phase-runner

Execute phased plans across multiple sessions using a four-file structure.

Updated Aug 27, 2026

Search Tags:#automation #workflow #multi-agent #orchestration #task-management #phase

Ready to run

npx skills add https://github.com/aiguy611/cc-tools --skill phase-runner-aiguy611

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: phase-runner
Source: https://github.com/aiguy611/cc-tools/tree/main/.github/skills/phase-runner
Command: npx skills add https://github.com/aiguy611/cc-tools --skill phase-runner-aiguy611

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Long-running automation phases require careful coordination to avoid context exhaustion and ensure progress across multiple agents, with graceful handoffs when limits are reached.

Core Features & Use Cases

Orchestrates a four-file phase structure (context, role, tasks, execution-plan) to drive deterministic wave-based execution
Enforces token-aware budgets and automatic handoffs to ensure continuity and recoverability
Supports multi-session orchestration via sub-agents and real-time task syncing

Quick Start

Activate phase runner on a directory containing the 4-file phase set (context, role, tasks, execution-plan) to begin executing waves.

Frequently Asked Questions about phase-runner

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I prevent context window exhaustion during long-running multi-agent automation workflows?▼

Multi-agent orchestration prevents context window exhaustion by enforcing token-aware tool budgets and triggering graceful handoffs to sub-agents. This ensures long-running task phases maintain progress and recoverability across multiple sessions without exceeding limits.

What is the best way to orchestrate phased task execution for plans with 20 or more tasks?▼

Phased task execution for large plans is best handled through a four-file structure—context, role, tasks, and execution-plan—driving deterministic wave-based execution. This method enforces tool budgets and requires real-time task syncing with timestamps to track progress.

Can I resume a multi-session automation workflow if a sub-agent reaches its token limit?▼

Yes, multi-session orchestration supports recoverability via graceful handoffs when token limits are reached. Sub-agents update phase files with completion timestamps in real-time, allowing the next wave to resume execution seamlessly from the last saved state.

Do I need specific files to start wave-based workflow automation?▼

Yes, wave-based automation requires a directory containing a four-file phase set: context, role, tasks, and execution-plan. Activating the orchestrator on this directory begins the deterministic execution of task waves with automatic token budget enforcement.

Why does multi-agent task management require real-time updates to execution files?▼

Real-time updates with timestamps are required to ensure progress tracking and recoverability across multiple sub-agents. This file syncing mechanism allows subsequent waves or handoff agents to verify completed tasks and resume the orchestration without losing context.

What are the limitations of using token-aware budget enforcement for workflow orchestration?▼

Token-aware budget enforcement limits the number of tool calls per phase to prevent context exhaustion, meaning very long task lists must be divided into multiple waves. If phase files are not updated with timestamps, subsequent sub-agents may lose orchestration state.