← the index
OthmanAdi/planning-with-files
4%
of 326 commits were committed by an AI agent — a floor, not an estimate
4% agent · top contributor 23.1%6 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

13
agent commits
313
human commits
6
agent contributors
23.1%
largest contributor

Assisted or autonomous

13assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.

Agent share by month

Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 17.1%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic82.5%
OpenAI CodexOpenAI30.9%
Cursor AgentAnysphere20.6%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • 9375667ffix: prefer known system Python paths over PATH resolution in hook scriptsClaude Code
  • 34666a07fix: cap session-catchup output before injecting into model context (#138)Claude Code
  • 9f7c0d26fix: correct PowerShell syntax in Pi session-catchup invocation (#137)Claude Code
  • 4ffd78cePrefer current Codex thread for catchupOpenAI Codex
  • 14ea1099Tighten Codex catchup message parsingOpenAI Codex
  • 5df903e0Add Codex session catchup supportOpenAI Codex
  • 28e89aaedocs: rename moltbot.md to openclaw.mdCursor Agent
  • cbf393a5docs: update moltbot.md to use OpenClaw naming and pathsCursor Agent

What was excluded

Commits in window346
Merge commits removed20
CI / dependency bots removed0
Considered326

Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.

How this was measured

Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.

Run it yourself: npx qmmit-cli OthmanAdi/planning-with-files

Scan another repository