What problem does it solve? Long-running AI agent tasks lose track of goals after many tool calls because context windows are volatile and limited. This Skill persists plans, findings, and progress to markdown files on disk so work survives context resets and session interruptions. ## Core Features & Use Cases - Persistent Planning Files: Creates and maintains task_plan.md, findings.md, and progress.md in your project directory as external working memory. - Session Recovery: A session-catchup script detects unsynced context from previous sessions after /clear, and hooks report phase completion status. - Structured Error Protocols: Enforces a 3-strike error protocol, error logging tables, and read-before-decide rules to prevent repeated failures. - Use Case: When starting a research project or multi-phase feature build requiring more than five tool calls, the agent creates a phased plan file first, logs discoveries after every two search operations, and resumes cleanly after interruptions. ## Quick Start Ask the agent to start a complex task using planning-with-files so it creates task_plan.md, findings.md, and progress.md in your project before executing.
