Claude Code

Page 1 of 8

  1. Claude-BugHunter Audited: 1,122 Declared Report Counts, 433 Clickable Citations, and the Two Skills Holding 59% of the 681 Headline With Nothing to Click

    I grepped all 83 skills: 8 of 36 pattern libraries contradict their own report_count, and 12,350 tokens of descriptions load every session.

    AI
  2. gstack Audited: 139,339 Stars for 'All Markdown' Hides 689,039 Lines of TypeScript, a 122-Version Lag Behind the Last Tag, and 20,616 Tokens Before /review Reads Your Diff

    gstack has 139,339 stars but 766 watchers. I cloned it: 689,039 TypeScript lines behind 'all Markdown' and 20,616 tokens before /review reads a diff.

    Developer Tools
  3. Worktrunk Audited: 153 Releases in 351 Days, a post-start Hook That Fails While wt switch Exits 0, and hash_port Ports That Collide Across Repositories

    Worktrunk has 10,479 stars and 153 releases in 351 days. I ran the binary: a failing post-start hook exits 0, merge deletes your cwd, hash_port collides.

    Developer Tools
  4. Same Version, Three Files: Auditing the Claude Code Extension Backdoor Against Both Public Registries

    Version 2.1.312 ships as two byte-identical clean builds on Microsoft and Open VSX, plus a backdoored one on Cursor. I hashed all three channels.

    Developer Tools
  5. claude-mem at 104,793 Stars: One LLM Call per Tool Event, a 400,000-Character History, and a 10,000-Character Ceiling That Fails Silently

    claude-mem at 104,793 stars runs one observer call per tool event and re-sends 400,000 chars of history; a 10,000-char ceiling fails silently

    AI
  6. Hallmark vs Impeccable: 118,552 Stars, 259 Watchers, and Each One's Linter Fails the Other's Showcase

    Two anti-slop design skills hold 118,552 stars and 259 watchers between them. I ran each one's deterministic linter over the other's showcase: Hallmark's sloplint found …

    Developer Tools