Every commit scored for change-risk against this repo's own history, so 'elevated' means elevated here rather than on some global curve.
Needs review
5 commits sit in this repo's top risk tercile, which is 31% of the 16scored. The cut is drawn against this codebase's own history rather than a global curve, so a quiet repo still fills its top band, and here it starts at 9.4 out of 10. What pushes a commit up is size and spread together: a large change confined to one area scores below a smaller one scattered across a dozen files.
Commit categories over time, read off the subject line. Fixes carry the accent because that is the series this chart exists to show.
How this repo's commit mix shifts over time.
Ranked by change-risk, highest first. Priority is a tercile of this repo's own distribution, so a quiet repo still fills its top band.
| # | Commit | Author | When | Lines | Risk | Top driver |
|---|---|---|---|---|---|---|
| 1 | 2261064ffeat: add multi-tool AI agent documentation with unified harness | Raymond Manaloto | 6mo ago | +5.5K -598 | 94%Elevated | more lines added than baseline |
| 2 | b6b5ddecfeat: integrate AI-first best practices framework (#1) | Raymond Manaloto | 6mo ago | +9.3K -127 | 94%Elevated | more lines added than baseline |
| 3 | 20d597badocs: add interactive diagrams and customization points for all tools | Raymond Manaloto | 6mo ago | +3.5K -71 | 84%Elevated | more lines added than baseline |
| 4 | 2c95460fAdd comprehensive AI/LLM agentic coding optimization | Raymond Manaloto | 6mo ago | +3.5K -0 | 78%Elevated | more lines added than baseline |
| 5 | b08e4998docs: add Aider documentation (8th tool) | Raymond Manaloto | 6mo ago | +726 -7 | 72%Elevated | more lines added than baseline |
| 6 | e63f9a3dfeat: add comprehensive browser test suite for interactive guide | Raymond Manaloto | 6mo ago | +306 -0 | 66%Typical | more lines added than baseline |
| 7 | 750a0b28Add Agent Skills (SKILL.md) as alternative to manual LLM optimization | Raymond Manaloto | 6mo ago | +300 -5 | 56%Typical | more lines added than baseline |
| 8 | 6cb10dc8Add LLM-OPTIMIZATION-TEMPLATE.md - minimal reusable template | Raymond Manaloto | 6mo ago | +249 -0 | 56%Typical | more lines added than baseline |
| 9 | 68051b9fAdd comprehensive Vercel Labs AI tools research | Raymond Manaloto | 6mo ago | +326 -0 | 47%Typical | more lines added than baseline |
| 10 | a86f6901Document .agents/skills/ as canonical directory to reduce duplication | Raymond Manaloto | 6mo ago | +135 -0 | 41%Typical | more lines added than baseline |
| 11 | 030b58f2Update all tool configs to reference entry points consistently | Raymond Manaloto | 6mo ago | +158 -185 | 34%Typical | more lines added than baseline |
| 12 | ef01fa9fdocs: add agent-browser (11.8k stars) and update Vercel Labs tools research | Raymond Manaloto | 6mo ago | +121 -23 | 28%Below typical | more lines added than baseline |
| 13 | 6b1911c6Restructure following agents.md best practices | Raymond Manaloto | 6mo ago | +107 -290 | 22%Below typical | more lines added than baseline |
| 14 | d9e479fcdocs: update tool count from 7 to 8 after adding Aider | Raymond Manaloto | 6mo ago | +20 -13 | 16%Below typical | more lines added than baseline |
| 15 | 7de3abf8Add .gitignore entries for installed skills | Raymond Manaloto | 6mo ago | +17 -0 | 9%Below typical | more lines added than baseline |
| 16 | c38e1f0dfix: resolve Mermaid rendering errors in interactive HTML | Raymond Manaloto | 6mo ago | +11 -37 | 3%Below typical | more focused than baseline |
Two views of the same model: where the cuts fall, and what commit shape lands you above them.
Every scored commit, binned on the raw 0 to 10 score rather than the percentile. Percentile ranks are uniform by construction, so that axis has no shape to draw. The dashed lines are the tercile cuts behind each row's priority pill.
The 16 most recent commits, on their own recency sample rather than the feed above: that defaults to risk-sorted, so reusing it would plot only the top tercile and call it the spread. Big and scattered is what the model penalises. Click a dot to open it.
ray-manaloto/ai-agent-study-guide has 16 commits in its history from 1 contributor, the first of them Jan 31, 2026. No file in the repository changed in the last 90 days. Every commit is scored for change risk from its size, spread and the history of the files it touches.
