CLAUDE.md Evaluation
Does your CLAUDE.md actually help your coding agent?
A controlled before-and-after measurement in pinned Docker containers — same agent, same tasks, honest noise-envelope reporting.
No measurable effect0.0 pp± 20.0 pp · n=5×3 · isolated Docker
egress openn=5×3σ ±0.0 ppGemini (experimental)/gemini-2.5-flash
Measurement pipeline
Within noise across 4 evaluations under gemini-2.5-flash — no measurable effect detected so far.
Showing last export — commit 44983090, 13 Jun 2026. Re-run PRIMER and re-export to update.
Evaluations
- 4498309013 Jun 2026No measurable effect0.0 pp± 20.0 ppegress openView
- 4498309013 Jun 2026No measurable effect0.0 pp± 20.0 ppegress openView
- 4498309013 Jun 2026No measurable effect0.0 pp± 20.0 ppegress openView
- 449830905 Jun 2026No measurable effect0.0 pp± 20.0 ppegress openView
| Commit | Date | Verdict | Delta ± noise | Egress | Compare |
|---|---|---|---|---|---|
| 44983090 | 13 Jun 2026 | No measurable effect | 0.0 pp± 20.0 pp | open | compare → |
| 44983090 | 13 Jun 2026 | No measurable effect | 0.0 pp± 20.0 pp | open | compare → |
| 44983090 | 13 Jun 2026 | No measurable effect | 0.0 pp± 20.0 pp | open | compare → |
| 44983090 | 5 Jun 2026 | No measurable effect | 0.0 pp± 20.0 pp | open |