filesystem-context

What problem does it solve? LLM context windows overflow when tool outputs, plans, and multi-agent state all compete for limited tokens, causing lost information and degraded attention. This Skill uses the filesystem as a persistent overflow layer so agents store, retrieve, and update context on demand instead of stuffing everything into the prompt. ## Core Features & Use Cases - Tool Output Offloading: Write large tool outputs to timestamped scratch files and return compact references with summaries, keeping only ~100 tokens in context. - Plan Persistence: Save structured multi-step plans to disk so agents can re-read objectives and progress after context refreshes or summarization. - Sub-Agent File Workspaces: Route sub-agent findings through per-agent directories instead of lossy message chains, with dynamic skill loading and terminal log persistence. - Use Case: A research agent receives an 8000-token web search result; it writes the output to scratch/search_results_001.txt, returns a one-line summary, and greps the file later for specific details. ## Quick Start Use the filesystem-context skill to offload large tool outputs to scratch files and persist my current plan to disk.