Repository Audit

Page 1 of 4

  1. MuJoCo 4.0 Measured: 2,959× Better Integration, One Silent Actuator Change, and a Load Error That Never Says Why

    MuJoCo 4.0.0 has 61 changelog items, 13 in breaking boxes. Run side by side, RK4 error fell 2,959× and an armature-free actuator whipped to 447 rad/s.

    Open Source

  2. OpenMausBot Audited: 18,250 Stars, 1.07M Lines, and a Sandbox That Switches On Only in the Cloud

    OpenMausBot hit 18,250 stars in 89 days. Its bubblewrap sandbox is Apache-2.0, yet it defaults on only in the paid cloud; the self-host image lacks bwrap.

    AI

  3. Astryx Audited: Meta's 14,522-Star Design System Ran Its Own Agent Test Four Times, and the Floors Disagree

    Meta's Astryx has 14,522 stars and 6,948 commits, yet its own agent-discovery pilots measure bare installs at 0/5, 2/2 and 1/2. What ships, what does not.

    Developer Tools

  4. claude-red at 8,489 Stars: Its Own CONTRIBUTING.md Says Skills Without Frontmatter Won't Load — 28 of 79 Don't Have It, and They Hold 77% of the Bytes

    claude-red ships 79 SKILL.md files for Claude's skills system. Cloned on 2026-10-24: 28 of them have no YAML frontmatter, which the repo's own CONTRIBUTING.md says means …

    AI

  5. Anthropic's knowledge-work-plugins at 31,595 Stars: 123 Marketplace Entries, 11 in the README, and Only 2 of 17 Plugins Ship a Slash Command

    Anthropic's own plugin repo advertises 11 plugins and 'no code, no build steps'. Cloned on 2026-10-23 it contains 123 marketplace entries (101 pinned to 93 vendor repos), …

    AI

  6. Headroom at 77,253 Stars: 300 Log Lines Compressed to Zero, and Four Different Savings Numbers for the Same Tool

    Headroom advertises 20% fewer tokens for coding agents and 60-95% for JSON. Measured on 2026-10-22, a 300-line log became 35 tokens: '[300 lines compressed to 0. Retrieve …

    AI