AGENTS.md Reduces Runtime by 28.64% — First Empirical Study

Shared entities / Same source domain / Shared topic / What happened next

46% of agentic PRs get rejected, and we now know the 14 reasons why.

Both cover CLAUDE, PRs; reported by the same outlet (arxiv.org); overlapping topics (agent, claude, empirical).

Shared entity: CLAUDE / Same source domain / Shared topic / What happened next / Tension

10 actionable skills from today's findings:

Both cover CLAUDE; reported by the same outlet (arxiv.org); overlapping topics (agent, claude, context, output).

Shared entities / Same source domain / Shared topic / What happened next

Your CLAUDE.md is doing something. Whether it helps depends entirely on how you wrote it.

Both cover CLAUDE, PRs; reported by the same outlet (arxiv.org); overlapping topics (agent, claude).

First Large-Scale Study of AI Coding Bots in CI/CD.

Both cover Claude, PRs; reported by the same outlet (arxiv.org); overlapping topics (claude, empirical).

Shared entities / Shared topic / What happened next / Tension

Two Named CVEs Turn Claude Code Project Files Into Attack Weapons

Both cover Claude, PRs; overlapping topics (agent, claude); picks up the Claude thread on 2026-03-20.

Shared entity: CLAUDE / Same source domain / Shared topic / What happened next / Tension

Architecture Descriptors Cut AI Coding Agent Navigation by 33-44%: 7,012 Claude Code Sessions Analyzed

Both cover CLAUDE; reported by the same outlet (arxiv.org); overlapping topics (agent, claude).

Shared entity: Claude / Same source domain / Shared topic / What happened next / Tension

LLM Web Agents Fail Dark Patterns 41–72% of the Time

Both cover Claude; reported by the same outlet (arxiv.org); overlapping topics (agent, claude).

Shared entity: Claude / Same source domain / Shared topic / What happened next

claude-mem crossed 80K stars. Persistent memory across 28+ agent runtimes from one install

Both cover Claude; reported by the same outlet (arxiv.org); overlapping topics (agent, claude, context).