Phase Doc — AI skill for Claude Code
Generate the Execution Doc for the current phase — activities, model routing, token budgets, VERIFY criteria.
How to install Phase Doc
Installs to ~/.claude/skills/valsecchi75-project-scaffolder-phase-doc/SKILL.md
mkdir -p ~/.claude/skills/valsecchi75-project-scaffolder-phase-doc && curl -fsSL https://raw.githubusercontent.com/valsecchi75/project-scaffolder/HEAD/commands/phase-doc.md -o ~/.claude/skills/valsecchi75-project-scaffolder-phase-doc/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Phase Doc does
name: phase-doc description: Generate the Execution Doc for the current phase — activities, model routing, token budgets, VERIFY criteria
/phase-doc — Phase Execution Document
Generate `docs/phases/PHASE-{N}-execution.md` for the current phase. This document is the hard gate: the Cortex refuses `/task` without it.
Steps
- Determine the current phase N from CLAUDE.md ("Current phase") and
wiki/product/roadmap.md. - If
docs/phases/PHASE-{N}-execution.mdalready exists → ask:
Alternatives in AI
- Oh My Claudecode — 32 specialized agents and 7 execution modes for Claude Code, with smart model routing and automatic paralleliz 10.9k ★
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Osaurus — Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cry 5.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Fable Director
Token governance for Claude Code: the top model directs, execution goes to the cheapest adequate means. Routin
AI Agent Process
Structured workflow template for AI-powered development with Claude Code, featuring iteration budgets, frozen
Crew Config
Configure CodeCrew settings - model tiers, default mode, token budgets, and more. Subcommands: show, set, rese
AI Execution Router
Claude Code skill that routes software-engineering issues to an execution profile (model role, effort, effort
Update Model Routing
Deep-research current public model benchmarks and refresh MODEL-ROUTING.md (the advisory per-task routing tabl
Agentic Engineering
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
Related Agents
LLM FinOps Architect
LLM FinOps Architect specializing in model-tier routing, cost-envelope governance, burn-rate monitoring, per-p
AI Provider Expert
Primary reviewer for AI provider integrations, model routing, embeddings, prompt systems, streaming, token eff
Doc Code Sync Checker
Use this agent when you need to verify that documentation (implementation plans, feature descriptions, or tech