Activity, over time
Daily GitHub activity and social mentions.
Mentions
Daily posts linking to this repository
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Trending history
Daily top 10 · last 90 days · UTC
Mentions
Stars
Forks
Contributors
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
Scan pending.
Live mentions badge
Show how many posts mention your project in the last 30 days.
Live mentions · last 30 days
Mentions
Cognitive Gap: an agent skill to help you understand and maintain the code you build with AI We feed specs, docs, and existing code into coding agents and ask them to ship features quickly. As changes accumulate, it gets harder to track which assumptions became code, where behavior diverged from the spec, and why decisions were made. The codebase can grow faster than our understanding of it. I built Cognitive Gap, an open-source Agent Skill that keeps understanding connected to the whole task. It guides your agent to explain important decisions as it works, connect requirements to implementation and verification, and show the flow with diagrams when useful. The goal is to finish knowing why the code works, what was actually verified, and where to look when you need to change it. MIT-licensed, with no runtime dependencies or additional API keys. Installation instructions cover Codex, Claude Code, Copilot, Cursor, and other compatible agents. Related reading: Anthropic on AI assistance and coding skills and Microsoft Research/CMU on AI and critical thinking. GitHub: GiovanniPasq/cognitive-gap