Fix readme and docs to reflect provider/model syntax

[anakin87]

Description

When using the latest stable version of Verifiers (v0.1.9.post3), running prime eval run my-env -m gpt-5-nano fails with:

Invalid model: Model 'gpt-5-nano' not found or unavailable (GET https://api.pinference.ai/api/v1/models/gpt-5-nano → 404).

Using prime eval run my-env -m openai/gpt-5-nano works instead.

So I thought of updating README and docs. I also made some other small fixes.

@willccbb

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Test improvement

Testing

• All existing tests pass when running uv run pytest locally.
• New tests have been added to cover the changes

Checklist

• My code follows the style guidelines of this project as outlined in AGENTS.md
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Additional Notes

---

Note

Standardizes documentation and templates to the provider/model format and fixes minor examples/links.

• Update eval commands to use openai/... model IDs across README.md, AGENTS.md, docs/* (evaluation, FAQs, development, overview), verifiers/AGENTS.md, and the init.py README template
• Correct example code to reference vf.Rubric instead of Rubric
• Fix README doc links to point to docs/... paths

^{Written by Cursor Bugbot for commit b410460. This will update automatically on new commits. Configure here.}