MCP App StoreMCP App Store
from antigravity-skills868
Use the filesystem as an overflow and persistence layer for agent context — store large tool outputs, plans, logs, and sub-agent artifacts to keep active prompt
This skill teaches agents how to use the filesystem as a durable, searchable overflow layer for context. Instead of stuffing large outputs or long-running plans into the prompt, agents write them to files, return compact summaries or references, and selectively read back only the required sections. The skill covers scratch pads, plan persistence, sub-agent handoffs, terminal/log capture, and dynamic skill loading.
Activate when tool outputs exceed token budgets (e.g., >2k tokens), tasks span multiple turns, multiple agents must share state, or logs/terminals need selective retrieval. Avoid for single-turn interactions or when latency is critical.
Best suited for agents that support filesystem tools (Cursor, Claude Code, Copilot-like integrations). Works with any agent that can read/write files and run shell-style searches.
Well-crafted skill for using the filesystem as a context overflow layer for agents. The SKILL.md is thorough with clear patterns, gotchas, and integration notes. The bundled Python script implements three core patterns (scratch pad, plan persistence, tool output handler) with full type hints, docstrings, and a working demo. Script ran cleanly with exit code 0. No security concerns — pure local file operations with no network access or external dependencies.
High-quality skill. SKILL.md is comprehensive with excellent gotchas section and clear scope boundaries. Code is production-quality Python with proper dataclasses, type hints, and clean separation. Would benefit from more unique differentiation from standard context management approaches, but the execution is solid.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Moltpet - Digital Pets for Agents
Give agents persistent digital pets that hatch, evolve, and grow by recording daily moods and sentiment via a simple API.
OpenViking Memory Plugin
Provides automatic long-term memory capture and recall for OpenClaw agents: auto-capture, auto-recall, and memory management tools for more context-aware conver
Sync (Session Save-Point)
Fast, no-interaction session sync: append session-context files and MEMORY.md, print a concise summary; optional full run builds a capability inventory.
Save Codex Thread
Save the full Codex session transcript to Nowledge (nmem) so it can be searched, resumed, or referenced later. Includes command and workflow guidance.
Planning with Files
Manus-style file-based planning pattern: create task_plan.md, findings.md, and progress.md to manage complex multi-step work and session recovery.