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.

Detect secrets + live validation. Map blast radius. Revoke fast. Use the CLI or embed in Rust and Python.

01Result

mongodb/kingfisher ↗

mongodb/kingfisher AI coding statistics: 4%

of 527 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

4% agent · top contributor 61.9%7 contributors

team

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

agent commits

506

other considered commits

agent contributors

61.9%

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

19assisted

2autonomous

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: 24.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	16	3%
GitHub Copilot	GitHub	3	0.6%
Cursor Agent	Anysphere	2	0.4%

03Evidence

Inspect the matches

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

Matched commit samples

f3f5eace on GitHubStop Jira pagination when the cursor stops being renewedClaude Code
a105a043 on GitHubBound the Atlassian keyword requirement to whole wordsClaude Code
3e728cb1 on GitHubRedact the token in JiraAuth's Debug outputClaude Code
f74e7494 on GitHubFix release job artifact download permissionsGitHub Copilot
763e6604 on GitHubInitial planGitHub Copilot
25219f2e on GitHubPotential fix for pull request findingGitHub Copilot
d892d120 on GitHubAdd Hugging Face user access token revocation support.Cursor Agent
ec8761c4 on GitHubFix NPM token validation and improve revocation reliabilityCursor Agent

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	650
Merge commits removed	−114
CI / dependency bots removed	−9
Considered	527

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 →Rust AI coding statisticsCompare evidence across Rust 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 mongodb/kingfisher

Scan another repository

Try

Month	Agent share	Considered commits
2026-01	0%	7
2026-02	1.8%	110
2026-03	2.1%	95
2026-04	0%	129
2026-05	2.1%	48
2026-06	0%	38
2026-07	5.9%	34
2026-08	24.6%	57
2026-09	0%	9