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
3 commits sit in this repo's top risk tercile, which is 27% of the 11scored. 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 | 28d681f5Scaffold fluencydrift-mcp: TS/MCP skeleton + fluencyloop init | baokhang83claudeassisted | 2d ago | +3.2K -1 | 95%Elevated | more lines added than baseline |
| 2 | 262d6978Store reader: parse global and per-feature fluencyloop store JSONL | baokhang83claudeassisted | 2d ago | +2.4K -0 | 86%Elevated | more lines added than baseline |
| 3 | 33ff9c89Reality scanner + Drift engine: compare recorded architecture against reality | baokhang83claudeassisted | 2d ago | +689 -3 | 77%Elevated | more lines added than baseline |
| 4 | 1c81ecf7Real MCP tools: wire list_architectural_records, check_drift, explain_record (T6) | baokhang83claudeassisted | 2d ago | +300 -36 | 59%Typical | more lines added than baseline |
| 5 | 9aa8ae22Record resolver: latest-wins identity resolution + typed query API | baokhang83claudeassisted | 2d ago | +300 -3 | 59%Typical | more lines added than baseline |
| 6 | 56508bfbPlan: FluencyDrift MCP server (skeleton + drift detection) | baokhang83 | 2d ago | +218 -8 | 59%Typical | more lines added than baseline |
| 7 | cd644c4fMCP server skeleton: stdio transport + tool registration (T5) | baokhang83claudeassisted | 2d ago | +196 -103 | 41%Typical | more lines added than baseline |
| 8 | 36cd8496Package & dogfood smoke test: build, register with claude mcp add (T7) | baokhang83claudeassisted | 2d ago | +145 -14 | 32%Below typical | more lines added than baseline |
| 9 | 80f709bdRegenerate product-overview diagram for shipped architecture | baokhang83claudeassisted | 2d ago | +17 -11 | 23%Below typical | more lines added than baseline |
| 10 | fafb7983Initial commit | BaoKhang | 2d ago | +1 -0 | 14%Below typical | fewer lines added than baseline |
| 11 | 46aba13aFix: move product.md under docs/fluencyloop/distillations/ | baokhang83claudeassisted | 2d ago | +0 -0 | 5%Below typical | fewer lines added 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 11 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.
baokhang83/fluencydrift-mcp has 17 commits in its history from 2 contributors, the first of them Aug 13, 2026. In the last 90 days 32 files were touched, 36 times in total, most often index.ts. Every commit is scored for change risk from its size, spread and the history of the files it touches.
