# Commit message and PR description tells > Source-anchored research for Commit message and PR description tells. Run status: COMPLETED. Parent: [LLM tells in code, commit messages, comments and READMEs](https://llms-explorer.com/tree/ai-isms-code-and-commit-tells/) · 3 facets · 6 facts · page: https://llms-explorer.com/tree/commit-message-and-pr-description-tells/ ## Structure and components - In one study of security-related AI-generated PRs, 70.4% of 2,823 commit messages were high quality (contain both Why and What) and 29.6% omitted one or both. (low confidence) — [source](https://arxiv.org/pdf/2604.19965) ## Measurements and reference values - A classifier on AIDev PRs identified which of five agents (Codex, Copilot, Devin, Cursor, Claude Code) authored a PR at 97.2% F1; commit-message features dominated, with multiline commit ratio the strongest single signal (44.7% importance). (low confidence) — [source](https://arxiv.org/html/2601.17406v1) - Per-agent signatures differ: Codex extensive multiline commits, Copilot longer PR descriptions, Cursor bullet points and hyperlinks, Devin multiline messages. Claude Code recall was only 57% in that study, so its tells are weaker. (low confidence) — [source](https://arxiv.org/html/2601.17406v1) ## Facts and statements - Claude Code by default appends a Co-Authored-By: Claude trailer to commit messages and a 'Generated with Claude Code' line to PR bodies; cloud sessions also add a claude.ai link. The attribution.commit, attribution.pr and attribution.sessionUrl settings change or hide them. (high confidence) (verified as of 2026-09-23) — [source](https://www.ssdnodes.com/learn/claude-code-commit-attribution) - Trailer tells are easily removed (git commit --amend, force-push, commit-msg hook), so their absence does not show human authorship. (low confidence) — [source](https://www.ssdnodes.com/learn/claude-code-commit-attribution) - Agent-authored PRs show message-code inconsistency: descriptions can claim functionality with no corresponding implementation, or describe changes incompletely. A description's confident summary therefore needs checking against the diff. (medium confidence) — [source](https://arxiv.org/pdf/2601.04886)