What problem does it solve? Long multi-step tasks cause AI agents to lose track of goals after many tool calls, and context resets like /clear wipe all working memory. This Skill persists plans, findings, and progress to markdown files on disk so work survives context loss and stays organized. ## Core Features & Use Cases - File-Based Planning: Creates task_plan.md, findings.md, and progress.md in your project directory to track phases, decisions, errors, and session logs. - Session Recovery: Recovers unsynced context from previous sessions after /clear by analyzing session history and git diffs. - Parallel Plan Isolation: Supports multiple concurrent plans under .planning/<date>-<slug>/ directories with an active-plan pointer and PLAN_ID pinning. - Plan Integrity Attestation: Locks task_plan.md with a SHA-256 hash so hooks block injection of tampered plan content. - Use Case: When asked to research a topic, fix a bug, or build a feature spanning many steps, the agent writes a phased plan first, logs findings after every discovery, and resumes seamlessly after compaction or session breaks. ## Quick Start Ask the agent to plan out and break down your multi-step project using planning files before starting any work.
