planning-with-files

What problem does it solve? Long tasks with many tool calls cause AI agents to lose track of goals, repeat failed actions, and forget earlier findings. This Skill stores plans, findings, and progress in markdown files so context survives long sessions and even session resets. ## Core Features & Use Cases - File-Based Planning: Creates task_plan.md, findings.md, and progress.md in your project directory to track phases, decisions, and errors. - Session Recovery: A session-catchup script detects unsynced context from a previous session so work can resume after /clear. - Error Discipline: Enforces a 3-strike error protocol and logs every failure to prevent repeating failed actions. - Use Case: When asked to research a topic, fix a bug, or build a feature spanning many steps, the agent writes a phase plan first, updates it after each phase, and re-reads it before major decisions. ## Quick Start Plan out this multi-step project using planning files and track progress as you work through each phase.