Measured catalogue entries associated with Code assistants.
Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF
Stars160Measured · Oct 25, 2026
Momentum22.67 days · Measured · +1.91% relative change
Disciplined Agentic Engineering — a methodology kit for Claude Code: acceptance-test-first specs, explicit checkpoints, and autonomy you can actually leave running. The engineer, atdd and crap-analyzer plugins.
Stars160Measured · Oct 25, 2026
Momentum22.67 days · Measured · +1.91% relative change
Murmur Connect (Murmur) — encrypted agent-to-agent messaging for AI coding agents. Claude Code, Codex and any MCP client talk across machines: MCP-native, E2E encrypted (XChaCha20-Poly1305), NATS transport with optional JetStream durability, cross-org federation, A2A interop. Mac and Windows apps, CLI on npm.
Stars20Measured · Oct 25, 2026
Momentum22.67 days · Measured · +5.26% relative change
Modular daily-planner Claude skill: builds an e-ink one-sheet and sends it to your reMarkable / Supernote / Kindle Scribe via Folio
Stars20Measured · Oct 25, 2026
Momentum22.67 days · Measured · +5.26% relative change
An autonomous LLM research agent that executes the full academic paper pipeline — from literature search to compiled PDF
Stars20Measured · Oct 25, 2026
Momentum22.67 days · Measured · +5.26% relative change
Agent 等待响应通知插件（支持Claude Code、CodeX、DeepSeek Harness、Reasonix） — 11 个渠道，短通知即时触达，长通知异步兜底。人可以闲着，Agent 不可以。
Stars20Measured · Oct 25, 2026
Momentum22.67 days · Measured · +5.26% relative change
Spec-driven development for coding agents — you manage the intent, the machine writes the code. Skills, conventions and git-hook guard rails.
Stars20Measured · Oct 25, 2026
Momentum22.67 days · Measured · +5.26% relative change
Lateral thinking skills for AI agents - 8 techniques + a router. de Bono for your coding agent.
Stars328Measured · Oct 25, 2026
Momentum22.57 days · Measured · +1.23% relative change
Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.
Stars168Measured · Oct 25, 2026
Momentum22.47 days · Measured · +1.82% relative change
Skills, prompts, and instructions for building AI agents on top of Dynatrace production context
Stars167Measured · Oct 25, 2026
Momentum22.47 days · Measured · +1.83% relative change