Add instructions: research experiment discipline - #2854

Adds instructions/research-experiment-discipline.instructions.md — guidance for repositories where Copilot writes evaluation harnesses, benchmark sweeps, or any code that reports a performance number.

Falls under "Development methodologies and best practices" / "Testing strategies and quality assurance" in CONTRIBUTING. The gap it addresses: in research code the common failure is not a crash but a number that looks great and is wrong — models happily write evaluation code that tunes on the test set, compares against unmatched baselines, or reports point estimates inflated by group leakage. The instructions are specific and mechanical: null models scored first (freeze on a well-scoring null), calibration/held-out separation on the unit of independence, a held-out access budget, published-baseline reproduction before improvement claims, paired error bars, and every new check demonstrated to fail on a deliberately broken input.

Distilled from real failures in agent-run experiment campaigns; the longer-form methodology with runnable demonstrations lives at https://github.com/GuoCheng24/breakthrough-harness.

• Branch created from main
• npm start run; docs/README.instructions.md updated (the script also produced unrelated churn in docs/README.agents.md from live MCP-registry data — left out to keep the diff minimal; happy to include if the check requires it)