Anthropic's official Claude Code plugin directory leads GitHub Trending for a second consecutive

Anthropic's official Claude Code plugin directory leads GitHub Trending for a second consecutive capture at +1,397 stars today (41,953 total); its README separates internal and external plugins, fixes published slugs, and warns that Anthropic does not control all included software.

ECC holds GitHub Trending #3 for a third capture (+1,145 stars today; 282,676 total in the scrape). Its README bundles cross-harness agents, skills, memory, commands, and security tooling; the snapshot does not independently validate its reported scale.

Anthropic's self-authored employment report says junior technical hires fell from 27% to 9% since early 2025, while meeting time per employee rose 20% year over year. These are company-specific, self-reported figures, not an economy-wide causal estimate.

DeepSeek's V4.1-Flash-1017 model card reports Terminal-Bench 4.0 of 42.3 vs. 31.2 and DeepSWE v1.1 of 77.0 vs. 74.2 for its prior checkpoint. These are vendor results; local inference documentation includes a custom encoding stack and no Jinja chat template.

HKUDS/CLI-Anything ranks #4 on GitHub Trending (+574 stars today; 54,165 total). Its project README describes a CLI Hub and demos that generate interfaces for GUI software, including CAD, 3D, diagrams, gameplay, and subtitles; demos are not independent reliability evidence.

Sphinx appeared in Show HN at 6 points and 0 comments 41 minutes after posting. Its Git hook asks developers to explain a committed change before configured pushes proceed, but the project says this is practice rather than a security gate and notes that checks are bypassable.

Caldera appears in today's Product Hunt capture, but the listing is dated October 12. Its Obsidian plugin describes selective profile/garden publishing and on-device identity keys; privacy and contact-filter behavior remain project claims rather than independently audited properties.

Claude by Anthropic is absent from the captured Google Play top 30 for a second consecutive day. This is a chart observation only; it does not establish installs, retention, or a causal change in demand.