MCP App StoreMCP App Store
from context-cooler10
Drastically reduce token burn by running heavy commands in sandboxed subprocesses and using indexed summaries instead of raw output.
Context Cooler provides a high-efficiency execution layer that prevents the LLM context window from being flooded by massive API responses or log files. It intercepts heavy skill commands, executes them in a sandbox, and returns a compact, intent-filtered summary while indexing the full result in a local FTS5 SQLite database for targeted retrieval.
ctx_run.py for sandboxed execution, ctx_batch.py for multi-skill pipelines, ctx_session.py for state snapshots, and ctx_search.py for querying indexed data.Designed for agents supporting shell execution and local file/database access, including Claude Code, Codex, and other MCP-compatible environments.
This skill has not been reviewed by our automated audit pipeline yet.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Go Data Structures
Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container
React Development Expert
Provides authoritative React guidance on hooks, state patterns, Server Components, performance optimization, and common architectural patterns.
Memory Search
Search past coding sessions and observations using natural-language queries to retrieve decisions, notes, and context.
Code Reviewer
Perform structured, prioritized code reviews that find correctness, security, performance, reliability, and testing issues and provide concrete fix suggestions.
dotLottie Web
Guidelines and patterns for implementing performant dotLottie/Lottie animations on the web (vanilla JS and React), including workers, state machines, and themin