Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.
Cross-referenced across 55 tracked directories
#3023
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
8/17/2026
Created
7
GitHub Stars
Run an AI-powered security scan to analyze this package's source code for vulnerabilities, prompt injection vectors, data exfiltration risks, and behavior mismatches.
Scans fetch actual source code from the GitHub repository, not just the README.
Ivan Davidov
Placeholder — Production-grade Playwright + TypeScript Scaffold for Agentic Testing. Use: npm create agentic-playwright. Full release: September 2026.
...more0-co
MCP schema linter & quality grader — validate, audit, optimize, grade (A+ to F). Also: @tool → OpenAI, Claude, Gemini, MCP. Zero deps.
...moreadityaarsharma
🥒 Pickle — In a pickle? Pickle sorts it. Claude Code skill that scans Slack + ClickUp, extracts what needs you, tracks follow-ups. /pickle-slack · /pickle-clickup — by Aditya Sharma
...moreairmang
MCP server for AI agents to read, edit, inspect, and validate local HWPX documents.
1
Open Issues
10/5/2026
Last Commit
Recently added to the ecosystem