Dataset: 2026-10-27-catalog-ai-v2
Ruleset: b2e8889c66f7
Scanned: 2026-10-27
Window: February–September 15, 2026

Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

SQL views for Dune

01Result

duneanalytics/spellbook ↗

duneanalytics/spellbook AI coding statistics: 35.4%

of 494 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

35.4% agent · top contributor 40%20 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

175

agent commits

319

other considered commits

agent contributors

40%

largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

175assisted

0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Peak month: 47.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	114	23.1%
Claude Code	Anthropic	68	13.8%
GitHub Copilot	GitHub	1	0.2%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

5726ec35 on GitHubfix: dedupe vvs cronos v2 merge keys after factory re-inclusion (#10006)Cursor Agent
395126d0 on GitHubfeat: add Uniswap V4 on X Layer to dex.trades (#9954)Cursor Agent
7473d646 on GitHubAdd Uniswap V4 on X Layer to dex.trades (#9950)Cursor Agent
a11399f6 on GitHubfix(dex): band synthetic evt_index away from real log indices (#9989)Claude Code
62ee319b on GitHubfeat(dex): add Agra DEX (ethereum, hyperevm, monad) (#9881)Claude Code
458433b8 on GitHubfix(oneinch): drop merge target predicate that duplicated late-settled croClaude Code
997717f7 on GitHubfeat: add rp11 (#9298)GitHub Copilot

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window	495
Merge commits removed	−0
CI / dependency bots removed	−1
Considered	494

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Python AI coding statisticsCompare evidence across Python repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →

Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli duneanalytics/spellbook

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	26.7%	75
2026-03	43%	93
2026-04	21.5%	79
2026-05	46.3%	54
2026-06	39.4%	99
2026-07	47.2%	53
2026-08	23.3%	30
2026-09	18.2%	11