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.
Source
GitHub
Language
Python
Last activity
Oct 17, 2026
Stars166Measured · Oct 21, 2026
Momentum22.47 days · Measured · +1.84% relative change
Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human must decide. MIT.
Source
GitHub
Language
Shell
Last activity
Oct 21, 2026
Stars73Measured · Oct 21, 2026
Momentum22.27 days · Measured · +2.82% relative change
42 SEO commands for Claude Code — site audits, Ahrefs backlinks, GSC analytics, SERP research, content briefs, technical SEO, schema validation, and more
Source
GitHub
Language
Python
Last activity
Jun 11, 2026
Stars22Measured · Oct 21, 2026
Momentum21.97 days · Measured · +4.76% relative change
A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.
Source
GitHub
Language
HTML
Last activity
Sep 27, 2026
Stars1,667Measured · Oct 21, 2026
Momentum21.57 days · Measured · +0.36% relative change
CMMC 2.0 compliance advisor as a Claude Code skill. All 3 levels, 14 domains, 110 practices; CUI scoping, SSP + POA&M; modern IT mapping for cloud, productivity, AI services, endpoints; contractor profiles and anti-patterns. Built from public DoD and NIST sources.
Source
GitHub
Language
Python
Last activity
Apr 22, 2026
Stars23Measured · Oct 21, 2026
Momentum21.57 days · Measured · +4.55% relative change