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.

A cloud-native Pipeline resource.

01Result

tektoncd/pipeline ↗

tektoncd/pipeline AI coding statistics: 14.5%

of 317 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

14.5% agent · top contributor 47.8%9 contributors

org-wide

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

agent commits

271

other considered commits

agent contributors

47.8%

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

46assisted

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: 21.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	42	13.2%
Cursor Agent	Anysphere	4	1.3%

03Evidence

Inspect the matches

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

Matched commit samples

209110c1 on GitHubAllow tt.params as a valid variable-reference prefixClaude Code
3ee1745a on GitHubfix: upload codecov coverage on pull requestsClaude Code
00b6de09 on GitHubfix: exclude generated and non-library code from codecov coverageClaude Code
e36d1a37 on GitHubUse folder-level symlinks for agent skill discoveryCursor Agent
1e86b7bd on GitHubAdd configuration for custom git resolver backoffCursor Agent
9bc4d9bb on GitHubfix(release): copy vendor tarball into kodata instead of symlinkCursor 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	617
Merge commits removed	−0
CI / dependency bots removed	−300
Considered	317

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Go AI coding statisticsCompare evidence across Go 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 tektoncd/pipeline

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	8.3%	36
2026-03	21.3%	75
2026-04	21.9%	32
2026-05	20.6%	34
2026-06	4.8%	62
2026-07	17.1%	41
2026-08	8%	25
2026-09	8.3%	12