality and maintainability
- Merge readiness
Report findings with severity (HIGH/MEDIUM/LOW) and file:line references.
b. Categorize Codex findings:
Document findings in state
Exit criteria:
Transition: Mark Phase 7 complete, advance to Phase 8
Purpose: Final validation with OpenAI Codex extra-high reasoning
Required Tool: mcp__codex-xhigh__codex
Actions:
Mark Phase 8 as in_progress
Invoke mcp__codex-xhigh__codex with final validation prompt:
Final validation review. Run these commands first:
1. make lint
2. make test
This is the FINAL check before merge. Be thorough.
Report findings with severity (HIGH/MEDIUM/LOW) and file:line references.
Focus on:
- Correctness and logic errors
- Idempotency of operations
- Documentation accuracy
- Test coverage gaps
- Security concerns
- Edge cases missed in earlier reviews
Address any HIGH severity issues
Re-run Codex-xhigh if significant changes made
Exit criteria:
Transition: Mark Phase 8 complete
After Phase 8:
superpowers:finishing-a-development-branch for merge prepIf iteration was interrupted:
.agents/iteration-state.jsoncurrentPhase fieldNever:
If blocked: